@cursor/july 0.1.91 → 0.1.92
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +4 -0
- package/dist/docs/404.html +3 -1
- package/dist/docs/ab.html +4 -2
- package/dist/docs/ab.md +338 -0
- package/dist/docs/building-with-agents.html +4 -2
- package/dist/docs/building-with-agents.md +124 -0
- package/dist/docs/concepts.html +4 -2
- package/dist/docs/concepts.md +174 -0
- package/dist/docs/deployment.html +4 -2
- package/dist/docs/deployment.md +464 -0
- package/dist/docs/evals.html +4 -2
- package/dist/docs/evals.md +481 -0
- package/dist/docs/example-agents/approval-buddy.html +4 -2
- package/dist/docs/example-agents/approval-buddy.md +266 -0
- package/dist/docs/example-agents/benny.html +4 -2
- package/dist/docs/example-agents/benny.md +182 -0
- package/dist/docs/example-agents/bugbot.html +4 -2
- package/dist/docs/example-agents/bugbot.md +229 -0
- package/dist/docs/example-agents/codebase-wiki.html +4 -2
- package/dist/docs/example-agents/codebase-wiki.md +170 -0
- package/dist/docs/example-agents/codeowners-review.html +4 -2
- package/dist/docs/example-agents/codeowners-review.md +192 -0
- package/dist/docs/example-agents/concierge.html +4 -2
- package/dist/docs/example-agents/concierge.md +201 -0
- package/dist/docs/example-agents/fsd.html +4 -2
- package/dist/docs/example-agents/fsd.md +329 -0
- package/dist/docs/example-agents/index.html +4 -2
- package/dist/docs/example-agents/index.md +102 -0
- package/dist/docs/example-agents/knowledge-base.html +4 -2
- package/dist/docs/example-agents/knowledge-base.md +168 -0
- package/dist/docs/example-agents/oncall.html +4 -2
- package/dist/docs/example-agents/oncall.md +212 -0
- package/dist/docs/example-agents/security-reviewer.html +4 -2
- package/dist/docs/example-agents/security-reviewer.md +265 -0
- package/dist/docs/example-agents/slack-agent.html +4 -2
- package/dist/docs/example-agents/slack-agent.md +142 -0
- package/dist/docs/example-agents/weather-agent.html +4 -2
- package/dist/docs/example-agents/weather-agent.md +296 -0
- package/dist/docs/guides/agent-to-agent.html +4 -2
- package/dist/docs/guides/agent-to-agent.md +113 -0
- package/dist/docs/guides/cloud-runtime.html +4 -2
- package/dist/docs/guides/cloud-runtime.md +131 -0
- package/dist/docs/guides/convert-automation.html +4 -2
- package/dist/docs/guides/convert-automation.md +171 -0
- package/dist/docs/guides/github.html +4 -2
- package/dist/docs/guides/github.md +287 -0
- package/dist/docs/guides/human-in-the-loop.html +4 -2
- package/dist/docs/guides/human-in-the-loop.md +126 -0
- package/dist/docs/guides/mcp-oauth.html +4 -2
- package/dist/docs/guides/mcp-oauth.md +159 -0
- package/dist/docs/guides/opentelemetry.html +4 -2
- package/dist/docs/guides/opentelemetry.md +209 -0
- package/dist/docs/guides/slack.html +4 -2
- package/dist/docs/guides/slack.md +337 -0
- package/dist/docs/guides/webhooks.html +4 -2
- package/dist/docs/guides/webhooks.md +463 -0
- package/dist/docs/hillclimbing.html +4 -2
- package/dist/docs/hillclimbing.md +88 -0
- package/dist/docs/index.html +4 -2
- package/dist/docs/index.md +179 -0
- package/dist/docs/llms-full.txt +11518 -0
- package/dist/docs/llms.txt +75 -0
- package/dist/docs/quickstart.html +4 -2
- package/dist/docs/quickstart.md +364 -0
- package/dist/docs/reference/agent-config.html +4 -2
- package/dist/docs/reference/agent-config.md +256 -0
- package/dist/docs/reference/artifacts.html +4 -2
- package/dist/docs/reference/artifacts.md +112 -0
- package/dist/docs/reference/channels.html +4 -2
- package/dist/docs/reference/channels.md +255 -0
- package/dist/docs/reference/cli.html +4 -2
- package/dist/docs/reference/cli.md +957 -0
- package/dist/docs/reference/connections.html +4 -2
- package/dist/docs/reference/connections.md +268 -0
- package/dist/docs/reference/hooks.html +4 -2
- package/dist/docs/reference/hooks.md +102 -0
- package/dist/docs/reference/http-api.html +4 -2
- package/dist/docs/reference/http-api.md +267 -0
- package/dist/docs/reference/instructions.html +4 -2
- package/dist/docs/reference/instructions.md +74 -0
- package/dist/docs/reference/playground.html +4 -2
- package/dist/docs/reference/playground.md +62 -0
- package/dist/docs/reference/project-layout.html +4 -2
- package/dist/docs/reference/project-layout.md +107 -0
- package/dist/docs/reference/prompt.html +4 -2
- package/dist/docs/reference/prompt.md +42 -0
- package/dist/docs/reference/schedules.html +4 -2
- package/dist/docs/reference/schedules.md +215 -0
- package/dist/docs/reference/sessions.html +4 -2
- package/dist/docs/reference/sessions.md +170 -0
- package/dist/docs/reference/skills.html +4 -2
- package/dist/docs/reference/skills.md +83 -0
- package/dist/docs/reference/subagents.html +4 -2
- package/dist/docs/reference/subagents.md +71 -0
- package/dist/docs/reference/tools.html +4 -2
- package/dist/docs/reference/tools.md +298 -0
- package/dist/docs/scaffolding-agents.html +4 -2
- package/dist/docs/scaffolding-agents.md +130 -0
- package/dist/docs/storage.html +4 -2
- package/dist/docs/storage.md +219 -0
- package/dist/docs/templates/agentic-owners.html +4 -2
- package/dist/docs/templates/agentic-owners.md +92 -0
- package/dist/docs/templates/demo.html +4 -2
- package/dist/docs/templates/demo.md +79 -0
- package/dist/docs/templates/pr-autofixer.html +4 -2
- package/dist/docs/templates/pr-autofixer.md +131 -0
- package/dist/docs/templates/security-reviewer.html +4 -2
- package/dist/docs/templates/security-reviewer.md +84 -0
- package/dist/docs/templates/triage.html +4 -2
- package/dist/docs/templates/triage.md +98 -0
- package/dist/docs/troubleshooting.html +4 -2
- package/dist/docs/troubleshooting.md +111 -0
- package/dist/internal/init-scaffold.d.ts.map +1 -1
- package/dist/internal/init-scaffold.js +1 -0
- package/dist/internal/playground/static.d.ts.map +1 -1
- package/dist/internal/playground/static.js +2 -0
- package/dist/internal/session-engine.d.ts.map +1 -1
- package/dist/internal/session-engine.js +3 -1
- package/package.json +2 -2
- package/skills/ab/SKILL.md +3 -0
- package/skills/create-agent/SKILL.md +3 -0
- package/skills/debug/SKILL.md +3 -0
- package/skills/evals/SKILL.md +3 -0
- package/skills/framework-map/SKILL.md +3 -0
- package/skills/github/SKILL.md +3 -0
- package/skills/hillclimb/SKILL.md +3 -0
- package/skills/mcp-auth/SKILL.md +3 -0
- package/skills/otel/SKILL.md +3 -0
- package/skills/setup-slack/SKILL.md +3 -0
- package/src/internal/init-scaffold.ts +1 -0
- package/src/internal/playground/static.ts +2 -0
- package/src/internal/session-engine.ts +4 -6
|
@@ -16,13 +16,15 @@
|
|
|
16
16
|
<link rel="modulepreload" href="/docs/assets/hillclimbing.md.ywF3yDAd.lean.js">
|
|
17
17
|
<script id="check-dark-mode">(()=>{const e=localStorage.getItem("vitepress-theme-appearance")||"auto",a=window.matchMedia("(prefers-color-scheme: dark)").matches;(!e||e==="auto"?a:e==="dark")&&document.documentElement.classList.add("dark")})();</script>
|
|
18
18
|
<script id="check-mac-os">document.documentElement.classList.toggle("mac",/Mac|iPhone|iPod|iPad/i.test(navigator.platform));</script>
|
|
19
|
+
<link rel="alternate" type="text/plain" href="/docs/llms.txt">
|
|
20
|
+
<link rel="alternate" type="text/markdown" href="/docs/hillclimbing.md">
|
|
19
21
|
</head>
|
|
20
22
|
<body>
|
|
21
|
-
<div id="app"><div class="Layout" data-v-282c430e><!--[--><!--]--><!--[--><span tabindex="-1" data-v-af8643bc></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-af8643bc>Skip to content</a><!--]--><!----><header class="VPNav" data-v-282c430e data-v-4751689a><div class="VPNavBar" data-v-4751689a data-v-d2a336f3><div class="wrapper" data-v-d2a336f3><div class="container" data-v-d2a336f3><div class="title" data-v-d2a336f3><div class="VPNavBarTitle has-sidebar" data-v-d2a336f3 data-v-3a787a7b><a class="title" href="/docs/" data-v-3a787a7b><!--[--><!--]--><!----><span data-v-3a787a7b>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.91" data-v-c26a5f4f>0.1.91</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-d2a336f3><div class="content-body" data-v-d2a336f3><!--[--><!--]--><div class="VPNavBarSearch search" data-v-d2a336f3><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-d2a336f3 data-v-b60c0a58><span id="main-nav-aria-label" class="visually-hidden" data-v-b60c0a58> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/example-agents/" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Examples</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-d2a336f3 data-v-d559fc20><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-d559fc20 data-v-deaafa36 data-v-88da49d2><span class="check" data-v-88da49d2><span class="icon" data-v-88da49d2><!--[--><span class="vpi-sun sun" data-v-deaafa36></span><span class="vpi-moon moon" data-v-deaafa36></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-d2a336f3 data-v-75b97eb1 data-v-ed271fd4><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-ed271fd4><span class="vpi-more-horizontal icon" data-v-ed271fd4></span></button><div class="menu" data-v-ed271fd4><div class="VPMenu" data-v-ed271fd4 data-v-505057d2><!----><!--[--><!--[--><!----><div class="group" data-v-75b97eb1><div class="item appearance" data-v-75b97eb1><p class="label" data-v-75b97eb1>Appearance</p><div class="appearance-action" data-v-75b97eb1><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-75b97eb1 data-v-deaafa36 data-v-88da49d2><span class="check" data-v-88da49d2><span class="icon" data-v-88da49d2><!--[--><span class="vpi-sun sun" data-v-deaafa36></span><span class="vpi-moon moon" data-v-deaafa36></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-d2a336f3 data-v-966f1ac7><span class="container" data-v-966f1ac7><span class="top" data-v-966f1ac7></span><span class="middle" data-v-966f1ac7></span><span class="bottom" data-v-966f1ac7></span></span></button></div></div></div></div><div class="divider" data-v-d2a336f3><div class="divider-line" data-v-d2a336f3></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-282c430e data-v-f96f8409><div class="container" data-v-f96f8409><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-f96f8409><span class="vpi-align-left menu-icon" data-v-f96f8409></span><span class="menu-text" data-v-f96f8409>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-f96f8409 data-v-1bc67f4b><button data-v-1bc67f4b>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-282c430e data-v-3d1258d2><div class="curtain" data-v-3d1258d2></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-3d1258d2><span class="visually-hidden" id="sidebar-aria-label" data-v-3d1258d2> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Getting started</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Convert a Cursor Automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/concepts.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Templates</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/demo.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Demo agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agentic Owners</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0 has-active" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Improving agents</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/evals.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/ab.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Live A/B metrics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/storage.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Guides</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Host MCP OAuth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/cloud-runtime.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Cloud runtime</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>OpenTelemetry</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Example agents</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Choose an example</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/weather-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Weather agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/slack-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Slack agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/concierge.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Concierge</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/benny.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Playbook router</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/oncall.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Alert investigator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/bugbot.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>PR evidence reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/approval-buddy.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Approval Buddy</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/security-reviewer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Security Reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/fsd.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Remote PR coordinator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/knowledge-base.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Knowledge base</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/codebase-wiki.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Codebase wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/codeowners-review.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Codeowners review</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Operating</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/deployment.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0 collapsible" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-61fcdc7c><span class="vpi-chevron-right caret-icon" data-v-61fcdc7c></span></div></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-282c430e data-v-3b8d81ee><div class="VPDoc has-sidebar has-aside" data-v-3b8d81ee data-v-2e506a34><!--[--><!--]--><div class="container" data-v-2e506a34><div class="aside" data-v-2e506a34><div class="aside-curtain" data-v-2e506a34></div><div class="aside-container" data-v-2e506a34><div class="aside-content" data-v-2e506a34><div class="VPDocAside" data-v-2e506a34 data-v-b485a79e><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-b485a79e data-v-cc6b345c><div class="content" data-v-cc6b345c><div class="outline-marker" data-v-cc6b345c></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-cc6b345c>On this page</div><ul class="VPDocOutlineItem root" data-v-cc6b345c data-v-4f0215bf><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-b485a79e></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-2e506a34><div class="content-container" data-v-2e506a34><!--[--><!--]--><main class="main" data-v-2e506a34><div style="position:relative;" class="vp-doc _docs_hillclimbing" data-v-2e506a34><div><h1 id="hillclimbing" tabindex="-1">Hillclimbing <a class="header-anchor" href="#hillclimbing" aria-label="Permalink to "Hillclimbing""></a></h1><p>Make an agent better on fixed inputs: measure, change one lever, remeasure, and lock every kept win with an eval.</p><h2 id="what-is-hillclimbing" tabindex="-1">What is hillclimbing? <a class="header-anchor" href="#what-is-hillclimbing" aria-label="Permalink to "What is hillclimbing?""></a></h2><p>Hillclimbing is a measured improvement loop. You pin a few fixtures, name the one dominant problem in the run, change one lever, and check the same fixtures again. Keep only what helps. Every kept change lands an <a href="./evals.html">eval</a> so the win stays put.</p><p>You don't have to run the loop alone. The package ships a coding-agent skill that drives it with you.</p><div class="language-mermaid vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">mermaid</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">flowchart LR</span></span>
|
|
23
|
+
<div id="app"><div class="Layout" data-v-282c430e><!--[--><!--]--><!--[--><span tabindex="-1" data-v-af8643bc></span><a href="#VPContent" class="VPSkipLink visually-hidden" data-v-af8643bc>Skip to content</a><!--]--><!----><header class="VPNav" data-v-282c430e data-v-4751689a><div class="VPNavBar" data-v-4751689a data-v-d2a336f3><div class="wrapper" data-v-d2a336f3><div class="container" data-v-d2a336f3><div class="title" data-v-d2a336f3><div class="VPNavBarTitle has-sidebar" data-v-d2a336f3 data-v-3a787a7b><a class="title" href="/docs/" data-v-3a787a7b><!--[--><!--]--><!----><span data-v-3a787a7b>Agent SDK</span><!--[--><!--[--><!--[--><!--[--><span class="agent-sdk-version" title="@cursor/july 0.1.92" data-v-c26a5f4f>0.1.92</span><!--]--><!--]--><!--]--><!--]--></a></div></div><div class="content" data-v-d2a336f3><div class="content-body" data-v-d2a336f3><!--[--><!--]--><div class="VPNavBarSearch search" data-v-d2a336f3><!--[--><!----><div id="local-search"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><span class="vp-icon DocSearch-Search-Icon"></span><span class="DocSearch-Button-Placeholder">Search</span></span><span class="DocSearch-Button-Keys"><kbd class="DocSearch-Button-Key"></kbd><kbd class="DocSearch-Button-Key">K</kbd></span></button></div><!--]--></div><nav aria-labelledby="main-nav-aria-label" class="VPNavBarMenu menu" data-v-d2a336f3 data-v-b60c0a58><span id="main-nav-aria-label" class="visually-hidden" data-v-b60c0a58> Main Navigation </span><!--[--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/quickstart.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Quickstart</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/guides/webhooks.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Guides</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/example-agents/" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Examples</span><!--]--></a><!--]--><!--[--><a class="VPLink link VPNavBarMenuLink" href="/docs/reference/project-layout.html" tabindex="0" data-v-b60c0a58 data-v-74de87b9><!--[--><span data-v-74de87b9>Reference</span><!--]--></a><!--]--><!--]--></nav><!----><div class="VPNavBarAppearance appearance" data-v-d2a336f3 data-v-d559fc20><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-d559fc20 data-v-deaafa36 data-v-88da49d2><span class="check" data-v-88da49d2><span class="icon" data-v-88da49d2><!--[--><span class="vpi-sun sun" data-v-deaafa36></span><span class="vpi-moon moon" data-v-deaafa36></span><!--]--></span></span></button></div><!----><div class="VPFlyout VPNavBarExtra extra" data-v-d2a336f3 data-v-75b97eb1 data-v-ed271fd4><button type="button" class="button" aria-haspopup="true" aria-expanded="false" aria-label="extra navigation" data-v-ed271fd4><span class="vpi-more-horizontal icon" data-v-ed271fd4></span></button><div class="menu" data-v-ed271fd4><div class="VPMenu" data-v-ed271fd4 data-v-505057d2><!----><!--[--><!--[--><!----><div class="group" data-v-75b97eb1><div class="item appearance" data-v-75b97eb1><p class="label" data-v-75b97eb1>Appearance</p><div class="appearance-action" data-v-75b97eb1><button class="VPSwitch VPSwitchAppearance" type="button" role="switch" title aria-checked="false" data-v-75b97eb1 data-v-deaafa36 data-v-88da49d2><span class="check" data-v-88da49d2><span class="icon" data-v-88da49d2><!--[--><span class="vpi-sun sun" data-v-deaafa36></span><span class="vpi-moon moon" data-v-deaafa36></span><!--]--></span></span></button></div></div></div><!----><!--]--><!--]--></div></div></div><!--[--><!--]--><button type="button" class="VPNavBarHamburger hamburger" aria-label="mobile navigation" aria-expanded="false" aria-controls="VPNavScreen" data-v-d2a336f3 data-v-966f1ac7><span class="container" data-v-966f1ac7><span class="top" data-v-966f1ac7></span><span class="middle" data-v-966f1ac7></span><span class="bottom" data-v-966f1ac7></span></span></button></div></div></div></div><div class="divider" data-v-d2a336f3><div class="divider-line" data-v-d2a336f3></div></div></div><!----></header><div class="VPLocalNav has-sidebar empty" data-v-282c430e data-v-f96f8409><div class="container" data-v-f96f8409><button class="menu" aria-expanded="false" aria-controls="VPSidebarNav" data-v-f96f8409><span class="vpi-align-left menu-icon" data-v-f96f8409></span><span class="menu-text" data-v-f96f8409>Menu</span></button><div class="VPLocalNavOutlineDropdown" style="--vp-vh:0px;" data-v-f96f8409 data-v-1bc67f4b><button data-v-1bc67f4b>Return to top</button><!----></div></div></div><aside class="VPSidebar" data-v-282c430e data-v-3d1258d2><div class="curtain" data-v-3d1258d2></div><nav class="nav" id="VPSidebarNav" aria-labelledby="sidebar-aria-label" tabindex="-1" data-v-3d1258d2><span class="visually-hidden" id="sidebar-aria-label" data-v-3d1258d2> Sidebar Navigation </span><!--[--><!--]--><!--[--><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Getting started</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Overview</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/quickstart.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Quickstart</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/scaffolding-agents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Scaffold an agent with Cursor</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/convert-automation.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Convert a Cursor Automation</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/concepts.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Concepts</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Templates</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/demo.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Demo agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/security-reviewer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Security reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/agentic-owners.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agentic Owners</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/pr-autofixer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>PR autofixer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/templates/triage.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Triage agent</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0 has-active" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Improving agents</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/building-with-agents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Building agents with agents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/evals.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Evals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/ab.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Live A/B metrics</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/storage.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Storage</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/hillclimbing.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Hillclimbing</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Guides</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/webhooks.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Webhooks & custom channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/github.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>GitHub</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/slack.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Slack</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/human-in-the-loop.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Human-in-the-loop approvals</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/agent-to-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agent-to-agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/mcp-oauth.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Host MCP OAuth</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/cloud-runtime.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Cloud runtime</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/guides/opentelemetry.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>OpenTelemetry</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Example agents</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Choose an example</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/weather-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Weather agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/slack-agent.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Slack agent</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/concierge.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Concierge</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/benny.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Playbook router</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/oncall.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Alert investigator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/bugbot.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>PR evidence reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/approval-buddy.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Approval Buddy</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/security-reviewer.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Security Reviewer</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/fsd.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Remote PR coordinator</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/knowledge-base.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Knowledge base</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/codebase-wiki.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Codebase wiki</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/example-agents/codeowners-review.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Codeowners review</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Operating</h2><!----></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/deployment.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Deployment</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/troubleshooting.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Fix common problems</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><div class="no-transition group" data-v-f2306e18><section class="VPSidebarItem level-0 collapsible" data-v-f2306e18 data-v-61fcdc7c><div class="item" role="button" tabindex="0" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><h2 class="text" data-v-61fcdc7c>Reference</h2><div class="caret" role="button" aria-label="toggle section" tabindex="0" data-v-61fcdc7c><span class="vpi-chevron-right caret-icon" data-v-61fcdc7c></span></div></div><div class="items" data-v-61fcdc7c><!--[--><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/project-layout.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Project layout</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/agent-config.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Agent config</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/instructions.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Instructions</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/tools.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Tools</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/prompt.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>prompt</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/skills.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Skills</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/connections.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>MCP Connections</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/subagents.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Subagents</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/channels.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Channels</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/schedules.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Schedules & reminders</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/hooks.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Hooks</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/artifacts.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Artifacts</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/sessions.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Sessions & streaming</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/playground.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>Playground</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/cli.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>CLI</p><!--]--></a><!----></div><!----></div><div class="VPSidebarItem level-1 is-link" data-v-61fcdc7c><div class="item" data-v-61fcdc7c><div class="indicator" data-v-61fcdc7c></div><a class="VPLink link link" href="/docs/reference/http-api.html" data-v-61fcdc7c><!--[--><p class="text" data-v-61fcdc7c>HTTP API</p><!--]--></a><!----></div><!----></div><!--]--></div></section></div><!--]--><!--[--><!--]--></nav></aside><div class="VPContent has-sidebar" id="VPContent" data-v-282c430e data-v-3b8d81ee><div class="VPDoc has-sidebar has-aside" data-v-3b8d81ee data-v-2e506a34><!--[--><!--]--><div class="container" data-v-2e506a34><div class="aside" data-v-2e506a34><div class="aside-curtain" data-v-2e506a34></div><div class="aside-container" data-v-2e506a34><div class="aside-content" data-v-2e506a34><div class="VPDocAside" data-v-2e506a34 data-v-b485a79e><!--[--><!--]--><!--[--><!--]--><nav aria-labelledby="doc-outline-aria-label" class="VPDocAsideOutline" data-v-b485a79e data-v-cc6b345c><div class="content" data-v-cc6b345c><div class="outline-marker" data-v-cc6b345c></div><div aria-level="2" class="outline-title" id="doc-outline-aria-label" role="heading" data-v-cc6b345c>On this page</div><ul class="VPDocOutlineItem root" data-v-cc6b345c data-v-4f0215bf><!--[--><!--]--></ul></div></nav><!--[--><!--]--><div class="spacer" data-v-b485a79e></div><!--[--><!--]--><!----><!--[--><!--]--><!--[--><!--]--></div></div></div></div><div class="content" data-v-2e506a34><div class="content-container" data-v-2e506a34><!--[--><!--]--><main class="main" data-v-2e506a34><div style="position:relative;" class="vp-doc _docs_hillclimbing" data-v-2e506a34><div><h1 id="hillclimbing" tabindex="-1">Hillclimbing <a class="header-anchor" href="#hillclimbing" aria-label="Permalink to "Hillclimbing""></a></h1><p>Make an agent better on fixed inputs: measure, change one lever, remeasure, and lock every kept win with an eval.</p><h2 id="what-is-hillclimbing" tabindex="-1">What is hillclimbing? <a class="header-anchor" href="#what-is-hillclimbing" aria-label="Permalink to "What is hillclimbing?""></a></h2><p>Hillclimbing is a measured improvement loop. You pin a few fixtures, name the one dominant problem in the run, change one lever, and check the same fixtures again. Keep only what helps. Every kept change lands an <a href="./evals.html">eval</a> so the win stays put.</p><p>You don't have to run the loop alone. The package ships a coding-agent skill that drives it with you.</p><div class="language-mermaid vp-adaptive-theme"><button title="Copy Code" class="copy"></button><span class="lang">mermaid</span><pre class="shiki shiki-themes github-light github-dark vp-code" tabindex="0"><code><span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;">flowchart LR</span></span>
|
|
22
24
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> measure[Measure] --> change[Change one lever]</span></span>
|
|
23
25
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> change --> remeasure[Remeasure]</span></span>
|
|
24
26
|
<span class="line"><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8;"> remeasure --> measure</span></span></code></pre></div><h2 id="how-do-i-hillclimb-an-agent-with-a-coding-agent" tabindex="-1">How do I hillclimb an agent with a coding agent? <a class="header-anchor" href="#how-do-i-hillclimb-an-agent-with-a-coding-agent" aria-label="Permalink to "How do I hillclimb an agent with a coding agent?""></a></h2><p>Have Cursor read <a href="./../skills/hillclimb/SKILL.html"><code>skills/hillclimb/SKILL.md</code></a>.</p><p>Tell it:</p><ol><li><strong>Which agent</strong> you're improving (path or slug)</li><li><strong>One to three fixtures</strong> you'll reuse every round: a PR URL, a saved webhook body, or a canonical chat prompt</li><li><strong>What "better" means</strong> this round: correct tool choice, fewer tools, lower latency, or output quality. Name the freeze line too: API shape, public output, and existing evals that must stay green</li></ol><p>The skill serves the agent, hits your fixtures, reads the session trajectory, proposes one change, remeasures, and checks with you before the next round.</p><p>Other skills cover the edges:</p><table tabindex="0"><thead><tr><th>When you need…</th><th>Skill</th></tr></thead><tbody><tr><td>The measured improvement loop</td><td><a href="./../skills/hillclimb/SKILL.html"><code>skills/hillclimb/SKILL.md</code></a></td></tr><tr><td>An eval that locks a kept win</td><td><a href="./../skills/evals/SKILL.html"><code>skills/evals/SKILL.md</code></a></td></tr><tr><td>Repeatable GitHub webhook inputs</td><td><a href="./../skills/github/SKILL.html"><code>skills/github/SKILL.md</code></a></td></tr><tr><td>A run that misbehaves</td><td><a href="./../skills/debug/SKILL.html"><code>skills/debug/SKILL.md</code></a></td></tr></tbody></table><p>See <a href="./building-with-agents.html">Building agents with agents</a> for every framework skill and a good first prompt.</p><h2 id="what-do-i-need-before-a-hillclimb-round" tabindex="-1">What do I need before a hillclimb round? <a class="header-anchor" href="#what-do-i-need-before-a-hillclimb-round" aria-label="Permalink to "What do I need before a hillclimb round?""></a></h2><p>Agree on four things before you edit:</p><ol><li><strong>The target agent</strong>: the project you're improving</li><li><strong>Fixtures</strong>: one to three fixed inputs you can compare across runs</li><li><strong>Success criteria</strong>: what better means this round</li><li><strong>The freeze line</strong>: what must not change</li></ol><p>Pin the input first. A moving fixture is noise. For GitHub agents, use <code>agent-sdk github replay</code> (see the <a href="./guides/github.html">GitHub guide</a>). For a single tool without a model turn, use <code>agent-sdk call</code>. For a chat turn, use <code>agent-sdk run --dir . --message "…"</code>.</p><h2 id="how-do-i-run-one-hillclimb-round" tabindex="-1">How do I run one hillclimb round? <a class="header-anchor" href="#how-do-i-run-one-hillclimb-round" aria-label="Permalink to "How do I run one hillclimb round?""></a></h2><p><strong>Measure.</strong> Hit the agent the way a user would: playground, channel HTTP, or Slack in <code>--dev</code>. Or ask the hillclimb skill to do it. <code>agent-sdk run</code> returns a JSON trajectory and writes a trace under <code>.agent-serve/traces/</code>.</p><p><strong>Reflect.</strong> Score the trajectory, not impressions. Was the answer right? Did the model thrash (too many tools, fat evidence, grep loops)? Did it invent work the host should have prepared? Name the single dominant problem for this round in one sentence. Example: "Full-file dumps trigger grep loops."</p><p><strong>Change one lever.</strong> Prefer the smallest change that addresses that problem:</p><ol><li>Host prep: seed what the model needs so it doesn't hunt</li><li>Evidence shape: trim or reorder artifacts</li><li>Instructions and skills: tighten the procedure</li><li>Tool surface: remove or gate tools that invite wandering</li><li>Framework changes: only when the agent can't express the fix</li></ol><p><strong>Remeasure.</strong> Same fixtures. Diff tools, wall time, and quality side by side. Keep the change only if the target metric improves and the freeze line holds.</p><h2 id="how-do-i-lock-a-hillclimb-improvement-with-an-eval" tabindex="-1">How do I lock a hillclimb improvement with an eval? <a class="header-anchor" href="#how-do-i-lock-a-hillclimb-improvement-with-an-eval" aria-label="Permalink to "How do I lock a hillclimb improvement with an eval?""></a></h2><p>Every kept change needs an eval that would have failed before the change: a tool-choice gate, an <code>action.result</code> count bound, or an output-shape check. Run <code>agent-sdk eval --dir . --json</code> between rounds. Never weaken an existing gate to pass the round.</p><p>Details live in <a href="./evals.html">Evals</a>. The evals skill will author the case with you.</p><h2 id="what-habits-help-hillclimbing-stay-reliable" tabindex="-1">What habits help hillclimbing stay reliable? <a class="header-anchor" href="#what-habits-help-hillclimbing-stay-reliable" aria-label="Permalink to "What habits help hillclimbing stay reliable?""></a></h2><ul><li>One problem per round. Don't bundle "trim evidence and rewrite instructions" unless you chose that on purpose.</li><li>Keep fixtures fixed until you deliberately need a harder case.</li><li>Separate host work from model tools when you blame latency. Moving deterministic prep onto the host is often the biggest win. In one PR reviewer, host-prepared evidence cut turns from about 8 minutes to about 1 minute.</li><li>Spot-check quality on at least one fixture against a known-good answer. Efficiency-only climbs quietly drop findings.</li><li>Treat <code>turn.failed</code> with <code>"turn interrupted"</code> as expected when a follow-up or stop preempted the turn.</li><li>Don't deploy, post to real surfaces, or weaken evals as part of a climb.</li></ul><h2 id="related" tabindex="-1">Related <a class="header-anchor" href="#related" aria-label="Permalink to "Related""></a></h2><ul><li><a href="./evals.html">Evals</a></li><li><a href="./building-with-agents.html">Building agents with agents</a></li><li><a href="./guides/github.html">GitHub guide</a></li><li><a href="./troubleshooting.html">Fix common agent problems</a></li></ul></div></div></main><footer class="VPDocFooter" data-v-2e506a34 data-v-574f06fa><!--[--><!--]--><!----><nav class="prev-next" aria-labelledby="doc-footer-aria-label" data-v-574f06fa><span class="visually-hidden" id="doc-footer-aria-label" data-v-574f06fa>Pager</span><div class="pager" data-v-574f06fa><a class="VPLink link pager-link prev" href="/docs/storage.html" data-v-574f06fa><!--[--><span class="desc" data-v-574f06fa>Previous page</span><span class="title" data-v-574f06fa>Storage</span><!--]--></a></div><div class="pager" data-v-574f06fa><a class="VPLink link pager-link next" href="/docs/guides/webhooks.html" data-v-574f06fa><!--[--><span class="desc" data-v-574f06fa>Next page</span><span class="title" data-v-574f06fa>Webhooks & custom channels</span><!--]--></a></div></nav></footer><!--[--><!--]--></div></div></div><!--[--><!--]--></div></div><!----><!--[--><!--]--></div></div>
|
|
25
|
-
<script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"CVzWxLoB\",\"building-with-agents.md\":\"DH8A_cHA\",\"concepts.md\":\"CRfU3bVg\",\"deployment.md\":\"DX_hc3ze\",\"evals.md\":\"a0SMN6r9\",\"example-agents_approval-buddy.md\":\"DNL83puR\",\"example-agents_benny.md\":\"C40vHRLc\",\"example-agents_bugbot.md\":\"BRGMi9O2\",\"example-agents_codebase-wiki.md\":\"Dftj_tPp\",\"example-agents_codeowners-review.md\":\"Bfta-lBU\",\"example-agents_concierge.md\":\"MrKpQndp\",\"example-agents_fsd.md\":\"ZWHWWZPE\",\"example-agents_index.md\":\"QZ8mhr6n\",\"example-agents_knowledge-base.md\":\"DqKqHQ9u\",\"example-agents_oncall.md\":\"DK4XkYTd\",\"example-agents_security-reviewer.md\":\"Bai6D0Ee\",\"example-agents_slack-agent.md\":\"D7Kdj5BV\",\"example-agents_weather-agent.md\":\"lVEAbWFf\",\"guides_agent-to-agent.md\":\"BCeVdJRJ\",\"guides_cloud-runtime.md\":\"BSMLIBHr\",\"guides_convert-automation.md\":\"D06eIzea\",\"guides_github.md\":\"Cdt1s2QC\",\"guides_human-in-the-loop.md\":\"By1G2T3_\",\"guides_mcp-oauth.md\":\"Du0f7pGU\",\"guides_opentelemetry.md\":\"bmPmkvJu\",\"guides_slack.md\":\"DiUmk_Oi\",\"guides_webhooks.md\":\"BpnIdO0i\",\"hillclimbing.md\":\"ywF3yDAd\",\"index.md\":\"BAaMXLFd\",\"quickstart.md\":\"DsrarzEg\",\"reference_agent-config.md\":\"Bqylgw50\",\"reference_artifacts.md\":\"Dior32Qw\",\"reference_channels.md\":\"DQZjCnyh\",\"reference_cli.md\":\"B7GkAJRC\",\"reference_connections.md\":\"DYidrb-j\",\"reference_hooks.md\":\"B9FSgdDe\",\"reference_http-api.md\":\"CSHVobzG\",\"reference_instructions.md\":\"DhNCOl7r\",\"reference_playground.md\":\"Dfb92yQf\",\"reference_project-layout.md\":\"CwkSbEWT\",\"reference_prompt.md\":\"DZUMtLPD\",\"reference_schedules.md\":\"DNipebiG\",\"reference_sessions.md\":\"tUFzz98S\",\"reference_skills.md\":\"B5ZEuHfG\",\"reference_subagents.md\":\"Xoav0AII\",\"reference_tools.md\":\"wpaJtHn6\",\"scaffolding-agents.md\":\"CRDDUtYJ\",\"storage.md\":\"JbjlHWZ6\",\"templates_agentic-owners.md\":\"DSJSIpWU\",\"templates_demo.md\":\"DhFcWN6j\",\"templates_pr-autofixer.md\":\"1HAR3RXE\",\"templates_security-reviewer.md\":\"ByFyRta2\",\"templates_triage.md\":\"CVlpctKS\",\"troubleshooting.md\":\"DYECCZiJ\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.
|
|
27
|
+
<script>window.__VP_HASH_MAP__=JSON.parse("{\"ab.md\":\"CVzWxLoB\",\"building-with-agents.md\":\"DH8A_cHA\",\"concepts.md\":\"CRfU3bVg\",\"deployment.md\":\"DX_hc3ze\",\"evals.md\":\"a0SMN6r9\",\"example-agents_approval-buddy.md\":\"DNL83puR\",\"example-agents_benny.md\":\"C40vHRLc\",\"example-agents_bugbot.md\":\"BRGMi9O2\",\"example-agents_codebase-wiki.md\":\"Dftj_tPp\",\"example-agents_codeowners-review.md\":\"Bfta-lBU\",\"example-agents_concierge.md\":\"MrKpQndp\",\"example-agents_fsd.md\":\"ZWHWWZPE\",\"example-agents_index.md\":\"QZ8mhr6n\",\"example-agents_knowledge-base.md\":\"DqKqHQ9u\",\"example-agents_oncall.md\":\"DK4XkYTd\",\"example-agents_security-reviewer.md\":\"Bai6D0Ee\",\"example-agents_slack-agent.md\":\"D7Kdj5BV\",\"example-agents_weather-agent.md\":\"lVEAbWFf\",\"guides_agent-to-agent.md\":\"BCeVdJRJ\",\"guides_cloud-runtime.md\":\"BSMLIBHr\",\"guides_convert-automation.md\":\"D06eIzea\",\"guides_github.md\":\"Cdt1s2QC\",\"guides_human-in-the-loop.md\":\"By1G2T3_\",\"guides_mcp-oauth.md\":\"Du0f7pGU\",\"guides_opentelemetry.md\":\"bmPmkvJu\",\"guides_slack.md\":\"DiUmk_Oi\",\"guides_webhooks.md\":\"BpnIdO0i\",\"hillclimbing.md\":\"ywF3yDAd\",\"index.md\":\"BAaMXLFd\",\"quickstart.md\":\"DsrarzEg\",\"reference_agent-config.md\":\"Bqylgw50\",\"reference_artifacts.md\":\"Dior32Qw\",\"reference_channels.md\":\"DQZjCnyh\",\"reference_cli.md\":\"B7GkAJRC\",\"reference_connections.md\":\"DYidrb-j\",\"reference_hooks.md\":\"B9FSgdDe\",\"reference_http-api.md\":\"CSHVobzG\",\"reference_instructions.md\":\"DhNCOl7r\",\"reference_playground.md\":\"Dfb92yQf\",\"reference_project-layout.md\":\"CwkSbEWT\",\"reference_prompt.md\":\"DZUMtLPD\",\"reference_schedules.md\":\"DNipebiG\",\"reference_sessions.md\":\"tUFzz98S\",\"reference_skills.md\":\"B5ZEuHfG\",\"reference_subagents.md\":\"Xoav0AII\",\"reference_tools.md\":\"wpaJtHn6\",\"scaffolding-agents.md\":\"CRDDUtYJ\",\"storage.md\":\"JbjlHWZ6\",\"templates_agentic-owners.md\":\"DSJSIpWU\",\"templates_demo.md\":\"DhFcWN6j\",\"templates_pr-autofixer.md\":\"1HAR3RXE\",\"templates_security-reviewer.md\":\"ByFyRta2\",\"templates_triage.md\":\"CVlpctKS\",\"troubleshooting.md\":\"DYECCZiJ\"}");window.__VP_SITE_DATA__=JSON.parse("{\"lang\":\"en-US\",\"dir\":\"ltr\",\"title\":\"Agent SDK\",\"description\":\"Filesystem-first framework for building and serving Cursor agents.\",\"base\":\"/docs/\",\"head\":[],\"router\":{\"prefetchLinks\":true},\"appearance\":true,\"themeConfig\":{\"sdkVersion\":\"0.1.92\",\"nav\":[{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Guides\",\"link\":\"/guides/webhooks\"},{\"text\":\"Examples\",\"link\":\"/example-agents/\"},{\"text\":\"Reference\",\"link\":\"/reference/project-layout\"}],\"search\":{\"provider\":\"local\"},\"outline\":{\"level\":[2,3]},\"sidebar\":[{\"text\":\"Getting started\",\"items\":[{\"text\":\"Overview\",\"link\":\"/\"},{\"text\":\"Quickstart\",\"link\":\"/quickstart\"},{\"text\":\"Scaffold an agent with Cursor\",\"link\":\"/scaffolding-agents\"},{\"text\":\"Convert a Cursor Automation\",\"link\":\"/guides/convert-automation\"},{\"text\":\"Concepts\",\"link\":\"/concepts\"}]},{\"text\":\"Templates\",\"items\":[{\"text\":\"Demo agent\",\"link\":\"/templates/demo\"},{\"text\":\"Security reviewer\",\"link\":\"/templates/security-reviewer\"},{\"text\":\"Agentic Owners\",\"link\":\"/templates/agentic-owners\"},{\"text\":\"PR autofixer\",\"link\":\"/templates/pr-autofixer\"},{\"text\":\"Triage agent\",\"link\":\"/templates/triage\"}]},{\"text\":\"Improving agents\",\"items\":[{\"text\":\"Building agents with agents\",\"link\":\"/building-with-agents\"},{\"text\":\"Evals\",\"link\":\"/evals\"},{\"text\":\"Live A/B metrics\",\"link\":\"/ab\"},{\"text\":\"Storage\",\"link\":\"/storage\"},{\"text\":\"Hillclimbing\",\"link\":\"/hillclimbing\"}]},{\"text\":\"Guides\",\"items\":[{\"text\":\"Webhooks & custom channels\",\"link\":\"/guides/webhooks\"},{\"text\":\"GitHub\",\"link\":\"/guides/github\"},{\"text\":\"Slack\",\"link\":\"/guides/slack\"},{\"text\":\"Human-in-the-loop approvals\",\"link\":\"/guides/human-in-the-loop\"},{\"text\":\"Agent-to-agent\",\"link\":\"/guides/agent-to-agent\"},{\"text\":\"Host MCP OAuth\",\"link\":\"/guides/mcp-oauth\"},{\"text\":\"Cloud runtime\",\"link\":\"/guides/cloud-runtime\"},{\"text\":\"OpenTelemetry\",\"link\":\"/guides/opentelemetry\"}]},{\"text\":\"Example agents\",\"items\":[{\"text\":\"Choose an example\",\"link\":\"/example-agents/\"},{\"text\":\"Weather agent\",\"link\":\"/example-agents/weather-agent\"},{\"text\":\"Slack agent\",\"link\":\"/example-agents/slack-agent\"},{\"text\":\"Concierge\",\"link\":\"/example-agents/concierge\"},{\"text\":\"Playbook router\",\"link\":\"/example-agents/benny\"},{\"text\":\"Alert investigator\",\"link\":\"/example-agents/oncall\"},{\"text\":\"PR evidence reviewer\",\"link\":\"/example-agents/bugbot\"},{\"text\":\"Approval Buddy\",\"link\":\"/example-agents/approval-buddy\"},{\"text\":\"Security Reviewer\",\"link\":\"/example-agents/security-reviewer\"},{\"text\":\"Remote PR coordinator\",\"link\":\"/example-agents/fsd\"},{\"text\":\"Knowledge base\",\"link\":\"/example-agents/knowledge-base\"},{\"text\":\"Codebase wiki\",\"link\":\"/example-agents/codebase-wiki\"},{\"text\":\"Codeowners review\",\"link\":\"/example-agents/codeowners-review\"}]},{\"text\":\"Operating\",\"items\":[{\"text\":\"Deployment\",\"link\":\"/deployment\"},{\"text\":\"Fix common problems\",\"link\":\"/troubleshooting\"}]},{\"text\":\"Reference\",\"collapsed\":false,\"items\":[{\"text\":\"Project layout\",\"link\":\"/reference/project-layout\"},{\"text\":\"Agent config\",\"link\":\"/reference/agent-config\"},{\"text\":\"Instructions\",\"link\":\"/reference/instructions\"},{\"text\":\"Tools\",\"link\":\"/reference/tools\"},{\"text\":\"prompt\",\"link\":\"/reference/prompt\"},{\"text\":\"Skills\",\"link\":\"/reference/skills\"},{\"text\":\"MCP Connections\",\"link\":\"/reference/connections\"},{\"text\":\"Subagents\",\"link\":\"/reference/subagents\"},{\"text\":\"Channels\",\"link\":\"/reference/channels\"},{\"text\":\"Schedules & reminders\",\"link\":\"/reference/schedules\"},{\"text\":\"Hooks\",\"link\":\"/reference/hooks\"},{\"text\":\"Artifacts\",\"link\":\"/reference/artifacts\"},{\"text\":\"Sessions & streaming\",\"link\":\"/reference/sessions\"},{\"text\":\"Playground\",\"link\":\"/reference/playground\"},{\"text\":\"CLI\",\"link\":\"/reference/cli\"},{\"text\":\"HTTP API\",\"link\":\"/reference/http-api\"}]}]},\"locales\":{},\"scrollOffset\":134,\"cleanUrls\":false}");</script>
|
|
26
28
|
|
|
27
29
|
</body>
|
|
28
30
|
</html>
|
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
# Hillclimbing
|
|
2
|
+
|
|
3
|
+
Make an agent better on fixed inputs: measure, change one lever, remeasure, and lock every kept win with an eval.
|
|
4
|
+
|
|
5
|
+
## What is hillclimbing?
|
|
6
|
+
|
|
7
|
+
Hillclimbing is a measured improvement loop. You pin a few fixtures, name the one dominant problem in the run, change one lever, and check the same fixtures again. Keep only what helps. Every kept change lands an [eval](/docs/evals.md) so the win stays put.
|
|
8
|
+
|
|
9
|
+
You don't have to run the loop alone. The package ships a coding-agent skill that drives it with you.
|
|
10
|
+
|
|
11
|
+
```mermaid
|
|
12
|
+
flowchart LR
|
|
13
|
+
measure[Measure] --> change[Change one lever]
|
|
14
|
+
change --> remeasure[Remeasure]
|
|
15
|
+
remeasure --> measure
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## How do I hillclimb an agent with a coding agent?
|
|
19
|
+
|
|
20
|
+
Have Cursor read [`skills/hillclimb/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/hillclimb/SKILL.md).
|
|
21
|
+
|
|
22
|
+
Tell it:
|
|
23
|
+
|
|
24
|
+
1. **Which agent** you're improving (path or slug)
|
|
25
|
+
2. **One to three fixtures** you'll reuse every round: a PR URL, a saved webhook body, or a canonical chat prompt
|
|
26
|
+
3. **What "better" means** this round: correct tool choice, fewer tools, lower latency, or output quality. Name the freeze line too: API shape, public output, and existing evals that must stay green
|
|
27
|
+
|
|
28
|
+
The skill serves the agent, hits your fixtures, reads the session trajectory, proposes one change, remeasures, and checks with you before the next round.
|
|
29
|
+
|
|
30
|
+
Other skills cover the edges:
|
|
31
|
+
|
|
32
|
+
| When you need… | Skill |
|
|
33
|
+
| --- | --- |
|
|
34
|
+
| The measured improvement loop | [`skills/hillclimb/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/hillclimb/SKILL.md) |
|
|
35
|
+
| An eval that locks a kept win | [`skills/evals/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/evals/SKILL.md) |
|
|
36
|
+
| Repeatable GitHub webhook inputs | [`skills/github/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/github/SKILL.md) |
|
|
37
|
+
| A run that misbehaves | [`skills/debug/SKILL.md`](https://github.com/cursor/cursor/blob/main/packages/agent-serve/skills/debug/SKILL.md) |
|
|
38
|
+
|
|
39
|
+
See [Building agents with agents](/docs/building-with-agents.md) for every framework skill and a good first prompt.
|
|
40
|
+
|
|
41
|
+
## What do I need before a hillclimb round?
|
|
42
|
+
|
|
43
|
+
Agree on four things before you edit:
|
|
44
|
+
|
|
45
|
+
1. **The target agent**: the project you're improving
|
|
46
|
+
2. **Fixtures**: one to three fixed inputs you can compare across runs
|
|
47
|
+
3. **Success criteria**: what better means this round
|
|
48
|
+
4. **The freeze line**: what must not change
|
|
49
|
+
|
|
50
|
+
Pin the input first. A moving fixture is noise. For GitHub agents, use `agent-sdk github replay` (see the [GitHub guide](/docs/guides/github.md)). For a single tool without a model turn, use `agent-sdk call`. For a chat turn, use `agent-sdk run --dir . --message "…"`.
|
|
51
|
+
|
|
52
|
+
## How do I run one hillclimb round?
|
|
53
|
+
|
|
54
|
+
**Measure.** Hit the agent the way a user would: playground, channel HTTP, or Slack in `--dev`. Or ask the hillclimb skill to do it. `agent-sdk run` returns a JSON trajectory and writes a trace under `.agent-serve/traces/`.
|
|
55
|
+
|
|
56
|
+
**Reflect.** Score the trajectory, not impressions. Was the answer right? Did the model thrash (too many tools, fat evidence, grep loops)? Did it invent work the host should have prepared? Name the single dominant problem for this round in one sentence. Example: "Full-file dumps trigger grep loops."
|
|
57
|
+
|
|
58
|
+
**Change one lever.** Prefer the smallest change that addresses that problem:
|
|
59
|
+
|
|
60
|
+
1. Host prep: seed what the model needs so it doesn't hunt
|
|
61
|
+
2. Evidence shape: trim or reorder artifacts
|
|
62
|
+
3. Instructions and skills: tighten the procedure
|
|
63
|
+
4. Tool surface: remove or gate tools that invite wandering
|
|
64
|
+
5. Framework changes: only when the agent can't express the fix
|
|
65
|
+
|
|
66
|
+
**Remeasure.** Same fixtures. Diff tools, wall time, and quality side by side. Keep the change only if the target metric improves and the freeze line holds.
|
|
67
|
+
|
|
68
|
+
## How do I lock a hillclimb improvement with an eval?
|
|
69
|
+
|
|
70
|
+
Every kept change needs an eval that would have failed before the change: a tool-choice gate, an `action.result` count bound, or an output-shape check. Run `agent-sdk eval --dir . --json` between rounds. Never weaken an existing gate to pass the round.
|
|
71
|
+
|
|
72
|
+
Details live in [Evals](/docs/evals.md). The evals skill will author the case with you.
|
|
73
|
+
|
|
74
|
+
## What habits help hillclimbing stay reliable?
|
|
75
|
+
|
|
76
|
+
- One problem per round. Don't bundle "trim evidence and rewrite instructions" unless you chose that on purpose.
|
|
77
|
+
- Keep fixtures fixed until you deliberately need a harder case.
|
|
78
|
+
- Separate host work from model tools when you blame latency. Moving deterministic prep onto the host is often the biggest win. In one PR reviewer, host-prepared evidence cut turns from about 8 minutes to about 1 minute.
|
|
79
|
+
- Spot-check quality on at least one fixture against a known-good answer. Efficiency-only climbs quietly drop findings.
|
|
80
|
+
- Treat `turn.failed` with `"turn interrupted"` as expected when a follow-up or stop preempted the turn.
|
|
81
|
+
- Don't deploy, post to real surfaces, or weaken evals as part of a climb.
|
|
82
|
+
|
|
83
|
+
## Related
|
|
84
|
+
|
|
85
|
+
- [Evals](/docs/evals.md)
|
|
86
|
+
- [Building agents with agents](/docs/building-with-agents.md)
|
|
87
|
+
- [GitHub guide](/docs/guides/github.md)
|
|
88
|
+
- [Fix common agent problems](/docs/troubleshooting.md)
|