ai-engineering-loop 2.13.0 → 2.14.1
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/skills/ael/SKILL.md +1 -17
- package/.agents/skills/ael/references/loop-deliver.md +20 -0
- package/.agents/skills/ael/references/loop-goal.md +3 -2
- package/.agents/skills/ael/references/loop-judge.md +9 -0
- package/.agents/skills/ael/references/loop-maker.md +1 -2
- package/.agents/skills/ael/references/loop-modes.md +6 -0
- package/.agents/skills/ael/references/loop-review.md +2 -6
- package/CHANGELOG.md +16 -0
- package/agents/instruction-only/AGENTS.md +1 -1
- package/bin/ai-engineering-loop.js +19 -3
- package/core/goal-contract.md +18 -0
- package/lib/ste.js +69 -0
- package/lib/sync-hosts.js +2 -0
- package/lib/verification-lanes.js +1 -2
- package/package.json +1 -1
- package/README.npm.md +0 -104
- package/docs/images/ael-hero.svg +0 -19
- package/docs/images/engineering-loop-overview.svg +0 -114
- package/docs/images/social-preview.png +0 -0
- package/docs/images/studio-hero-orange.svg +0 -136
- package/docs/images/studio-hero.svg +0 -136
|
@@ -43,20 +43,4 @@ Invariants (every tier):
|
|
|
43
43
|
|
|
44
44
|
## Report header
|
|
45
45
|
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
```
|
|
49
|
-
Execution Mode: TRUE_INDEPENDENT_AGENT
|
|
50
|
-
Independent LLM Execution: PROVEN
|
|
51
|
-
Native Subagent Invocation: AVAILABLE
|
|
52
|
-
Review Method: True Independent Agent
|
|
53
|
-
```
|
|
54
|
-
|
|
55
|
-
When no subagent ran (tool AVAILABLE: mode adds `(reason: <why>)`):
|
|
56
|
-
|
|
57
|
-
```
|
|
58
|
-
Execution Mode: CONTEXT_ISOLATION_ONLY
|
|
59
|
-
Independent LLM Execution: NOT PROVEN
|
|
60
|
-
Native Subagent Invocation: UNAVAILABLE
|
|
61
|
-
Review Method: Clean-Slate Artifact Isolation Barrier
|
|
62
|
-
```
|
|
46
|
+
The final report starts with the execution-mode block in `loop-deliver` (TRUE_INDEPENDENT_AGENT or CONTEXT_ISOLATION_ONLY); never claim independent execution without a subagent result. Tool AVAILABLE but unused: add `(reason: <why>)`.
|
|
@@ -9,3 +9,23 @@
|
|
|
9
9
|
- Commit before `deliver` (its receipt binds `HEAD`; videos/screenshots: `--evidence AC-N=<https-url>`, required for `crossComponent` and rubric ACs). Paste `RUN_DIR/receipt.md` into the PR/MR Receipt section unchanged; ❌ stays ❌ (`docs pr-receipt`).
|
|
10
10
|
- Only the delivery gate completes the run. It also mines lessons for the next Run.
|
|
11
11
|
- Worktree Run: after `deliver`, continue in `cleanup.mainCheckout` (Stage 9).
|
|
12
|
+
|
|
13
|
+
## Report header (execution mode)
|
|
14
|
+
|
|
15
|
+
When a subagent returned its own result (Grok: its own `subagent_id`):
|
|
16
|
+
|
|
17
|
+
```
|
|
18
|
+
Execution Mode: TRUE_INDEPENDENT_AGENT
|
|
19
|
+
Independent LLM Execution: PROVEN
|
|
20
|
+
Native Subagent Invocation: AVAILABLE
|
|
21
|
+
Review Method: True Independent Agent
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
When no subagent ran (tool AVAILABLE: mode adds `(reason: <why>)`):
|
|
25
|
+
|
|
26
|
+
```
|
|
27
|
+
Execution Mode: CONTEXT_ISOLATION_ONLY
|
|
28
|
+
Independent LLM Execution: NOT PROVEN
|
|
29
|
+
Native Subagent Invocation: UNAVAILABLE
|
|
30
|
+
Review Method: Clean-Slate Artifact Isolation Barrier
|
|
31
|
+
```
|
|
@@ -7,9 +7,10 @@
|
|
|
7
7
|
- AC is a failure table: each row has a statement, required evidence, and failure cases. Do not freeze sunny-path-only. T0 may use 1-3 rows that still list failure cases.
|
|
8
8
|
- Boundary-crossing AC (UI-API, service-DB, queue, IPC): `crossComponent: true`; needs L3.
|
|
9
9
|
- Optional per AC: `verify.command` (Judge PASS needs it green), `rubric` for subjective ACs; Goal `featureId` links `features.json`; Goal `flow` (from/event/to) for UI work: show its table with the draft (`docs goal-contract`).
|
|
10
|
-
- Write the contract JSON to `.ai-engineering-loop/drafts/goal.json`, then `npx ai-engineering-loop goal draft --run <runId> --file <file> --revision <currentRevision>` (publishes the draft and the freeze question to Studio). Show the human
|
|
10
|
+
- Write the contract JSON to `.ai-engineering-loop/drafts/goal.json`, then `npx ai-engineering-loop goal draft --json --run <runId> --file <file> --revision <currentRevision>` (publishes the draft and the freeze question to Studio). Show the human `goal show --run <runId> --human` (plain Markdown) and the `impactPreview` in one message.
|
|
11
|
+
- Write `objective`, AC `statement` and `failureCases` in STE style (`docs goal-contract`, STE): one fact or action per sentence, active voice, at most 20-25 words, words a test can check. Fix `readability` warnings from `goal draft` before asking for the freeze.
|
|
11
12
|
- If `goal draft` returns `diagramOptions`, offer the recommended view or freeze; render only the pick (`goal diagram --view <v>`), then ask: freeze, another view, or add AC for `?`/side effects.
|
|
12
|
-
- Wait for the explicit human freeze, then `npx ai-engineering-loop goal freeze --latest --run <runId> --by <name>` (or `--revision <r> --hash <h>`). Add `--confirm-impact` when that answer also accepts the blast radius. T0: `quick start`.
|
|
13
|
+
- Wait for the explicit human freeze, then `npx ai-engineering-loop goal freeze --json --latest --run <runId> --by <name>` (or `--revision <r> --hash <h>`). Add `--confirm-impact` when that answer also accepts the blast radius. T0: `quick start`.
|
|
13
14
|
- Otherwise the freeze writes a DRAFT blast-radius map: `impact show --run <runId>`. ASSISTED: the human confirms or edits it (`impact confirm --by <name> [--allow <glob>] [--remove <path>]`); copy/CSS/comment-only goals: `impact skip --by <name> --reason <text>` (`docs blast-radius-map`).
|
|
14
15
|
- Do not edit production code until the Goal gate passes.
|
|
15
16
|
- After the freeze, work from the frozen contract (`goal show --run <runId>`), not the drafting chat; compact the conversation there if the host supports it.
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
# Stage 7: Judge and ITERATE
|
|
2
|
+
|
|
3
|
+
Read when `gate review` says `judgeRequired`, on T2, or when acting on findings.
|
|
4
|
+
|
|
5
|
+
- Otherwise run `npx ai-engineering-loop escalation --json` and resolve the required tier through the host model catalog; if unavailable, escalate to the user. T2 needs STRONG_MODEL.
|
|
6
|
+
- Judge context: only run-summary.md, verification-summary.json (or verification.json), open-findings.json/findings.json, and the Goal hash; it reads the full diff only if those contradict each other. Judge prompt includes "at most 4 tool calls; ledger and contract only; skip css; do not re-review the whole diff".
|
|
7
|
+
- Spawn a fresh sibling Judge, wait, `budget record`, write `RUN_DIR/verdict.json` with `modelTier` and any `judgeFindings`, then `gate judge`. A gate failure overrides optimistic prose.
|
|
8
|
+
- Acting on findings (ITERATE or human MR comments): verify each one before changing code; fix valid ones test-first, decline invalid ones with evidence (skill `ael-receiving-code-review` if installed).
|
|
9
|
+
- ITERATE under the recipe cap: fix in the parent, re-verify, spawn a **new** DA (never resume the previous child). At the cap or NO_PROGRESS, ESCALATE to the human.
|
|
@@ -1,8 +1,7 @@
|
|
|
1
1
|
# Stages 2-4: Maker
|
|
2
2
|
|
|
3
3
|
- T1/T2: read `docs tdd-policy` before Maker. Use `npx ai-engineering-loop context query <term>` and `context related <file>` before opening broad source files.
|
|
4
|
-
-
|
|
5
|
-
- Maker intern: read `maker_intern` from workflow.md (missing or `none` = parent is Maker). Confirm it through the host model catalog; otherwise the parent is Maker and you report INVOCATION_UNAVAILABLE. The intern cannot skip later gates or spawn DA/Judge.
|
|
4
|
+
- ASSISTED (default): the parent (or intern) is Maker; delivery needs human approval. REPORT_ONLY, UNATTENDED, `maker_intern`: `loop-modes`.
|
|
6
5
|
- Guardrails: Claude Code enforces them after `hooks install`. Elsewhere, before an out-of-scope edit or a destructive command (`rm -rf`, `DROP TABLE`, `git push --force`, `git reset --hard`, `git clean -fd`) run `guard check --tool edit --path <file>` or `--tool bash --command "<cmd>"`: `warn` = ask the human, `block` = do not run it.
|
|
7
6
|
- No code comments in product code (C-26): put intent in names, types, tests; rationale in the commit.
|
|
8
7
|
- Bugs: red repro first. Features: one red test per AC row, then green.
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
# Run modes and the Maker intern
|
|
2
|
+
|
|
3
|
+
Read when the Run is REPORT_ONLY or UNATTENDED, or `workflow.md` names a `maker_intern`.
|
|
4
|
+
|
|
5
|
+
- Branch on mode. REPORT_ONLY: never edit repository files; write `RUN_DIR/report.json` with summary and recommendations, then the report review (`loop-report`), run `gate report`, and stop. ASSISTED: the parent (or intern) is Maker; delivery later needs human approval. UNATTENDED: `sandbox create --run <runId>`, Maker works only in the returned worktreePath, never the parent checkout, then `sandbox capture --run <runId>`.
|
|
6
|
+
- Maker intern: read `maker_intern` from workflow.md (missing or `none` = parent is Maker). Confirm it through the host model catalog; otherwise the parent is Maker and you report INVOCATION_UNAVAILABLE. The intern cannot skip later gates or spawn DA/Judge.
|
|
@@ -10,10 +10,6 @@ REPORT_ONLY runs skip these stages; their single report review is in `loop-maker
|
|
|
10
10
|
- Iteration 2+: give unresolved findings and new hunks, not the whole diff again.
|
|
11
11
|
- Wait, `budget record` its usage (or `--unavailable`), save its output to a file, then `review ingest --run <runId> --child-id <id> --file <output> --json` (binds the ledger, runs `gate review`, and `gate judge` when not required). Never drop a finding; dismiss or downgrade only with `dismissal: {by, evidence}`. Report Spec and Standards separately.
|
|
12
12
|
|
|
13
|
-
## Judge
|
|
13
|
+
## Judge and iterate
|
|
14
14
|
|
|
15
|
-
-
|
|
16
|
-
- Judge context: only run-summary.md, verification-summary.json (or verification.json), open-findings.json/findings.json, and the Goal hash; it reads the full diff only if those contradict each other. Judge prompt includes "at most 4 tool calls; ledger and contract only; skip css; do not re-review the whole diff".
|
|
17
|
-
- Spawn a fresh sibling Judge, wait, `budget record`, write `RUN_DIR/verdict.json` with `modelTier` and any `judgeFindings`, then `gate judge`. A gate failure overrides optimistic prose.
|
|
18
|
-
- Acting on findings (ITERATE or human MR comments): verify each one before changing code; fix valid ones test-first, decline invalid ones with evidence (skill `ael-receiving-code-review` if installed).
|
|
19
|
-
- ITERATE under the recipe cap: fix in the parent, re-verify, spawn a **new** DA (never resume the previous child). At the cap or NO_PROGRESS, ESCALATE to the human.
|
|
15
|
+
- Judge only when `gate review` says `judgeRequired` or T2, or on ITERATE: `loop-judge`.
|
package/CHANGELOG.md
CHANGED
|
@@ -6,6 +6,22 @@ All notable changes to this project are documented here. Versions follow [Semant
|
|
|
6
6
|
|
|
7
7
|
_No changes yet._
|
|
8
8
|
|
|
9
|
+
## 2.14.1 - 2026-11-21
|
|
10
|
+
|
|
11
|
+
Repo cleanup.
|
|
12
|
+
|
|
13
|
+
- **Changed:** repo cleanup (`docs/audit/repo-cleanup-2026-11-21.md`). Finished cards, board history, old designs, the issue #110 cut and QA pack, and old feasibility docs moved to `docs/archive/`; unused images, `README.npm.md`, `templates/repo-config/` and `examples/` removed; `social-preview.png` moved out of the package to `docs/brand/`. The package is 87 KB smaller.
|
|
14
|
+
- **Changed:** `scripts/init.sh` is deprecated: it now runs `npx ai-engineering-loop init` and will be removed in the next release.
|
|
15
|
+
- **Changed:** CI runs the release checks (`doctor --package`, `check:skills`, `audit:package`, `measure`); `ael help` lists every command again, including `gate`, `context`, `review` and `outcome`.
|
|
16
|
+
|
|
17
|
+
## 2.14.0 - 2026-11-21
|
|
18
|
+
|
|
19
|
+
Readable Goals for people (ASD-STE100 style) and skill headroom.
|
|
20
|
+
|
|
21
|
+
- **Changed:** `goal draft` and `goal freeze` print the readable Goal (`goal.md`) and the next step by default, everywhere. Agents and scripts pass `--json` for the full JSON (the skill does). Scripts that parsed the old default output must add `--json`.
|
|
22
|
+
- **Added:** a Goal for people. Every `goal draft` writes `RUN_DIR/goal.md` (What changes, Done when with proof and "Fail if" lines, Not in this change, Not confirmed yet), and `goal show --human` prints it. `goal draft` returns `readability` warnings in the style of ASD-STE100 Simplified Technical English (long or passive sentences, vague words, several actions in one sentence); they never block. The JSON for agents is unchanged (`docs goal-contract`, "Writing for people").
|
|
23
|
+
- **Changed:** skill headroom. The Judge and ITERATE steps moved to `loop-judge` (read only when `judgeRequired`, on T2 or on ITERATE), REPORT_ONLY / UNATTENDED / Maker intern to `loop-modes`, and the report header block to `loop-deliver`. SKILL.md 4000 -> 3757 of 4000 chars; T1 context 17853 -> 16626 of 17859. No rule was dropped.
|
|
24
|
+
|
|
9
25
|
## 2.13.0 - 2026-11-21
|
|
10
26
|
|
|
11
27
|
Newcomer UX from a clean Docker sandbox (cards C-47..C-56 in `docs/cards/novice-ux-2026-11-21.md`; rerun with `scripts/sandbox-e2e.sh`) and "dig first" (C-45, C-46 in `docs/cards/dig-first-2026-11-21.md`).
|
|
@@ -6,7 +6,7 @@ For hosts with no subagent tool (certification `instruction-only`). Full skill:
|
|
|
6
6
|
Loop: Specify (0-1), Make (2-4), Review (5-7), Deliver (8). You are Maker. Devil's Advocate (DA) and Judge run in this session as `CONTEXT_ISOLATION_ONLY`, with the same budgets; never claim independent review.
|
|
7
7
|
|
|
8
8
|
1. `npx ai-engineering-loop run --json` gives runId, tier, budget. Read `.ai-engineering-loop/glossary.md`.
|
|
9
|
-
2. Goal Contract: AC is a failure table (happy, empty, boundary, error). Only after the human freezes: `goal freeze --latest --run <runId> --by human`. Chat agreement is not freeze.
|
|
9
|
+
2. Goal Contract: AC is a failure table (happy, empty, boundary, error). Only after the human freezes: `goal freeze --json --latest --run <runId> --by human`. Chat agreement is not freeze.
|
|
10
10
|
3. Maker: one red test per AC row before the fix, then `gate maker`.
|
|
11
11
|
4. `verify --cmd <test command>`, then write claimed-vs-reality.md.
|
|
12
12
|
5. DA: re-read only the diff, Goal, and evidence; log findings; `gate review`. Judge: write the verdict from the evidence, then `gate judge`. ITERATE at most 3 times.
|
|
@@ -3336,6 +3336,11 @@ function handleGoal() {
|
|
|
3336
3336
|
const extra = {};
|
|
3337
3337
|
if (action === 'show') {
|
|
3338
3338
|
result = loadGoalDraft(CWD, runId);
|
|
3339
|
+
if (process.argv.includes('--human')) {
|
|
3340
|
+
if (!result) throw Object.assign(new Error('No Goal draft yet'), { code: 'GOAL_DRAFT_MISSING', fix: '`scaffold goal`, fill it in, then `goal draft --file .ai-engineering-loop/drafts/goal.json --revision 0`.' });
|
|
3341
|
+
process.stdout.write(require('../lib/ste.js').renderHumanGoal(result.contract, { runId, revision: result.metadata?.revision }));
|
|
3342
|
+
return;
|
|
3343
|
+
}
|
|
3339
3344
|
if (result?.contract?.designRef) extra.design = require('../lib/design-ref.js').designStatus(CWD, result.contract.designRef);
|
|
3340
3345
|
} else if (action === 'draft') {
|
|
3341
3346
|
appendRunLifecycle(CWD, runId, {
|
|
@@ -3375,6 +3380,11 @@ function handleGoal() {
|
|
|
3375
3380
|
expectedRevision: requiredIntegerArg('--revision')
|
|
3376
3381
|
});
|
|
3377
3382
|
extra.impactPreview = impactPreview(runId, draftGoal);
|
|
3383
|
+
const ste = require('../lib/ste.js');
|
|
3384
|
+
const humanPath = path.join(runsDir(CWD), runId, 'goal.md');
|
|
3385
|
+
fs.writeFileSync(humanPath, ste.renderHumanGoal(draftGoal, { runId, revision: result.metadata?.revision }), { mode: 0o600 });
|
|
3386
|
+
extra.human = { path: path.relative(CWD, humanPath).split(path.sep).join('/'), show: `goal show --run ${runId} --human` };
|
|
3387
|
+
extra.readability = ste.goalReadability(draftGoal);
|
|
3378
3388
|
if (draftGoal && draftGoal.flow != null) {
|
|
3379
3389
|
const flowLib = require('../lib/flow.js');
|
|
3380
3390
|
extra.flow = { table: flowLib.renderFlow(draftGoal.flow), mermaid: flowLib.renderMermaid(draftGoal.flow), problems: flowLib.flowProblems(draftGoal.flow), warnings: flowLib.flowWarnings(draftGoal.flow), ...flowLib.flowCounts(draftGoal) };
|
|
@@ -3461,12 +3471,17 @@ function handleGoal() {
|
|
|
3461
3471
|
error.code = 'INVALID_USAGE';
|
|
3462
3472
|
throw error;
|
|
3463
3473
|
}
|
|
3464
|
-
if (
|
|
3474
|
+
if (!process.argv.includes('--json') && ['draft', 'freeze'].includes(action)) {
|
|
3465
3475
|
const meta = result?.metadata || {};
|
|
3466
3476
|
log.success(`✓ goal ${action}: Run ${runId}${meta.revision != null ? `, revision ${meta.revision}` : ''}${meta.contentHash ? ` (${String(meta.contentHash).slice(0, 12)})` : ''}`);
|
|
3477
|
+
if (action === 'draft' && extra.human) {
|
|
3478
|
+
console.log('');
|
|
3479
|
+
process.stdout.write(fs.readFileSync(path.join(CWD, extra.human.path), 'utf8'));
|
|
3480
|
+
console.log('');
|
|
3481
|
+
}
|
|
3467
3482
|
if (extra.impactPreview) console.log(`- Impact preview: ${JSON.stringify(extra.impactPreview).slice(0, 200)}`);
|
|
3468
3483
|
if (extra.warning) console.log(`! ${extra.warning}`);
|
|
3469
|
-
console.log(action === 'draft' ? `- Next:
|
|
3484
|
+
console.log(action === 'draft' ? `- Next: the human reads this and says freeze; then \`goal freeze --latest --run ${runId} --by <name>\`. Agents: add --json.` : '- Next: Maker (implement), then `gate maker --from-git`. Agents: add --json.');
|
|
3470
3485
|
return;
|
|
3471
3486
|
}
|
|
3472
3487
|
console.log(JSON.stringify({ ok: true, runId, [action === 'show' ? 'draft' : 'result']: result, ...extra }, null, 2));
|
|
@@ -4765,6 +4780,7 @@ Commands:
|
|
|
4765
4780
|
draft --file <json> --revision <n> [--run <id>] [--by <agent>]
|
|
4766
4781
|
draft --from-design <doc.md> [--file <json>] --revision <n> prefill from a design doc, record designRef
|
|
4767
4782
|
freeze --revision <n> --hash <sha256> [--run <id>] [--by <name>]
|
|
4783
|
+
show --human [--run <id>] the Goal as plain Markdown for people (STE style: short active sentences)
|
|
4768
4784
|
freeze --latest [--run <id>] --by <name> freeze the newest draft (CLI resolves revision/hash)
|
|
4769
4785
|
diagram --view state|storyboard|lanes [--run <id>] [--revision <n>] [--lang <tag>] [--open] draw the Goal flow as HTML
|
|
4770
4786
|
verification Summarize verification.json for compact Judge context
|
|
@@ -4977,7 +4993,7 @@ function printHelp() {
|
|
|
4977
4993
|
}
|
|
4978
4994
|
|
|
4979
4995
|
function commandNames() {
|
|
4980
|
-
return [...new Set(helpText().split('\n').map((line) => (line.match(/^ ([a-z][\w-]*)(?:
|
|
4996
|
+
return [...new Set(helpText().split('\n').map((line) => (line.match(/^ ([a-z][\w-]*)(?: (?:\[[^\]]+\]|<[^>]+>))*(?:\s{2,}|\s+(?=[A-Z])|\s*$)/) || [])[1]).filter(Boolean))];
|
|
4981
4997
|
}
|
|
4982
4998
|
|
|
4983
4999
|
function shortHelp() {
|
package/core/goal-contract.md
CHANGED
|
@@ -230,3 +230,21 @@ The receipt lists `--evidence AC-N=<https-url>` links first, typed as video, scr
|
|
|
230
230
|
```
|
|
231
231
|
|
|
232
232
|
Then: `goal draft --run <runId> --file .ai-engineering-loop/drafts/goal.json --revision 0`, show the draft to the human, and `goal freeze`.
|
|
233
|
+
|
|
234
|
+
## Writing for people: STE style (ASD-STE100)
|
|
235
|
+
|
|
236
|
+
The Goal JSON is for the tools; people read `RUN_DIR/goal.md` (`goal show --human`), written on every `goal draft`. Write the text fields in the style of ASD-STE100 Simplified Technical English (https://www.asd-ste100.org), so a reviewer, a client or a non-native reader understands each line on the first read:
|
|
237
|
+
|
|
238
|
+
| Rule | Do | Not |
|
|
239
|
+
|---|---|---|
|
|
240
|
+
| One fact or one action per sentence | "Export saves a CSV file." | "Export saves a CSV and then emails it and logs it." |
|
|
241
|
+
| Active voice: say who does what | "The API rejects an empty name." | "An empty name is rejected." |
|
|
242
|
+
| Short sentences | Instructions 20 words or fewer, descriptions 25 or fewer | Long sentences with many clauses |
|
|
243
|
+
| Words a test can check | "The page loads in 2 seconds or less." | "fast", "robust", "properly", "should", "etc." |
|
|
244
|
+
| Same word for the same thing | Use the glossary term every time | Switching between "invoice", "bill" and "receipt" |
|
|
245
|
+
| Start with the subject or the verb | "The filter keeps the last value." | "Keeping the last value, the filter..." |
|
|
246
|
+
|
|
247
|
+
`goal draft` prints `goal.md` and the next step by default; agents and scripts pass `--json` for the full JSON. With `--json` it returns `readability`: warnings for long sentences, passive voice, vague words, several actions in one sentence and sentences that start with an -ing word. They never block the gate; fix them before you ask for the freeze. AEL checks these general writing rules only; it does not ship the ASD-STE100 dictionary.
|
|
248
|
+
|
|
249
|
+
`goal.md` has these sections: What changes, Done when (each AC with its proof and "Fail if" lines), Not in this change, Not confirmed yet (assumptions from `statements`), and the writing checks.
|
|
250
|
+
|
package/lib/ste.js
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
'use strict';
|
|
2
|
+
|
|
3
|
+
const MAX_WORDS = { instruction: 20, description: 25 };
|
|
4
|
+
const VAGUE = ['should', 'might', 'could', 'would', 'may', 'maybe', 'probably', 'possibly', 'some', 'various', 'etc', 'and/or', 'appropriate', 'properly', 'correctly', 'as needed', 'if necessary', 'user-friendly', 'robust', 'seamless', 'fast', 'easy'];
|
|
5
|
+
const PASSIVE = /\b(is|are|was|were|be|been|being|gets|got)\s+(\w+ly\s+)?(\w+ed|built|done|made|shown|sent|set|written|given|taken|seen|known|found|kept|held|read|run|left|put|shut|split|spent|chosen|broken)\b/i;
|
|
6
|
+
const IMPERATIVE_HINT = /^(add|remove|show|hide|send|save|open|close|keep|use|return|reject|accept|write|read|run|stop|start|set|make|create|delete|update|move|check|display|export|import|log|block|allow)\b/i;
|
|
7
|
+
|
|
8
|
+
const words = (sentence) => sentence.split(/\s+/).filter((word) => /[A-Za-z0-9]/.test(word));
|
|
9
|
+
|
|
10
|
+
function sentences(text) {
|
|
11
|
+
return String(text || '')
|
|
12
|
+
.replace(/`[^`]*`/g, 'CODE')
|
|
13
|
+
.split(/(?<=[.!?;])\s+|\n+/)
|
|
14
|
+
.map((part) => part.trim())
|
|
15
|
+
.filter(Boolean);
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
function steFindings(text, { kind = 'description' } = {}) {
|
|
19
|
+
const findings = [];
|
|
20
|
+
const limit = MAX_WORDS[kind] || MAX_WORDS.description;
|
|
21
|
+
for (const sentence of sentences(text)) {
|
|
22
|
+
const count = words(sentence).length;
|
|
23
|
+
if (count > limit) findings.push({ rule: 'length', detail: `${count} words; keep ${kind} sentences at ${limit} or fewer` });
|
|
24
|
+
if (PASSIVE.test(sentence)) findings.push({ rule: 'active-voice', detail: `passive "${sentence.match(PASSIVE)[0]}"; say who does what` });
|
|
25
|
+
const lower = ` ${sentence.toLowerCase().replace(/[^a-z/\s-]/g, ' ')} `;
|
|
26
|
+
const vague = VAGUE.filter((word) => lower.includes(` ${word} `));
|
|
27
|
+
if (vague.length) findings.push({ rule: 'precise-words', detail: `vague: ${vague.join(', ')}; use a word a test can check` });
|
|
28
|
+
if (kind === 'instruction' && (sentence.match(/\b(and then|then|and also)\b/gi) || []).length) findings.push({ rule: 'one-instruction', detail: 'more than one action; write one sentence per action' });
|
|
29
|
+
if (/^\w+ing\b/.test(sentence) && !IMPERATIVE_HINT.test(sentence)) findings.push({ rule: 'no-ing-start', detail: 'starts with an -ing word; start with the subject or the verb' });
|
|
30
|
+
}
|
|
31
|
+
return findings;
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
function goalReadability(goal) {
|
|
35
|
+
const out = [];
|
|
36
|
+
const add = (field, text, kind) => {
|
|
37
|
+
for (const finding of steFindings(text, { kind })) out.push({ field, ...finding });
|
|
38
|
+
};
|
|
39
|
+
add('objective', goal?.objective, 'description');
|
|
40
|
+
if (goal?.plainSummary) add('plainSummary', goal.plainSummary, 'description');
|
|
41
|
+
for (const criterion of goal?.acceptanceCriteria || []) {
|
|
42
|
+
add(`${criterion.id}.statement`, criterion.statement, 'description');
|
|
43
|
+
(criterion.failureCases || []).forEach((item, index) => add(`${criterion.id}.failureCases[${index}]`, item, 'description'));
|
|
44
|
+
}
|
|
45
|
+
return out;
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
const line = (text) => String(text || '').replace(/\s+/g, ' ').trim();
|
|
49
|
+
|
|
50
|
+
function renderHumanGoal(goal, { runId = goal?.runId, revision = null } = {}) {
|
|
51
|
+
const parts = [`# Goal${runId ? ` for Run ${runId}` : ''}${revision != null ? ` (revision ${revision})` : ''}`, ''];
|
|
52
|
+
parts.push('## What changes', '', line(goal?.plainSummary || goal?.objective), '');
|
|
53
|
+
parts.push('## Done when', '');
|
|
54
|
+
for (const criterion of goal?.acceptanceCriteria || []) {
|
|
55
|
+
parts.push(`${criterion.id}. ${line(criterion.statement)}`);
|
|
56
|
+
parts.push(` - Proof: ${line(criterion.evidenceRequired)}.`.replace(/\.\.$/, '.'));
|
|
57
|
+
for (const failure of criterion.failureCases || []) parts.push(` - Fail if: ${line(failure)}`);
|
|
58
|
+
}
|
|
59
|
+
parts.push('');
|
|
60
|
+
if ((goal?.outOfScope || []).length) parts.push('## Not in this change', '', ...goal.outOfScope.map((item) => `- ${line(item)}`), '');
|
|
61
|
+
const statements = goal?.statements || [];
|
|
62
|
+
const unconfirmed = statements.filter((item) => item.kind === 'assumption');
|
|
63
|
+
if (unconfirmed.length) parts.push('## Not confirmed yet', '', ...unconfirmed.map((item) => `- ${line(item.text)}`), '');
|
|
64
|
+
const findings = goalReadability(goal);
|
|
65
|
+
if (findings.length) parts.push('## Writing checks (STE style, not blocking)', '', ...findings.map((item) => `- ${item.field}: ${item.detail}`), '');
|
|
66
|
+
return `${parts.join('\n').trimEnd()}\n`;
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
module.exports = { MAX_WORDS, goalReadability, renderHumanGoal, steFindings };
|
package/lib/sync-hosts.js
CHANGED
|
@@ -99,8 +99,7 @@ const VERIFICATION_CATALOG = Object.freeze({
|
|
|
99
99
|
formal: { layer: 'LF', plan: false, what: 'formal verification (TLA+, Lean, model checking)' }
|
|
100
100
|
});
|
|
101
101
|
const LAYER_OF_KEY = Object.freeze(Object.fromEntries(Object.entries(VERIFICATION_CATALOG).map(([key, entry]) => [key, entry.layer])));
|
|
102
|
-
// Cheapest-first default plan
|
|
103
|
-
// "Default order"): L1 static checks, then L2 unit and property tests.
|
|
102
|
+
// Cheapest-first default plan: L1 static checks, then L2 unit and property tests.
|
|
104
103
|
const DEFAULT_PLAN_KEYS = Object.freeze(Object.keys(VERIFICATION_CATALOG).filter((key) => VERIFICATION_CATALOG[key].plan));
|
|
105
104
|
|
|
106
105
|
function layerOfKey(key) {
|
package/package.json
CHANGED
package/README.npm.md
DELETED
|
@@ -1,104 +0,0 @@
|
|
|
1
|
-
# AI Engineering Loop
|
|
2
|
-
|
|
3
|
-
[](https://www.npmjs.com/package/ai-engineering-loop)
|
|
4
|
-
[](https://opensource.org/licenses/MIT)
|
|
5
|
-
[](https://github.com/egagofur/ai-engineering-loop)
|
|
6
|
-
|
|
7
|
-
**A Reusable, Framework-Agnostic AI Engineering Operating System for Safe Coding Agents**
|
|
8
|
-
|
|
9
|
-
Move beyond linear AI pipelines and optimistic self-evaluation toward contract-driven execution, deterministic machine verification, independent adversarial review, and living project context.
|
|
10
|
-
|
|
11
|
-
---
|
|
12
|
-
|
|
13
|
-
## Quickstart CLI
|
|
14
|
-
|
|
15
|
-
Run the CLI in any repository root without global installation:
|
|
16
|
-
|
|
17
|
-
```bash
|
|
18
|
-
# 1. Bootstrap .ai-engineering-loop/ context from repository discovery
|
|
19
|
-
npx ai-engineering-loop init
|
|
20
|
-
|
|
21
|
-
# 2. Check the validity, readiness, and baseline freshness of context
|
|
22
|
-
npx ai-engineering-loop status
|
|
23
|
-
|
|
24
|
-
# 3. Reconcile drifted context against repository non-destructively
|
|
25
|
-
npx ai-engineering-loop refresh
|
|
26
|
-
|
|
27
|
-
# 4. Verify context readiness and begin engineering loop
|
|
28
|
-
npx ai-engineering-loop run
|
|
29
|
-
|
|
30
|
-
# Optional: analysis without repository mutation
|
|
31
|
-
npx ai-engineering-loop run --mode report-only "audit this repository"
|
|
32
|
-
|
|
33
|
-
# Inspect spend controls; ASSISTED is the default
|
|
34
|
-
npx ai-engineering-loop policy show
|
|
35
|
-
npx ai-engineering-loop budget status
|
|
36
|
-
npx ai-engineering-loop policy set --review-profile lean
|
|
37
|
-
npx ai-engineering-loop context query createStudioRun
|
|
38
|
-
npx ai-engineering-loop context fast-path --json
|
|
39
|
-
npx ai-engineering-loop context diff-hunks --run <run-id>
|
|
40
|
-
npx ai-engineering-loop verification summarize --run <run-id>
|
|
41
|
-
npx ai-engineering-loop context compact --run <run-id>
|
|
42
|
-
|
|
43
|
-
# Author and observe deterministic workflow recipes locally
|
|
44
|
-
npx ai-engineering-loop studio
|
|
45
|
-
|
|
46
|
-
# Export a redacted, integrity-bound knowledge handoff
|
|
47
|
-
npx ai-engineering-loop handoff create --audience developer
|
|
48
|
-
|
|
49
|
-
# 5. Copy package host skills into ~/.claude ~/.grok ~/.gemini ~/.agents
|
|
50
|
-
# Default: core pack (ai-engineering-loop skill, DA/Judge agents, commands).
|
|
51
|
-
# Optional: --pack backend,design (saved for later syncs); --prune removes them again.
|
|
52
|
-
npx ai-engineering-loop sync-hosts
|
|
53
|
-
npx ai-engineering-loop sync-hosts --pack backend,design
|
|
54
|
-
|
|
55
|
-
# Read one packaged spec instead of the whole package source
|
|
56
|
-
npx ai-engineering-loop docs grill-policy --section "When to grill"
|
|
57
|
-
```
|
|
58
|
-
|
|
59
|
-
---
|
|
60
|
-
|
|
61
|
-
## What It Does
|
|
62
|
-
|
|
63
|
-
1. **Zero-Config Discovery (`init`)**: Analyzes repository topology (monorepo vs single app), package manifests (`package.json`, `go.mod`, `Cargo.toml`, etc.), frameworks, and test scripts to generate `.ai-engineering-loop/` including `glossary.md` and `adrs/`.
|
|
64
|
-
2. **Living Project Context**: Tracks repository revisions and manifest checksums in `metadata.json` for instant drift detection. Stage 1 grill freezes a Goal Contract; Maker uses TDD at named seams; DA reports Spec vs Standards without merging them.
|
|
65
|
-
3. **Multi-Agent Triad**: Coordinates **Maker** (surgical diffs & tests), **Devil's Advocate** (independent adversarial review), and **Judge** (impartial evaluation & PASS certification).
|
|
66
|
-
4. **Context Impact Assessment**: Evaluates completed tasks (`NONE`, `TARGETED`, `MAJOR`) to keep project context fresh without expensive whole-repo re-analysis.
|
|
67
|
-
5. **Grok CLI host**: Native `spawn_subagent` for Devil's Advocate and Judge (`TRUE_INDEPENDENT_AGENT`). Disabled by `GROK_SUBAGENTS=0`.
|
|
68
|
-
6. **Production runtime controls**: `REPORT_ONLY`, human-approved `ASSISTED`, opt-in `UNATTENDED`, actual token ledgers, lean/standard/thorough review profiles, smart hunk-only context packs, a persistent kill switch, and locked disposable Maker worktrees.
|
|
69
|
-
7. **Local Workflow Studio**: A localhost-only authenticated DAG canvas with animated live stage state, token telemetry, explicit approvals, decision memory, atomic recipe installation, and redacted handoff export. It does not execute models or shell commands in the browser.
|
|
70
|
-
|
|
71
|
-
---
|
|
72
|
-
|
|
73
|
-
## Grok CLI
|
|
74
|
-
|
|
75
|
-
Inside a Grok TUI session, `/ael` uses repo-local `.grok/agents/` types. Devil's Advocate and Judge spawn as sibling children (`capability_mode: execute`, no `resume_from`). Do not use `caveman:cavecrew-reviewer` as the loop reviewer.
|
|
76
|
-
|
|
77
|
-
## Claude Code
|
|
78
|
-
|
|
79
|
-
Inside Claude Code, `/ael` uses `.claude/agents/` types via the **Task** tool. Pass only `subagent_type`, `description`, and `prompt`. Do not pass Grok keys (`spawn_subagent`, `capability_mode`, `resume_from`) — extra keys cause Kiro `REQUEST_BODY_INVALID`.
|
|
80
|
-
|
|
81
|
-
---
|
|
82
|
-
|
|
83
|
-
## Antigravity IDE Integration
|
|
84
|
-
|
|
85
|
-
In Antigravity IDE or compatible agentic platforms, invoke the loop directly in chat:
|
|
86
|
-
|
|
87
|
-
- `/ael init` — Bootstrap project context only.
|
|
88
|
-
- `/ael status` — Check context health and living freshness.
|
|
89
|
-
- `/ael refresh` — Reconcile drifted context files.
|
|
90
|
-
- `/ael <task>` — Execute the full 8-stage engineering lifecycle.
|
|
91
|
-
|
|
92
|
-
---
|
|
93
|
-
|
|
94
|
-
## Complete Documentation & Specifications
|
|
95
|
-
|
|
96
|
-
For the complete architectural specifications, project profiles (`web-app`, `backend-api`, `mobile-app`, `library`, `monorepo`), delivery adapters (GitLab, GitHub, Mattermost), and reference examples:
|
|
97
|
-
|
|
98
|
-
👉 **[Visit the GitHub Repository](https://github.com/egagofur/ai-engineering-loop)**
|
|
99
|
-
|
|
100
|
-
---
|
|
101
|
-
|
|
102
|
-
## License
|
|
103
|
-
|
|
104
|
-
MIT License — see [LICENSE](https://github.com/egagofur/ai-engineering-loop/blob/main/LICENSE) for details.
|
package/docs/images/ael-hero.svg
DELETED
|
@@ -1,19 +0,0 @@
|
|
|
1
|
-
<svg width="960" height="380" viewBox="0 0 960 380" fill="none" xmlns="http://www.w3.org/2000/svg">
|
|
2
|
-
<rect width="960" height="380" rx="12" fill="#FDFDFB"/>
|
|
3
|
-
<rect x="1" y="1" width="958" height="378" rx="11" stroke="#D9D9D5" stroke-width="2"/>
|
|
4
|
-
<text x="48" y="78" fill="#777777" font-family="monospace" font-size="15" letter-spacing="1.5">AI ENGINEERING LOOP</text>
|
|
5
|
-
<text x="48" y="148" fill="#111111" font-family="monospace" font-size="48" letter-spacing="-3">From idea to</text>
|
|
6
|
-
<text x="48" y="204" fill="#FC6404" font-family="monospace" font-size="48" letter-spacing="-3">trusted code.</text>
|
|
7
|
-
<rect x="48" y="258" width="430" height="56" stroke="#111111" stroke-width="2"/>
|
|
8
|
-
<text x="72" y="294" fill="#FC6404" font-family="monospace" font-size="20">$</text>
|
|
9
|
-
<text x="100" y="294" fill="#111111" font-family="monospace" font-size="19">npx ai-engineering-loop init</text>
|
|
10
|
-
<g>
|
|
11
|
-
<circle cx="748" cy="188" r="100" fill="#FC6404">
|
|
12
|
-
<animate attributeName="r" values="100;96;100" dur="3.2s" repeatCount="indefinite"/>
|
|
13
|
-
</circle>
|
|
14
|
-
<ellipse cx="712" cy="190" rx="11" ry="24" fill="#111111" transform="rotate(-8 712 190)"><animate attributeName="opacity" values="1;1;0.12;1" dur="4.8s" repeatCount="indefinite"/></ellipse>
|
|
15
|
-
<ellipse cx="782" cy="190" rx="11" ry="24" fill="#111111" transform="rotate(8 782 190)"><animate attributeName="opacity" values="1;1;0.12;1" dur="4.8s" repeatCount="indefinite"/></ellipse>
|
|
16
|
-
<path d="M602 298H894" stroke="#111111" stroke-width="2"/>
|
|
17
|
-
<ellipse cx="748" cy="304" rx="78" ry="8" fill="#111111" fill-opacity="0.14"/>
|
|
18
|
-
</g>
|
|
19
|
-
</svg>
|
|
@@ -1,114 +0,0 @@
|
|
|
1
|
-
<svg xmlns="http://www.w3.org/2000/svg" width="1440" height="900" viewBox="0 0 1440 900" role="img" aria-labelledby="title description">
|
|
2
|
-
<title id="title">AI Engineering Loop overview</title>
|
|
3
|
-
<desc id="description">A user task passes through context preparation, Specify, Make, Review, and Deliver. Failed verification and Judge ITERATE decisions return to Maker. Only a Judge PASS reaches delivery.</desc>
|
|
4
|
-
<defs>
|
|
5
|
-
<marker id="arrow" markerWidth="10" markerHeight="10" refX="8" refY="5" orient="auto">
|
|
6
|
-
<path d="M0 0L10 5L0 10Z" fill="#59616d"/>
|
|
7
|
-
</marker>
|
|
8
|
-
<marker id="arrow-orange" markerWidth="10" markerHeight="10" refX="8" refY="5" orient="auto">
|
|
9
|
-
<path d="M0 0L10 5L0 10Z" fill="#e95d37"/>
|
|
10
|
-
</marker>
|
|
11
|
-
<style>
|
|
12
|
-
.title{font:700 38px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#17191d}
|
|
13
|
-
.subtitle{font:400 18px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#59616d}
|
|
14
|
-
.phase{font:700 14px system-ui,-apple-system,"Segoe UI",sans-serif;letter-spacing:2px;fill:#59616d}
|
|
15
|
-
.number{font:700 16px ui-monospace,SFMono-Regular,Consolas,monospace;fill:#ffffff}
|
|
16
|
-
.node-title{font:700 19px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#17191d}
|
|
17
|
-
.node-copy{font:400 14px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#59616d}
|
|
18
|
-
.gate{font:700 13px system-ui,-apple-system,"Segoe UI",sans-serif;letter-spacing:1px;fill:#17191d}
|
|
19
|
-
.label{font:700 13px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#59616d}
|
|
20
|
-
.small{font:400 13px system-ui,-apple-system,"Segoe UI",sans-serif;fill:#6d7480}
|
|
21
|
-
.line{fill:none;stroke:#59616d;stroke-width:3;marker-end:url(#arrow)}
|
|
22
|
-
.feedback{fill:none;stroke:#e95d37;stroke-width:3;stroke-dasharray:8 7;marker-end:url(#arrow-orange)}
|
|
23
|
-
</style>
|
|
24
|
-
</defs>
|
|
25
|
-
|
|
26
|
-
<rect width="1440" height="900" rx="24" fill="#f5f2eb"/>
|
|
27
|
-
<text class="title" x="70" y="72">From task to trusted delivery</text>
|
|
28
|
-
<text class="subtitle" x="70" y="106">One workflow. Eight stages. Evidence advances the work—not AI confidence.</text>
|
|
29
|
-
|
|
30
|
-
<rect x="70" y="145" width="1300" height="98" rx="14" fill="#ffffff" stroke="#d8d3c9" stroke-width="2"/>
|
|
31
|
-
<rect x="94" y="170" width="154" height="48" rx="24" fill="#17191d"/>
|
|
32
|
-
<text x="171" y="200" text-anchor="middle" style="font:700 16px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#fff">USER TASK</text>
|
|
33
|
-
<path class="line" d="M250 194H328"/>
|
|
34
|
-
<text class="node-title" x="355" y="188">Stage 0 · Prepare context</text>
|
|
35
|
-
<text class="node-copy" x="355" y="213">Initialize missing context or reconcile drift before reasoning begins.</text>
|
|
36
|
-
<path class="line" d="M920 194H1120"/>
|
|
37
|
-
<rect x="1132" y="166" width="204" height="56" rx="9" fill="#fff4e8" stroke="#e95d37" stroke-width="2"/>
|
|
38
|
-
<text class="gate" x="1234" y="190" text-anchor="middle">CONTEXT READY</text>
|
|
39
|
-
<text class="small" x="1234" y="210" text-anchor="middle">deterministic check</text>
|
|
40
|
-
|
|
41
|
-
<text class="phase" x="70" y="298">SPECIFY</text>
|
|
42
|
-
<text class="phase" x="380" y="298">MAKE</text>
|
|
43
|
-
<text class="phase" x="835" y="298">REVIEW</text>
|
|
44
|
-
<text class="phase" x="1190" y="298">DELIVER</text>
|
|
45
|
-
|
|
46
|
-
<rect x="70" y="320" width="270" height="322" rx="16" fill="#fff8ef" stroke="#e6b083" stroke-width="2"/>
|
|
47
|
-
<circle cx="104" cy="365" r="18" fill="#e95d37"/><text class="number" x="104" y="371" text-anchor="middle">1</text>
|
|
48
|
-
<text class="node-title" x="135" y="362">Goal Contract</text>
|
|
49
|
-
<text class="node-copy" x="104" y="398">Freeze explicit acceptance</text>
|
|
50
|
-
<text class="node-copy" x="104" y="419">criteria and failure cases.</text>
|
|
51
|
-
<line x1="104" y1="451" x2="306" y2="451" stroke="#e6b083"/>
|
|
52
|
-
<text class="gate" x="104" y="484">OUTPUT</text>
|
|
53
|
-
<text class="node-copy" x="104" y="513">A shared definition of done</text>
|
|
54
|
-
<text class="node-copy" x="104" y="534">that machines can verify.</text>
|
|
55
|
-
<rect x="104" y="570" width="202" height="44" rx="8" fill="#ffffff" stroke="#e6b083"/>
|
|
56
|
-
<text class="gate" x="205" y="597" text-anchor="middle">GOAL GATE</text>
|
|
57
|
-
|
|
58
|
-
<rect x="380" y="320" width="415" height="322" rx="16" fill="#f1f6fb" stroke="#94b5d2" stroke-width="2"/>
|
|
59
|
-
<circle cx="414" cy="365" r="18" fill="#467da8"/><text class="number" x="414" y="371" text-anchor="middle">2</text>
|
|
60
|
-
<text class="node-title" x="445" y="362">Root cause</text>
|
|
61
|
-
<text class="node-copy" x="414" y="394">Reproduce and explain the real problem.</text>
|
|
62
|
-
<path d="M414 422H760" stroke="#b8cad9" stroke-width="2"/>
|
|
63
|
-
<circle cx="414" cy="463" r="18" fill="#467da8"/><text class="number" x="414" y="469" text-anchor="middle">3</text>
|
|
64
|
-
<text class="node-title" x="445" y="460">Implementation plan</text>
|
|
65
|
-
<text class="node-copy" x="414" y="492">Choose seams, tests, and the smallest coherent change.</text>
|
|
66
|
-
<path d="M414 520H760" stroke="#b8cad9" stroke-width="2"/>
|
|
67
|
-
<circle cx="414" cy="561" r="18" fill="#467da8"/><text class="number" x="414" y="567" text-anchor="middle">4</text>
|
|
68
|
-
<text class="node-title" x="445" y="558">Maker</text>
|
|
69
|
-
<text class="node-copy" x="414" y="590">Implement surgical changes with red → green tests.</text>
|
|
70
|
-
<rect x="643" y="550" width="117" height="44" rx="8" fill="#ffffff" stroke="#94b5d2"/>
|
|
71
|
-
<text class="gate" x="701" y="577" text-anchor="middle">DIFF + TESTS</text>
|
|
72
|
-
|
|
73
|
-
<rect x="835" y="320" width="315" height="322" rx="16" fill="#f5f0fa" stroke="#b49bcb" stroke-width="2"/>
|
|
74
|
-
<circle cx="869" cy="365" r="18" fill="#765596"/><text class="number" x="869" y="371" text-anchor="middle">5</text>
|
|
75
|
-
<text class="node-title" x="900" y="362">Verify</text>
|
|
76
|
-
<text class="node-copy" x="869" y="394">Run commands; capture exact evidence.</text>
|
|
77
|
-
<path d="M869 422H1115" stroke="#c9bad7" stroke-width="2"/>
|
|
78
|
-
<circle cx="869" cy="463" r="18" fill="#765596"/><text class="number" x="869" y="469" text-anchor="middle">6</text>
|
|
79
|
-
<text class="node-title" x="900" y="460">Devil’s Advocate</text>
|
|
80
|
-
<text class="node-copy" x="869" y="492">Challenge claims against reality.</text>
|
|
81
|
-
<path d="M869 520H1115" stroke="#c9bad7" stroke-width="2"/>
|
|
82
|
-
<circle cx="869" cy="561" r="18" fill="#765596"/><text class="number" x="869" y="567" text-anchor="middle">7</text>
|
|
83
|
-
<text class="node-title" x="900" y="558">Judge</text>
|
|
84
|
-
<text class="node-copy" x="869" y="590">PASS, ITERATE, or ESCALATE.</text>
|
|
85
|
-
|
|
86
|
-
<rect x="1190" y="320" width="180" height="322" rx="16" fill="#eef8f1" stroke="#81b994" stroke-width="2"/>
|
|
87
|
-
<circle cx="1224" cy="365" r="18" fill="#39885a"/><text class="number" x="1224" y="371" text-anchor="middle">8</text>
|
|
88
|
-
<text class="node-title" x="1255" y="362">Deliver</text>
|
|
89
|
-
<text class="node-copy" x="1224" y="404">Refresh context.</text>
|
|
90
|
-
<text class="node-copy" x="1224" y="428">Require approval.</text>
|
|
91
|
-
<text class="node-copy" x="1224" y="452">Publish through</text>
|
|
92
|
-
<text class="node-copy" x="1224" y="476">the adapter.</text>
|
|
93
|
-
<rect x="1216" y="550" width="128" height="64" rx="9" fill="#39885a"/>
|
|
94
|
-
<text x="1280" y="576" text-anchor="middle" style="font:700 13px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#fff">TARGET</text>
|
|
95
|
-
<text x="1280" y="596" text-anchor="middle" style="font:400 13px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#fff">REPOSITORY</text>
|
|
96
|
-
|
|
97
|
-
<path class="line" d="M340 365H380"/>
|
|
98
|
-
<path class="line" d="M795 561H815V365H835"/>
|
|
99
|
-
<path class="line" d="M1150 561H1170V365H1190"/>
|
|
100
|
-
<rect x="1139" y="505" width="62" height="28" rx="14" fill="#39885a"/>
|
|
101
|
-
<text x="1170" y="524" text-anchor="middle" style="font:700 12px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#fff">PASS</text>
|
|
102
|
-
|
|
103
|
-
<path class="feedback" d="M869 365C810 365 820 700 650 700H590C515 700 500 636 500 610"/>
|
|
104
|
-
<rect x="656" y="676" width="137" height="28" rx="14" fill="#f5f2eb"/>
|
|
105
|
-
<text class="label" x="724" y="695" text-anchor="middle">FAIL → FIX</text>
|
|
106
|
-
<path class="feedback" d="M869 561C815 561 835 770 665 770H575C470 770 455 650 455 610"/>
|
|
107
|
-
<rect x="665" y="746" width="175" height="28" rx="14" fill="#f5f2eb"/>
|
|
108
|
-
<text class="label" x="752" y="765" text-anchor="middle">ITERATE → MAKER</text>
|
|
109
|
-
|
|
110
|
-
<rect x="70" y="815" width="1300" height="48" rx="10" fill="#17191d"/>
|
|
111
|
-
<circle cx="101" cy="839" r="7" fill="#e95d37"/>
|
|
112
|
-
<text x="119" y="845" style="font:600 14px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#fff">Safety invariant:</text>
|
|
113
|
-
<text x="245" y="845" style="font:400 14px system-ui,-apple-system,'Segoe UI',sans-serif;fill:#d5d8dd">a model can propose work, but only contracts, artifacts, verification evidence, and gates can advance the run.</text>
|
|
114
|
-
</svg>
|
|
Binary file
|
|
@@ -1,136 +0,0 @@
|
|
|
1
|
-
<svg xmlns="http://www.w3.org/2000/svg" width="1600" height="900" viewBox="0 0 1600 900" role="img" aria-labelledby="title desc">
|
|
2
|
-
<title id="title">AI Engineering Loop Workflow Studio</title>
|
|
3
|
-
<desc id="desc">A dark Workflow Studio live-run view: a stage rail from goal to deliver with review in progress, a pending question banner, compliance chips, a short timeline, and a Start with AI Agent button.</desc>
|
|
4
|
-
<defs>
|
|
5
|
-
<linearGradient id="bg" x1="0" y1="0" x2="1" y2="1">
|
|
6
|
-
<stop stop-color="#111512"/>
|
|
7
|
-
<stop offset="1" stop-color="#080a09"/>
|
|
8
|
-
</linearGradient>
|
|
9
|
-
<linearGradient id="glow" x1="0" y1="0" x2="1" y2="1">
|
|
10
|
-
<stop stop-color="#fc6404" stop-opacity=".28"/>
|
|
11
|
-
<stop offset="1" stop-color="#fc6404" stop-opacity="0"/>
|
|
12
|
-
</linearGradient>
|
|
13
|
-
<filter id="shadow" x="-30%" y="-30%" width="160%" height="160%">
|
|
14
|
-
<feDropShadow dx="0" dy="18" stdDeviation="24" flood-color="#000" flood-opacity=".45"/>
|
|
15
|
-
</filter>
|
|
16
|
-
<filter id="soft">
|
|
17
|
-
<feGaussianBlur stdDeviation="55"/>
|
|
18
|
-
</filter>
|
|
19
|
-
<pattern id="grid" width="32" height="32" patternUnits="userSpaceOnUse">
|
|
20
|
-
<path d="M32 0H0V32" fill="none" stroke="#fff" stroke-opacity=".035"/>
|
|
21
|
-
</pattern>
|
|
22
|
-
<marker id="arrow" markerWidth="10" markerHeight="10" refX="8" refY="5" orient="auto">
|
|
23
|
-
<path d="M0 0L10 5L0 10Z" fill="#5b625d"/>
|
|
24
|
-
</marker>
|
|
25
|
-
<style>
|
|
26
|
-
.ui{font-family:Inter,ui-sans-serif,system-ui,-apple-system,"Segoe UI",sans-serif}
|
|
27
|
-
.mono{font-family:"SFMono-Regular",Consolas,monospace}
|
|
28
|
-
.eyebrow{font-size:14px;font-weight:700;letter-spacing:2.4px;fill:#7f8881}
|
|
29
|
-
.node-title{font-size:22px;font-weight:700;fill:#f4f6f4}
|
|
30
|
-
.node-copy{font-size:14px;fill:#888f8a}
|
|
31
|
-
.tiny{font-size:12px;fill:#707873}
|
|
32
|
-
.flow{fill:none;stroke:#5b625d;stroke-width:3;marker-end:url(#arrow)}
|
|
33
|
-
</style>
|
|
34
|
-
</defs>
|
|
35
|
-
|
|
36
|
-
<rect width="1600" height="900" fill="url(#bg)"/>
|
|
37
|
-
<circle cx="1240" cy="70" r="330" fill="#fc6404" opacity=".12" filter="url(#soft)"/>
|
|
38
|
-
<circle cx="280" cy="880" r="260" fill="#fc6404" opacity=".08" filter="url(#soft)"/>
|
|
39
|
-
|
|
40
|
-
<g class="ui">
|
|
41
|
-
<text x="110" y="112" font-size="16" font-weight="800" letter-spacing="2" fill="#fcaa72">AI ENGINEERING LOOP</text>
|
|
42
|
-
<text x="110" y="188" font-size="64" font-weight="750" letter-spacing="-2.8" fill="#f7f9f7">From idea to trusted code.</text>
|
|
43
|
-
<text x="112" y="232" font-size="21" fill="#9da49f">Your AI handles the workflow. You keep the clarity and control.</text>
|
|
44
|
-
</g>
|
|
45
|
-
|
|
46
|
-
<g filter="url(#shadow)">
|
|
47
|
-
<rect x="105" y="290" width="1390" height="510" rx="24" fill="#151816" stroke="#303632"/>
|
|
48
|
-
<rect x="105" y="290" width="1390" height="64" rx="24" fill="#1b1f1c"/>
|
|
49
|
-
<path d="M105 330V354H1495V330" fill="#1b1f1c"/>
|
|
50
|
-
<circle cx="140" cy="322" r="6" fill="#4d544f"/>
|
|
51
|
-
<circle cx="160" cy="322" r="6" fill="#4d544f"/>
|
|
52
|
-
<circle cx="180" cy="322" r="6" fill="#fc6404"/>
|
|
53
|
-
<rect x="680" y="307" width="240" height="30" rx="15" fill="#111411"/>
|
|
54
|
-
<circle cx="704" cy="322" r="6" fill="#fc6404"/>
|
|
55
|
-
<text class="ui tiny" x="720" y="326">Workflow Studio</text>
|
|
56
|
-
|
|
57
|
-
<rect x="105" y="354" width="72" height="446" fill="#101311"/>
|
|
58
|
-
<rect x="123" y="381" width="36" height="36" rx="10" fill="#fc6404"/>
|
|
59
|
-
<path d="M129 400h6l3-8 5 16 3-8h6" fill="none" stroke="#fff" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round"/>
|
|
60
|
-
<circle cx="141" cy="449" r="15" fill="#252a26"/>
|
|
61
|
-
<path d="M134 444h14M134 449h14M134 454h9" stroke="#818982" stroke-width="2" stroke-linecap="round"/>
|
|
62
|
-
<circle cx="141" cy="500" r="15" fill="#252a26"/>
|
|
63
|
-
<circle cx="135" cy="505" r="3" fill="none" stroke="#818982" stroke-width="2"/>
|
|
64
|
-
<circle cx="147" cy="495" r="3" fill="none" stroke="#818982" stroke-width="2"/>
|
|
65
|
-
<path d="M137.5 502.5l7-5" stroke="#818982" stroke-width="2"/>
|
|
66
|
-
|
|
67
|
-
<rect x="177" y="354" width="1318" height="446" fill="#111411"/>
|
|
68
|
-
<rect x="177" y="354" width="1318" height="446" fill="url(#grid)"/>
|
|
69
|
-
<ellipse cx="1220" cy="410" rx="300" ry="210" fill="url(#glow)"/>
|
|
70
|
-
|
|
71
|
-
<text class="ui eyebrow" x="222" y="397">LIVE RUN / PRODUCT LAUNCH</text>
|
|
72
|
-
<text class="ui tiny" x="222" y="420">T1 · ASSISTED · iteration 1 / 3 · budget 38%</text>
|
|
73
|
-
<rect x="1180" y="375" width="262" height="42" rx="9" fill="#1d221e" stroke="#343a35"/>
|
|
74
|
-
<circle cx="1206" cy="396" r="6" fill="#fc6404"/>
|
|
75
|
-
<circle cx="1206" cy="396" r="11" fill="none" stroke="#fc6404" stroke-opacity=".35" stroke-width="2"/>
|
|
76
|
-
<text class="ui tiny" x="1224" y="400">live: watch · heartbeat 3s ago</text>
|
|
77
|
-
|
|
78
|
-
<rect x="222" y="444" width="1220" height="50" rx="12" fill="#1a2418" stroke="#2f5a22"/>
|
|
79
|
-
<rect x="222" y="444" width="6" height="50" rx="3" fill="#fcaa72"/>
|
|
80
|
-
<text class="ui" x="248" y="474" font-size="13" font-weight="800" letter-spacing="1.4" fill="#fcaa72">QUESTION</text>
|
|
81
|
-
<text class="ui" x="340" y="474" font-size="15" fill="#e4e8e5">Should an empty cart show the “Continue shopping” link?</text>
|
|
82
|
-
<rect x="1316" y="456" width="110" height="26" rx="7" fill="#1d221e" stroke="#3b6b2c"/>
|
|
83
|
-
<text class="ui" x="1371" y="474" text-anchor="middle" font-size="12" font-weight="750" fill="#c9f0bd">Answer</text>
|
|
84
|
-
|
|
85
|
-
<line x1="300" y1="560" x2="1365" y2="560" stroke="#343a35" stroke-width="4" stroke-linecap="round"/>
|
|
86
|
-
<line x1="300" y1="560" x2="939" y2="560" stroke="#fc6404" stroke-width="4" stroke-linecap="round"/>
|
|
87
|
-
<circle cx="300" cy="560" r="18" fill="#fc6404"/>
|
|
88
|
-
<path d="M293 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
89
|
-
<text class="ui" x="300" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">GOAL</text>
|
|
90
|
-
<circle cx="513" cy="560" r="18" fill="#fc6404"/>
|
|
91
|
-
<path d="M506 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
92
|
-
<text class="ui" x="513" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">MAKER</text>
|
|
93
|
-
<circle cx="726" cy="560" r="18" fill="#fc6404"/>
|
|
94
|
-
<path d="M719 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
95
|
-
<text class="ui" x="726" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">VERIFY</text>
|
|
96
|
-
<circle cx="939" cy="560" r="28" fill="#fc6404" opacity=".18"/>
|
|
97
|
-
<circle cx="939" cy="560" r="18" fill="#1c211d" stroke="#fc6404" stroke-width="4"/>
|
|
98
|
-
<circle cx="939" cy="560" r="6" fill="#fc6404"/>
|
|
99
|
-
<text class="ui" x="939" y="608" text-anchor="middle" font-size="13" font-weight="800" letter-spacing="1.6" fill="#f4f6f4">REVIEW</text>
|
|
100
|
-
<circle cx="1152" cy="560" r="18" fill="#1c211d" stroke="#3b433d" stroke-width="3"/>
|
|
101
|
-
<text class="ui" x="1152" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#707873">JUDGE</text>
|
|
102
|
-
<circle cx="1365" cy="560" r="18" fill="#1c211d" stroke="#3b433d" stroke-width="3"/>
|
|
103
|
-
<text class="ui" x="1365" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#707873">DELIVER</text>
|
|
104
|
-
<text class="ui tiny" x="939" y="628" text-anchor="middle" fill="#fcaa72">Devil's Advocate running</text>
|
|
105
|
-
|
|
106
|
-
<rect x="222" y="652" width="600" height="62" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
107
|
-
<text class="ui eyebrow" x="246" y="688" font-size="12">COMPLIANCE</text>
|
|
108
|
-
<rect x="384" y="667" width="134" height="32" rx="16" fill="#1c2a18" stroke="#2f5a22"/>
|
|
109
|
-
<circle cx="402" cy="683" r="5" fill="#fc6404"/>
|
|
110
|
-
<text class="ui" x="414" y="688" font-size="13" fill="#c9f0bd">Guard 0 blocks</text>
|
|
111
|
-
<rect x="526" y="667" width="120" height="32" rx="16" fill="#1c2a18" stroke="#2f5a22"/>
|
|
112
|
-
<circle cx="543" cy="683" r="5" fill="#fc6404"/>
|
|
113
|
-
<text class="ui" x="555" y="688" font-size="13" fill="#c9f0bd">Scope in map</text>
|
|
114
|
-
<rect x="654" y="667" width="148" height="32" rx="16" fill="#1d221e" stroke="#343a35"/>
|
|
115
|
-
<circle cx="671" cy="683" r="5" fill="#707873"/>
|
|
116
|
-
<text class="ui" x="683" y="688" font-size="13" fill="#9da49f">Receipt pending</text>
|
|
117
|
-
|
|
118
|
-
<rect x="842" y="652" width="600" height="62" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
119
|
-
<text class="ui eyebrow" x="866" y="688" font-size="12">TIMELINE</text>
|
|
120
|
-
<text class="mono tiny" x="966" y="677">10:42</text>
|
|
121
|
-
<text class="ui" x="1012" y="677" font-size="13" fill="#c7ccc8">verify · npm test · 511 passed</text>
|
|
122
|
-
<text class="mono tiny" x="966" y="700">10:44</text>
|
|
123
|
-
<text class="ui" x="1012" y="700" font-size="13" fill="#c7ccc8">review · 2 findings, 0 blocking</text>
|
|
124
|
-
|
|
125
|
-
<rect x="224" y="734" width="1218" height="44" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
126
|
-
<text class="mono tiny" x="248" y="761">Task</text>
|
|
127
|
-
<text class="ui" x="300" y="761" font-size="14" fill="#c7ccc8">Ship a reliable feature without babysitting every command</text>
|
|
128
|
-
<rect x="1250" y="743" width="174" height="26" rx="7" fill="#fc6404"/>
|
|
129
|
-
<text class="ui" x="1337" y="761" text-anchor="middle" font-size="12" font-weight="750" fill="#fff">Start with AI Agent</text>
|
|
130
|
-
</g>
|
|
131
|
-
|
|
132
|
-
<g class="ui">
|
|
133
|
-
<text x="112" y="852" font-size="15" fill="#6f7771">Live runs · compliance you can see · evidence you can trust</text>
|
|
134
|
-
<text x="1488" y="852" text-anchor="end" font-size="15" font-weight="700" fill="#fc6404">OPEN SOURCE</text>
|
|
135
|
-
</g>
|
|
136
|
-
</svg>
|
|
@@ -1,136 +0,0 @@
|
|
|
1
|
-
<svg xmlns="http://www.w3.org/2000/svg" width="1600" height="900" viewBox="0 0 1600 900" role="img" aria-labelledby="title desc">
|
|
2
|
-
<title id="title">AI Engineering Loop Workflow Studio</title>
|
|
3
|
-
<desc id="desc">A dark Workflow Studio live-run view: a stage rail from goal to deliver with review in progress, a pending question banner, compliance chips, a short timeline, and a Start with AI Agent button.</desc>
|
|
4
|
-
<defs>
|
|
5
|
-
<linearGradient id="bg" x1="0" y1="0" x2="1" y2="1">
|
|
6
|
-
<stop stop-color="#111512"/>
|
|
7
|
-
<stop offset="1" stop-color="#080a09"/>
|
|
8
|
-
</linearGradient>
|
|
9
|
-
<linearGradient id="glow" x1="0" y1="0" x2="1" y2="1">
|
|
10
|
-
<stop stop-color="#28ad00" stop-opacity=".28"/>
|
|
11
|
-
<stop offset="1" stop-color="#28ad00" stop-opacity="0"/>
|
|
12
|
-
</linearGradient>
|
|
13
|
-
<filter id="shadow" x="-30%" y="-30%" width="160%" height="160%">
|
|
14
|
-
<feDropShadow dx="0" dy="18" stdDeviation="24" flood-color="#000" flood-opacity=".45"/>
|
|
15
|
-
</filter>
|
|
16
|
-
<filter id="soft">
|
|
17
|
-
<feGaussianBlur stdDeviation="55"/>
|
|
18
|
-
</filter>
|
|
19
|
-
<pattern id="grid" width="32" height="32" patternUnits="userSpaceOnUse">
|
|
20
|
-
<path d="M32 0H0V32" fill="none" stroke="#fff" stroke-opacity=".035"/>
|
|
21
|
-
</pattern>
|
|
22
|
-
<marker id="arrow" markerWidth="10" markerHeight="10" refX="8" refY="5" orient="auto">
|
|
23
|
-
<path d="M0 0L10 5L0 10Z" fill="#5b625d"/>
|
|
24
|
-
</marker>
|
|
25
|
-
<style>
|
|
26
|
-
.ui{font-family:Inter,ui-sans-serif,system-ui,-apple-system,"Segoe UI",sans-serif}
|
|
27
|
-
.mono{font-family:"SFMono-Regular",Consolas,monospace}
|
|
28
|
-
.eyebrow{font-size:14px;font-weight:700;letter-spacing:2.4px;fill:#7f8881}
|
|
29
|
-
.node-title{font-size:22px;font-weight:700;fill:#f4f6f4}
|
|
30
|
-
.node-copy{font-size:14px;fill:#888f8a}
|
|
31
|
-
.tiny{font-size:12px;fill:#707873}
|
|
32
|
-
.flow{fill:none;stroke:#5b625d;stroke-width:3;marker-end:url(#arrow)}
|
|
33
|
-
</style>
|
|
34
|
-
</defs>
|
|
35
|
-
|
|
36
|
-
<rect width="1600" height="900" fill="url(#bg)"/>
|
|
37
|
-
<circle cx="1240" cy="70" r="330" fill="#28ad00" opacity=".12" filter="url(#soft)"/>
|
|
38
|
-
<circle cx="280" cy="880" r="260" fill="#28ad00" opacity=".08" filter="url(#soft)"/>
|
|
39
|
-
|
|
40
|
-
<g class="ui">
|
|
41
|
-
<text x="110" y="112" font-size="16" font-weight="800" letter-spacing="2" fill="#83db69">AI ENGINEERING LOOP</text>
|
|
42
|
-
<text x="110" y="188" font-size="64" font-weight="750" letter-spacing="-2.8" fill="#f7f9f7">From idea to trusted code.</text>
|
|
43
|
-
<text x="112" y="232" font-size="21" fill="#9da49f">Your AI handles the workflow. You keep the clarity and control.</text>
|
|
44
|
-
</g>
|
|
45
|
-
|
|
46
|
-
<g filter="url(#shadow)">
|
|
47
|
-
<rect x="105" y="290" width="1390" height="510" rx="24" fill="#151816" stroke="#303632"/>
|
|
48
|
-
<rect x="105" y="290" width="1390" height="64" rx="24" fill="#1b1f1c"/>
|
|
49
|
-
<path d="M105 330V354H1495V330" fill="#1b1f1c"/>
|
|
50
|
-
<circle cx="140" cy="322" r="6" fill="#4d544f"/>
|
|
51
|
-
<circle cx="160" cy="322" r="6" fill="#4d544f"/>
|
|
52
|
-
<circle cx="180" cy="322" r="6" fill="#28ad00"/>
|
|
53
|
-
<rect x="680" y="307" width="240" height="30" rx="15" fill="#111411"/>
|
|
54
|
-
<circle cx="704" cy="322" r="6" fill="#28ad00"/>
|
|
55
|
-
<text class="ui tiny" x="720" y="326">Workflow Studio</text>
|
|
56
|
-
|
|
57
|
-
<rect x="105" y="354" width="72" height="446" fill="#101311"/>
|
|
58
|
-
<rect x="123" y="381" width="36" height="36" rx="10" fill="#28ad00"/>
|
|
59
|
-
<path d="M129 400h6l3-8 5 16 3-8h6" fill="none" stroke="#fff" stroke-width="2.2" stroke-linecap="round" stroke-linejoin="round"/>
|
|
60
|
-
<circle cx="141" cy="449" r="15" fill="#252a26"/>
|
|
61
|
-
<path d="M134 444h14M134 449h14M134 454h9" stroke="#818982" stroke-width="2" stroke-linecap="round"/>
|
|
62
|
-
<circle cx="141" cy="500" r="15" fill="#252a26"/>
|
|
63
|
-
<circle cx="135" cy="505" r="3" fill="none" stroke="#818982" stroke-width="2"/>
|
|
64
|
-
<circle cx="147" cy="495" r="3" fill="none" stroke="#818982" stroke-width="2"/>
|
|
65
|
-
<path d="M137.5 502.5l7-5" stroke="#818982" stroke-width="2"/>
|
|
66
|
-
|
|
67
|
-
<rect x="177" y="354" width="1318" height="446" fill="#111411"/>
|
|
68
|
-
<rect x="177" y="354" width="1318" height="446" fill="url(#grid)"/>
|
|
69
|
-
<ellipse cx="1220" cy="410" rx="300" ry="210" fill="url(#glow)"/>
|
|
70
|
-
|
|
71
|
-
<text class="ui eyebrow" x="222" y="397">LIVE RUN / PRODUCT LAUNCH</text>
|
|
72
|
-
<text class="ui tiny" x="222" y="420">T1 · ASSISTED · iteration 1 / 3 · budget 38%</text>
|
|
73
|
-
<rect x="1180" y="375" width="262" height="42" rx="9" fill="#1d221e" stroke="#343a35"/>
|
|
74
|
-
<circle cx="1206" cy="396" r="6" fill="#28ad00"/>
|
|
75
|
-
<circle cx="1206" cy="396" r="11" fill="none" stroke="#28ad00" stroke-opacity=".35" stroke-width="2"/>
|
|
76
|
-
<text class="ui tiny" x="1224" y="400">live: watch · heartbeat 3s ago</text>
|
|
77
|
-
|
|
78
|
-
<rect x="222" y="444" width="1220" height="50" rx="12" fill="#1a2418" stroke="#2f5a22"/>
|
|
79
|
-
<rect x="222" y="444" width="6" height="50" rx="3" fill="#83db69"/>
|
|
80
|
-
<text class="ui" x="248" y="474" font-size="13" font-weight="800" letter-spacing="1.4" fill="#83db69">QUESTION</text>
|
|
81
|
-
<text class="ui" x="340" y="474" font-size="15" fill="#e4e8e5">Should an empty cart show the “Continue shopping” link?</text>
|
|
82
|
-
<rect x="1316" y="456" width="110" height="26" rx="7" fill="#1d221e" stroke="#3b6b2c"/>
|
|
83
|
-
<text class="ui" x="1371" y="474" text-anchor="middle" font-size="12" font-weight="750" fill="#c9f0bd">Answer</text>
|
|
84
|
-
|
|
85
|
-
<line x1="300" y1="560" x2="1365" y2="560" stroke="#343a35" stroke-width="4" stroke-linecap="round"/>
|
|
86
|
-
<line x1="300" y1="560" x2="939" y2="560" stroke="#28ad00" stroke-width="4" stroke-linecap="round"/>
|
|
87
|
-
<circle cx="300" cy="560" r="18" fill="#28ad00"/>
|
|
88
|
-
<path d="M293 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
89
|
-
<text class="ui" x="300" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">GOAL</text>
|
|
90
|
-
<circle cx="513" cy="560" r="18" fill="#28ad00"/>
|
|
91
|
-
<path d="M506 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
92
|
-
<text class="ui" x="513" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">MAKER</text>
|
|
93
|
-
<circle cx="726" cy="560" r="18" fill="#28ad00"/>
|
|
94
|
-
<path d="M719 560l5 5 10-11" fill="none" stroke="#fff" stroke-width="3.5" stroke-linecap="round" stroke-linejoin="round"/>
|
|
95
|
-
<text class="ui" x="726" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#c7ccc8">VERIFY</text>
|
|
96
|
-
<circle cx="939" cy="560" r="28" fill="#28ad00" opacity=".18"/>
|
|
97
|
-
<circle cx="939" cy="560" r="18" fill="#1c211d" stroke="#28ad00" stroke-width="4"/>
|
|
98
|
-
<circle cx="939" cy="560" r="6" fill="#28ad00"/>
|
|
99
|
-
<text class="ui" x="939" y="608" text-anchor="middle" font-size="13" font-weight="800" letter-spacing="1.6" fill="#f4f6f4">REVIEW</text>
|
|
100
|
-
<circle cx="1152" cy="560" r="18" fill="#1c211d" stroke="#3b433d" stroke-width="3"/>
|
|
101
|
-
<text class="ui" x="1152" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#707873">JUDGE</text>
|
|
102
|
-
<circle cx="1365" cy="560" r="18" fill="#1c211d" stroke="#3b433d" stroke-width="3"/>
|
|
103
|
-
<text class="ui" x="1365" y="608" text-anchor="middle" font-size="13" font-weight="700" letter-spacing="1.6" fill="#707873">DELIVER</text>
|
|
104
|
-
<text class="ui tiny" x="939" y="628" text-anchor="middle" fill="#83db69">Devil's Advocate running</text>
|
|
105
|
-
|
|
106
|
-
<rect x="222" y="652" width="600" height="62" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
107
|
-
<text class="ui eyebrow" x="246" y="688" font-size="12">COMPLIANCE</text>
|
|
108
|
-
<rect x="384" y="667" width="134" height="32" rx="16" fill="#1c2a18" stroke="#2f5a22"/>
|
|
109
|
-
<circle cx="402" cy="683" r="5" fill="#28ad00"/>
|
|
110
|
-
<text class="ui" x="414" y="688" font-size="13" fill="#c9f0bd">Guard 0 blocks</text>
|
|
111
|
-
<rect x="526" y="667" width="120" height="32" rx="16" fill="#1c2a18" stroke="#2f5a22"/>
|
|
112
|
-
<circle cx="543" cy="683" r="5" fill="#28ad00"/>
|
|
113
|
-
<text class="ui" x="555" y="688" font-size="13" fill="#c9f0bd">Scope in map</text>
|
|
114
|
-
<rect x="654" y="667" width="148" height="32" rx="16" fill="#1d221e" stroke="#343a35"/>
|
|
115
|
-
<circle cx="671" cy="683" r="5" fill="#707873"/>
|
|
116
|
-
<text class="ui" x="683" y="688" font-size="13" fill="#9da49f">Receipt pending</text>
|
|
117
|
-
|
|
118
|
-
<rect x="842" y="652" width="600" height="62" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
119
|
-
<text class="ui eyebrow" x="866" y="688" font-size="12">TIMELINE</text>
|
|
120
|
-
<text class="mono tiny" x="966" y="677">10:42</text>
|
|
121
|
-
<text class="ui" x="1012" y="677" font-size="13" fill="#c7ccc8">verify · npm test · 511 passed</text>
|
|
122
|
-
<text class="mono tiny" x="966" y="700">10:44</text>
|
|
123
|
-
<text class="ui" x="1012" y="700" font-size="13" fill="#c7ccc8">review · 2 findings, 0 blocking</text>
|
|
124
|
-
|
|
125
|
-
<rect x="224" y="734" width="1218" height="44" rx="12" fill="#191d1a" stroke="#2b312c"/>
|
|
126
|
-
<text class="mono tiny" x="248" y="761">Task</text>
|
|
127
|
-
<text class="ui" x="300" y="761" font-size="14" fill="#c7ccc8">Ship a reliable feature without babysitting every command</text>
|
|
128
|
-
<rect x="1250" y="743" width="174" height="26" rx="7" fill="#28ad00"/>
|
|
129
|
-
<text class="ui" x="1337" y="761" text-anchor="middle" font-size="12" font-weight="750" fill="#fff">Start with AI Agent</text>
|
|
130
|
-
</g>
|
|
131
|
-
|
|
132
|
-
<g class="ui">
|
|
133
|
-
<text x="112" y="852" font-size="15" fill="#6f7771">Live runs · compliance you can see · evidence you can trust</text>
|
|
134
|
-
<text x="1488" y="852" text-anchor="end" font-size="15" font-weight="700" fill="#28ad00">OPEN SOURCE</text>
|
|
135
|
-
</g>
|
|
136
|
-
</svg>
|