History

Natalie 20d52431bc Some checks failed CI/CD / verify (push) Failing after 2s Details CI/CD / deploy (push) Has been skipped Details docs(deploy): edge basic_auth + token injection resolved; open = https registry, ssh, wg1 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>		2026-07-01 07:51:32 -04:00
..
ai-first-v4.md	docs(prospector): retire model-boss for @prospector/ai-harness; add DRAFT mode + alignment gate	2026-06-30 11:06:30 -04:00
ai-orchestrator.md	feat(mcp-orchestrator): scaffold AI streaming orchestrator MCP + design doc	2026-06-30 10:23:52 -04:00
ai-system-plan.md	docs: update PLAN + AI docs for the data→model lane (LoRA, e2e, infra-tools)	2026-07-01 07:37:06 -04:00
classifier-serving.md	feat(eval): gpu.py serve-classifier + classifier-serving integration contract	2026-06-30 17:12:22 -04:00
control-modes.md	docs(prospector): retire model-boss for @prospector/ai-harness; add DRAFT mode + alignment gate	2026-06-30 11:06:30 -04:00
deploy.md	docs(deploy): edge basic_auth + token injection resolved; open = https registry, ssh, wg1	2026-07-01 07:51:32 -04:00
draft-engine.md	docs(prospector): retire model-boss for @prospector/ai-harness; add DRAFT mode + alignment gate	2026-06-30 11:06:30 -04:00
gpu-cost-control.md	docs(prospector): split AI roles into orchestrator vs pipeline	2026-06-29 16:20:21 -04:00
mcp.md	docs: README + package.json reflect the implemented web/ operator PWA	2026-06-29 07:58:45 -04:00
model-eval-pipeline.md	docs(prospector): retire model-boss for @prospector/ai-harness; add DRAFT mode + alignment gate	2026-06-30 11:06:30 -04:00
README.md	docs(prospector): retire model-boss for @prospector/ai-harness; add DRAFT mode + alignment gate	2026-06-30 11:06:30 -04:00
training-loop.md	docs(prospector): fix unverified claims found by the doc-review workflow	2026-06-30 11:14:54 -04:00

README.md

Feature documentation — grouped by feature

Per-feature docs for prospector, grouped by area. Start with ../PROSPECTOR.md (the unified definition) and ai-system-plan.md (the AI master plan); everything below drills down.

🤖 AI system & control surface

The v4 "AI-first" effort — making the app operable by an LLM agent.

Doc	What it covers
`ai-system-plan.md`	Master plan. Layered architecture (trained-stable vs mission-volatile), the model facts (size/storage/GPU-vs-CPU/accuracy), UI/UX gaps, tuning levers. Read this first for the AI system.
`ai-first-v4.md`	The three control planes (operation/observation/autonomy) + the AI-roles taxonomy (orchestrator vs classifier vs message-generator).
`ai-orchestrator.md`	The streaming agent (`@packages/mcp-orchestrator/`) that watches the system, reports, and nudges the operator.

✍️ The engine (classify → generate)

How an inbound becomes a reply.

Doc	What it covers
`draft-engine.md`	OSS-on-GPU draft engine (the `@prospector/ai-harness` inference layer) + the CoT workflow builder; the `template` vs `do-gpu-<model>_<build>` engine selection; the runtime per-draft alignment gate + facts/mission config.
`control-modes.md`	The runner modes GO / PAUSE / AWAY + the new DRAFT trust-ramp mode (stage-for-review) and the DRAFT→GO graduation criteria.

🎓 Training & evaluation

Turning Quinn's message history into a tuned, hardened model.

Doc	What it covers
`training-loop.md`	CoT-labeled corpus → LoRA → eval-gated build flip; the matcher+generator hybrid; the move taxonomy.
`model-eval-pipeline.md`	The Claude-advisor / OSS-worker bake-off; per-role scoring; the candidate roster.
`../../tooling/eval/README.md`	The runnable pipeline — extract → sweep → rationalize → run → score, plus `gpu.py`. (Code, not just design.)

💻 GPU, cost & ops

Doc	What it covers
`gpu-cost-control.md`	Presence-driven warm-up, live cost meter, pause/teardown.
`../../tooling/eval/README.md`	`gpu.py` — on-demand provisioning with the self-reaping auto-teardown (no secret on the droplet).
`deploy.md`	Prod backend deploy on the DO droplet.

🔌 Interfaces

Doc	What it covers
`mcp.md`	The `@packages/mcp-prospector` agent interface (one MCP tool per REST endpoint).
`ai-orchestrator.md`	The proactive streaming orchestrator (see AI system above).