@agent-native/core 0.122.4 → 0.123.1

package/docs/content/template-brain-sources.mdx

@@ -0,0 +1,163 @@
+---
+title: "Brain: Connecting & Reviewing Sources"
+description: "How to connect Slack, Granola, GitHub, Clips, and webhook sources to Brain, roll out safely, and check whether a source is healthy."
+---
+
+# Brain: Connecting & Reviewing Sources
+
+This page is for whoever sets up Brain's data feeds: what a source is, how to add one safely, and how to tell whether it's actually working. It's written for the person connecting Brain to real company data, whether or not they write code.
+
+<Diagram id="doc-block-brain2" title="From source to cited knowledge, with Ops watching the pipeline" summary="Every source feeds raw captures through distillation and review before becoming knowledge. Ops tracks the health of every step without exposing raw content.">
+
+```html
+<div class="diagram-flow">
+  <div class="diagram-card">
+    <span class="diagram-pill">Sources</span
+    ><small class="diagram-muted"
+      >Slack · Granola · GitHub · Clips · webhooks</small
+    >
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-box" data-rough>
+    Raw captures<br /><small class="diagram-muted">deduped, redacted</small>
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-box" data-rough>
+    Distill<br /><small class="diagram-muted"
+      >facts · decisions · processes</small
+    >
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-card">
+    <span class="diagram-pill warn">Review</span
+    ><small class="diagram-muted">sensitive / low-confidence queue</small>
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-box" data-rough>
+    <span class="diagram-pill ok">Knowledge</span
+    ><small class="diagram-muted">approved, atomic</small>
+  </div>
+</div>
+<div class="diagram-flow diagram-ops-row">
+  <div class="diagram-box" data-rough>
+    <span class="diagram-pill accent">Ops</span
+    ><small class="diagram-muted"
+      >source health · sync freshness · queue retries</small
+    >
+  </div>
+  <div class="diagram-muted diagram-ops-note">
+    watches every source and every queued distillation job — reachable from the
+    Cmd+K command menu, not the sidebar
+  </div>
+</div>
+```
+
+```css
+.diagram-flow {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+  flex-wrap: wrap;
+}
+.diagram-flow .diagram-card {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+  padding: 10px 12px;
+}
+.diagram-flow .diagram-box {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+}
+.diagram-flow .diagram-arrow {
+  font-size: 20px;
+  line-height: 1;
+}
+.diagram-ops-row {
+  margin-top: 10px;
+  padding-top: 10px;
+  border-top: 1px dashed var(--wf-line, #ccc);
+}
+.diagram-ops-note {
+  font-size: 13px;
+}
+```
+
+</Diagram>
+
+## Adding a source
+
+Brain accepts exactly six source providers — there's no arbitrary "custom" provider:
+
+- **Slack** — an allow-listed set of channel IDs. DMs and MPIMs are always rejected.
+- **Granola** — a Team-space feed, polled on an interval you set. Enterprise API keys expose Team-space notes only, never private notes or folders.
+- **GitHub** — an allow-listed set of repositories, importing issue and pull-request context.
+- **Clips** — recordings exported from the Clips template over a signed webhook.
+- **Generic webhook** — any other source (call transcripts, customer research, imported notes) that can push a bounded capture to a signed endpoint.
+- **Manual** — captures you or the agent import directly, with no connector at all.
+
+Sources are org-shared by default so the company memory they produce is useful to the whole workspace. If a shared provider connection already exists elsewhere in the workspace (for example Dispatch already connected Slack), reuse it instead of pasting the same token into Brain — the Sources page shows each provider's connection readiness (connected, granted, needs a grant, or not connected) alongside the source list.
+
+## The Slack safe rollout
+
+Slack is the source most worth rolling out carefully, and Brain's Sources page builds the caution in as a four-step flow on each Slack source card:
+
+1. **Test** — validates the Slack bot token and checks the configured channel allow-list without reading any message history.
+2. **Safe pilot** — imports a tiny, capped sample (two validated channels, one page each, ten messages per page) so you can see what Brain would ingest before committing to a real sync.
+3. **Review captures** — opens the imported capture inventory. Raw message bodies stay hidden by default; enable a preview only when a reviewer needs the context.
+4. **Review queue** — sends reviewers to approve or reject the proposals a pilot or sync produced, before anything becomes queryable company knowledge.
+
+Keep background auto-sync off until the channel allow-list, review quality, and first distilled entries look right. Private channels require manually inviting the Slack app before Brain can validate or sync them — discovery is never treated as consent to read a private channel.
+
+## Checking source health on Ops {#ops}
+
+Brain has a dedicated operations view at `/ops` for exactly one question: is anything broken, and where? It's not in the left sidebar — open it from the Cmd+K command menu (search "Ops") or navigate to `/ops` directly. It shows:
+
+- **Distillation queue state** — queued, processing, done, failed, and stale counts, with a one-click retry for anything stuck or failed.
+- **Semantic index health** (admin-only signal) — index coverage, embedding lag, ACL freshness, and suppressed-record counts, so an admin can tell whether the search index has fallen behind without seeing any protected content.
+
+Each source also gets one deterministic health value, visible on the Sources page and summarized by Ops:
+
+| Health        | Meaning                                                                                 |
+| ------------- | --------------------------------------------------------------------------------------- |
+| `error`       | The source's status is `error`, it has a recorded error, or its latest sync run failed. |
+| `paused`      | The source is paused or archived.                                                       |
+| `needs_setup` | A Slack source with no configured channel allow-list yet.                               |
+| `needs_sync`  | An auto-sync-eligible source (Slack/Granola/GitHub) that has never completed a sync.    |
+| `stale`       | Past its next scheduled sync by more than a 15-minute grace window.                     |
+| `healthy`     | None of the above.                                                                      |
+
+Before telling someone "your source is broken" or "nothing has synced yet," check this instead of inspecting each source by hand — it's the same read the agent uses when asked "why isn't X in Brain yet."
+
+## Privacy and gating
+
+Brain is designed for company memory, not personal surveillance:
+
+- Slack sync only reads explicitly configured channels and always rejects DMs/MPIMs.
+- Granola sync reads Team-space notes exposed by Granola's API, never private notes or private folders.
+- Raw captures are redacted from listing/search surfaces by default; reviewers and distillation flows request previews or raw content only when needed.
+- Every allowed capture and derived record is scoped to an audience (org-wide, a private channel's membership, or a meeting's attendee list) so an answer can never surface content its reader isn't part of.
+- Source configs can require review before distilled knowledge becomes durable company memory.
+- Settings control the default publish tier, whether company-tier knowledge requires approval, citation requirements, email redaction, and connector error notifications.
+
+## Reusing an existing workspace integration
+
+Source credentials resolve in a fixed order: a workspace connection already granted to Brain first, then legacy Brain-local credentials, then a registered vault secret — never a raw `.env` value. The Sources page shows each provider's readiness so you don't have to guess:
+
+| State           | Meaning                                                                                 |
+| --------------- | --------------------------------------------------------------------------------------- |
+| `connected`     | An active workspace connection is already granted to Brain.                             |
+| `granted`       | Brain can access the connection, but it isn't currently active.                         |
+| `needs_grant`   | The workspace has a connection for this provider that hasn't been granted to Brain yet. |
+| `not_connected` | Brain is using its own scoped credentials, or there's no connection at all.             |
+
+If a provider shows `needs_grant`, the fix is granting Brain access to the existing connection in Dispatch — not creating a new one or asking for another token.
+
+## What's next
+
+- [**Brain overview**](/docs/template-brain) — what Brain is and when to pick it
+- [**Asking, Citations & Knowledge**](/docs/template-brain-knowledge) — where the knowledge these sources produce shows up
+- [**Talking to the Agent & Cross-App Use**](/docs/template-brain-agent) — prompts for checking source health and running a pilot from chat
+- [**Developer Guide**](/docs/template-brain-developers) — the full source-management action list and credential resolution code path
+- [**Messaging**](/docs/messaging) — connecting Slack at the workspace level

package/docs/content/template-brain.mdx

@@ -130,27 +130,23 @@ authenticated action surface.
 ## What you can do with it
 
 - **Ask cited questions.** Ask is the main product surface: a clean chat over
-  reviewed company memory, with source health, review count, and suggested
-  questions kept secondary. Every answer links back to the Slack thread,
-  meeting, issue, or capture that supports it.
-- **Connect approved sources.** Configure manual, generic webhook, Clips, Slack,
-  Granola, and GitHub sources. Sources are org-shared by default so company
-  memory is useful to the whole workspace.
-- **Review before publishing.** Proposed memories get a first-class Review route
-  where reviewers edit wording, inspect evidence/source links, and approve or
-  reject. High-confidence, non-sensitive entries can publish immediately;
-  company-tier or sensitive entries queue as proposals.
-- **Inspect cited knowledge.** The Knowledge route shows distilled, atomic
-  entries with kind, topic, entities, confidence, exact evidence quotes, and
-  supersede links.
-- **Reuse workspace integrations.** Brain sources can reuse shared workspace
-  connection grants instead of re-entering provider tokens. The Sources page
-  shows Brain source records beside reusable connection grants and provider
-  readiness.
-- **Mirror approved memory as ambient context.** Canonical approved entries can
-  mirror into workspace resources under `context/company-brain/...` so other
-  apps can use them as context. Both flows preview the exact Markdown before the
-  resource is written or removed.
+  reviewed company memory. Every answer links back to the Slack thread,
+  meeting, issue, or capture that supports it, and Brain says so honestly when
+  nothing supports an answer instead of guessing. See
+  [Asking, Citations & Knowledge](/docs/template-brain-knowledge).
+- **Connect approved sources.** Configure manual, generic webhook, Clips,
+  Slack, Granola, and GitHub sources, with a guided safe rollout for Slack.
+  See [Connecting & Reviewing Sources](/docs/template-brain-sources).
+- **Review before publishing.** Sensitive or low-confidence proposals queue for
+  human review before they become knowledge the whole company can be told as
+  fact. See [Asking, Citations & Knowledge](/docs/template-brain-knowledge).
+- **Check source and system health.** An Ops view tracks sync freshness and
+  distillation queue health across every source. See
+  [Connecting & Reviewing Sources](/docs/template-brain-sources).
+- **Answer across the whole workspace.** Brain can hand off a live-data
+  question — a metric, a mailbox, a workspace grant — to the specialist app
+  that owns it, and sibling apps can ask Brain for cited answers over A2A. See
+  [Talking to the Agent & Cross-App Use](/docs/template-brain-agent).
 
 ## Getting started
 
@@ -163,8 +159,8 @@ Live demo: [brain.agent-native.com](https://brain.agent-native.com).
 2. **Add one source.** Start with a single Slack channel, Granola Team-space
    feed, GitHub repository, Clips export, or generic transcript webhook. Keep
    the scope small until citations and review quality look right.
-3. **Review before publishing.** Use Review to inspect evidence, edit wording,
-   and approve only durable company memory.
+3. **Review before publishing.** Inspect evidence, edit wording, and approve
+   only durable company memory.
 4. **Ask from the source.** Use Ask for questions that should be grounded in
    approved knowledge, not raw chat logs.
 
@@ -172,384 +168,28 @@ For a public demo, the seeded corpus demonstrates product-decision recall,
 citation links, supersede behavior, review gating, redaction, personal-content
 exclusion, and honest not-found behavior without connecting a real workspace.
 
-### Useful prompts
-
-- "What did we decide about annual pricing, and where was that discussed?"
-- "Find the most recent onboarding-process change and cite the source."
-- "Summarize what this GitHub discussion means for the launch plan."
-- "Review the pending memory proposals and flag anything too vague to publish."
-- "Which sources are stale or failing sync?"
-
-## For developers
-
-The rest of this doc is for anyone forking the Brain template or extending it.
-
 ### Quick start
 
 ```bash
 npx @agent-native/core@latest create my-brain --standalone --template brain
-cd my-brain
-pnpm install
-pnpm dev
 ```
 
-Open the app and choose **Start demo** to see cited memory without connecting a real workspace.
-
-### Data model
-
-Brain intentionally uses SQL text search and agentic query expansion — there is
-no vector-database requirement, so the template stays portable across SQLite,
-Postgres, Neon, D1, Turso, and similar hosts. Application state mirrors the
-current route, filters, and selected IDs so the agent always knows the current
-navigation and selection.
-
-Brain's schema lives in `templates/brain/server/db/schema.ts`. Nine tables:
-
-| Table                    | What it holds                                                                                                                                  |
-| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------- |
-| `brain_sources`          | Connector config — provider, allow-listed channels/repos, sync cursors, review posture, `ingest_token_hash`, `status`, `last_synced_at`        |
-| `brain_source_shares`    | Per-source share grants (viewer / editor / admin)                                                                                              |
-| `brain_raw_captures`     | Transcripts, channel exports, notes, and webhook imports with `external_id` dedupe key, `content_hash`, kind, and distillation status          |
-| `brain_knowledge`        | Distilled atomic entries — kind (decision / fact / process / …), topic, entities, evidence quotes, confidence, `publish_tier`, supersede links |
-| `brain_knowledge_shares` | Per-knowledge share grants                                                                                                                     |
-| `brain_proposals`        | Pending review items — proposed create/update/archive with evidence and reviewer notes                                                         |
-| `brain_proposal_shares`  | Per-proposal share grants                                                                                                                      |
-| `brain_sync_runs`        | Sync audit log — provider, status, stats JSON, error, start/end timestamps                                                                     |
-| `brain_ingest_queue`     | Background distillation queue — operation, status, priority, retry count, `run_after`                                                          |
-
-<DataModel
-  id="doc-block-qwo0b1"
-  title="Brain data model"
-  summary={
-    "Connectors produce raw captures; distillation turns captures into reviewable knowledge; proposals gate sensitive entries. Sync runs and the ingest queue track background work."
-  }
-  entities={[
-    {
-      id: "sources",
-      name: "brain_sources",
-      note: "Connector config",
-      fields: [
-        {
-          name: "id",
-          type: "id",
-          pk: true,
-        },
-        {
-          name: "provider",
-          type: "text",
-          note: "slack / granola / github / clips / webhook",
-        },
-        {
-          name: "ingest_token_hash",
-          type: "text",
-        },
-        {
-          name: "status",
-          type: "text",
-        },
-        {
-          name: "last_synced_at",
-          type: "timestamp",
-          nullable: true,
-        },
-      ],
-    },
-    {
-      id: "source_shares",
-      name: "brain_source_shares",
-      note: "viewer / editor / admin",
-      fields: [
-        {
-          name: "source_id",
-          type: "id",
-          fk: "brain_sources.id",
-        },
-      ],
-    },
-    {
-      id: "captures",
-      name: "brain_raw_captures",
-      note: "Ingested raw payloads",
-      fields: [
-        {
-          name: "id",
-          type: "id",
-          pk: true,
-        },
-        {
-          name: "source_id",
-          type: "id",
-          fk: "brain_sources.id",
-        },
-        {
-          name: "external_id",
-          type: "text",
-          note: "dedupe key",
-        },
-        {
-          name: "content_hash",
-          type: "text",
-        },
-        {
-          name: "kind",
-          type: "text",
-        },
-      ],
-    },
-    {
-      id: "knowledge",
-      name: "brain_knowledge",
-      note: "Distilled atomic entries",
-      fields: [
-        {
-          name: "id",
-          type: "id",
-          pk: true,
-        },
-        {
-          name: "kind",
-          type: "text",
-          note: "decision / fact / process",
-        },
-        {
-          name: "topic",
-          type: "text",
-        },
-        {
-          name: "entities",
-          type: "json",
-        },
-        {
-          name: "confidence",
-          type: "real",
-        },
-        {
-          name: "publish_tier",
-          type: "text",
-        },
-      ],
-    },
-    {
-      id: "knowledge_shares",
-      name: "brain_knowledge_shares",
-      fields: [
-        {
-          name: "knowledge_id",
-          type: "id",
-          fk: "brain_knowledge.id",
-        },
-      ],
-    },
-    {
-      id: "proposals",
-      name: "brain_proposals",
-      note: "Pending review items",
-      fields: [
-        {
-          name: "id",
-          type: "id",
-          pk: true,
-        },
-        {
-          name: "op",
-          type: "text",
-          note: "create / update / archive",
-        },
-      ],
-    },
-    {
-      id: "proposal_shares",
-      name: "brain_proposal_shares",
-      fields: [
-        {
-          name: "proposal_id",
-          type: "id",
-          fk: "brain_proposals.id",
-        },
-      ],
-    },
-    {
-      id: "sync_runs",
-      name: "brain_sync_runs",
-      note: "Sync audit log",
-      fields: [
-        {
-          name: "source_id",
-          type: "id",
-          fk: "brain_sources.id",
-        },
-        {
-          name: "status",
-          type: "text",
-        },
-        {
-          name: "stats",
-          type: "json",
-        },
-      ],
-    },
-    {
-      id: "ingest_queue",
-      name: "brain_ingest_queue",
-      note: "Background distillation queue",
-      fields: [
-        {
-          name: "operation",
-          type: "text",
-        },
-        {
-          name: "status",
-          type: "text",
-        },
-        {
-          name: "priority",
-          type: "int",
-        },
-        {
-          name: "run_after",
-          type: "timestamp",
-          nullable: true,
-        },
-      ],
-    },
-  ]}
-  relations={[
-    {
-      from: "sources",
-      to: "captures",
-      kind: "1-n",
-      label: "ingested into",
-    },
-    {
-      from: "knowledge",
-      to: "captures",
-      kind: "n-n",
-      label: "evidence",
-    },
-    {
-      from: "knowledge",
-      to: "proposals",
-      kind: "1-n",
-      label: "gated by",
-    },
-    {
-      from: "sources",
-      to: "sync_runs",
-      kind: "1-n",
-      label: "audited by",
-    },
-  ]}
-/>
-
-### Key actions
-
-Grouped by area (`templates/brain/actions/`):
-
-- **Source management** — `create-source`, `update-source`, `delete-source`, `get-source`, `list-sources`, `sync-source`, `sync-due-sources`, `run-slack-pilot`, `test-slack-connection`
-- **Capture ingestion** — `import-capture`, `import-transcript`, `list-captures`, `get-capture`, `mark-capture-distilled`, `resanitize-captures`
-- **Distillation** — `enqueue-distillation`, `enqueue-captures-distillation`, `claim-distillation`, `retry-distillation`, `list-distillation-queue`
-- **Knowledge & review** — `write-knowledge`, `get-knowledge`, `list-knowledge`, `set-knowledge-canonical`, `preview-canonical-resource`, `list-proposals`, `review-proposal`, `approve-proposal`, `reject-proposal`, `update-proposal`
-- **Search & retrieval** — `ask-brain`, `search-knowledge`, `search-everything`
-- **Settings** — `get-brain-settings`, `update-brain-settings`, `set-settings`, `get-settings`
-- **Evaluation & demo** — `seed-demo-data`, `run-demo-eval`, `run-retrieval-eval`
-- **Context & navigation** — `view-screen`, `navigate`
-- **Provider APIs** — `provider-api-catalog`, `provider-api-docs`, `provider-api-request`
-
-### Connecting sources
-
-Brain resolves provider credentials from a granted workspace connection first,
-then from backward-compatible Brain-local or registered vault credentials.
-Brain source credentials do not fall back to deploy-level environment variables.
-If a shared provider already exists, grant Brain access instead of copying the
-same secret into a Brain-specific setting.
-
-**Slack.** Create a source scoped to specific channel IDs. The connector
-verifies each configured conversation, rejects DMs and MPIMs, and stores cursor
-state so each sync resumes where the last one stopped. A safe rollout flow on
-each Slack source card lets you **Test** the credential and allow-list without
-reading history, run a tiny capped **Safe pilot** sample, **Review captures**,
-and approve in the **Review queue** before anything becomes queryable. Grant the
-bot only the scopes the source needs (credential validation, allow-list
-verification, allow-listed channel history, and durable permalinks).
-
-**Granola.** Create a source with a polling window and page size. Granola
-Enterprise API keys expose Team-space notes, not private notes or folders. Brain
-stores the note summary, transcript, attendees, calendar metadata, and source
-URL as a raw capture before distillation.
-
-**GitHub.** Create a source scoped to approved repositories. The connector
-imports bounded issue and pull-request context with stable source URLs that can
-be distilled like Slack or meeting context. This is Brain context ingestion, not
-a replacement for Analytics-style GitHub reporting.
-
-**Clips and generic webhooks.** Brain exposes a signed webhook for Clips and
-generic transcript/capture imports at `/api/_agent-native/brain/ingest`. Create
-a source with a `sourceKey` to receive a bearer token, then send a
-`RawCapturePayload` with `Authorization: Bearer <ingestToken>`. Generic sources
-use the same payload shape for call transcripts, customer research, imported
-notes, or any other source that can produce a bounded capture.
-
-<Endpoint id="doc-block-1udptrp" title="Signed ingest webhook" summary="Clips and generic transcript/capture imports post a RawCapturePayload with a per-source bearer token." method="POST" path="/api/_agent-native/brain/ingest" summary="Import a raw capture from Clips or a generic source" auth={"Bearer <ingestToken> issued per source via its sourceKey"} request={{
-  "contentType": "application/json",
-  "example": "RawCapturePayload — bounded transcript / capture body"
-}} responses={[
-  {
-    "status": "200",
-    "description": "Capture accepted and queued for distillation"
-  },
-  {
-    "status": "401",
-    "description": "Missing or invalid ingest bearer token"
-  }
-]}>
-
-</Endpoint>
-
-Slack, Granola, and GitHub sources can opt into background `autoSync` with a
-poll cadence once review quality is proven.
-
-### Privacy and gating
-
-Brain is designed for company memory, not personal surveillance:
-
-- Slack sync only reads explicitly configured channels and rejects DMs/MPIMs.
-- Granola sync reads Team-space notes exposed by Granola's API, not private
-  notes or private folders.
-- Raw captures are redacted from listing/search surfaces by default; reviewers
-  and distillation flows request previews or raw content only when needed.
-- Source configs can require review before distilled knowledge becomes durable
-  company memory.
-- Settings control default publish tier, whether company-tier knowledge requires
-  approval, citation requirements, email redaction, and connector error
-  notifications.
-
-### Customizing it
-
-Brain follows the agent-native four-area contract — change behavior by editing
-the matching area, and the agent can make these edits for you:
-
-- `templates/brain/app/routes/` — the UI surface: Ask, Search, Knowledge,
-  Review, Sources, Settings, and Team routes.
-- `templates/brain/actions/` — every agent-callable operation (imports, source
-  management, pilot reports, distillation, proposal review, cited search,
-  navigation/context). Add a new file with `defineAction` to expose a new
-  capability.
-- `templates/brain/.agents/skills/` — Brain-specific guidance for distillation
-  and retrieval. Update or add a skill when you teach the agent a new workflow.
-- `templates/brain/AGENTS.md` — top-level agent guide. Update when you add major
-  features.
-- `templates/brain/server/db/schema.ts` — data model. Additive migrations only;
-  route, filters, and selected IDs mirror into `application_state` for agent
-  context.
-
-Ask the agent to make changes for you — it can edit its own source. See
-[Self-Modifying Code](/docs/key-concepts#agent-modifies-code).
+See [Getting Started](/docs/getting-started) for running it locally, and the
+[Developer Guide](/docs/template-brain-developers) for the data model and full
+action reference.
 
 ## What's next
 
+- [**Connecting & Reviewing Sources**](/docs/template-brain-sources) — adding
+  a source, the Slack safe rollout, and checking source health
+- [**Asking, Citations & Knowledge**](/docs/template-brain-knowledge) — Ask,
+  Search, browsing Knowledge, and reviewing proposals
+- [**Talking to the Agent & Cross-App Use**](/docs/template-brain-agent) —
+  useful prompts, cross-app answers, and A2A
+- [**Developer Guide**](/docs/template-brain-developers) — data model, the
+  full action reference, and how to customize Brain
 - [**Dispatch**](/docs/dispatch) — the workspace control plane
 - [**Dispatch template**](/docs/template-dispatch) — the scaffolded coordination app
-- [**Agent Resources**](/docs/agent-resources) — shared resources across apps
 - [**A2A Protocol**](/docs/a2a-protocol) — cross-app delegation
 - [**Templates**](/docs/cloneable-saas) — the clone-and-own model, and every other domain template to start from
 - [**Getting Started**](/docs/getting-started) — the framework fundamentals: actions, application state, and live sync