benai-agent-method

AI feature engineering — llama, embeddings, RAG quality, inference reliability, cost/token discipline.

System architecture, structured code review bar, and technical documentation.

Backend HTTP API, SQLite, Qdrant, integration contracts, schema and migration safety.

Maturity / inspection pass over [ORG_NAME] code sections (BCS). Load your org’s code-sections ledger, run verify ladder, update shared_context summary on main when columns change.

Data pipelines, ingest, remediation, entity quality — PDF/docs through to vector store.

Decision continuity, handoffs, supersession — Engineering Orchestrator (Mike) accountable; pair with session-notes.

Production frontend work — React 19, TypeScript, Vite, PrimeReact, [ORG_NAME] apps (client, system-console, dashboard).

Use when running or documenting a quality gate check for a release milestone. Covers gate criteria verification, evidence collection, and reporting.

Test and verify the [ORG_NAME] document ingestion pipeline. Use when ingesting files, testing the watcher, verifying Qdrant/SQLite data, running recall accuracy tests, or when the user mentions ingestion, pipeline testing, or dropping files.

Use before marking any backend, frontend, or ingestion feature as "complete." Checks the change against the Legacy Capability Audit to prevent regression.

Scope slicing, acceptance criteria, onboarding and adoption-oriented product decisions.

Use when implementing or refactoring Python in [ORG_NAME] product code or repo scripts: CLI design (argparse/Typer), exit codes, logging, pathlib, typing, pytest, and Ruff/Mypy per pyproject.toml.

Deterministic testing, regression discipline, API and a11y/perf checks — pair with gate-check for milestones.

CI/CD, operations, incidents, git/PR hygiene, rollback and observability posture.

Security, compliance, and claim-to-evidence integrity for releases and external-facing artifacts.

Use when writing or updating Engineering session notes. Covers the format, what to include, and filing location.

Defining measurable outcomes tied to evidence artifacts. Use when writing agent specs, closing waves, authoring handoffs, running release gates, or making any "done" claim.

Triage in-app tester feedback (thumbs / telemetry) and optional local logs. Diagnose bad responses through your product’s chat/RAG pipeline, apply minimal fixes, verify. Use when the user mentions feedback, flagged responses, tester issues, or bad answers.

UX, UI systems, and product-surface quality for [ORG_NAME] web apps — IA, states, design tokens, accessibility baseline.

Create a formal XD- handoff file between HQ and Engineering. Covers packet shape selection, YAML schema, filing, and memory log requirements.

Process new files in the founder's inbox ([YOUR_PLANS_DIR]/_inbox/). Covers triage, routing, and logging.

Log a decision, risk, milestone, blocker, or idea to the HQ business memory log. Covers entry schema, ID format, and filing rules.

John's first-contact skill. Drives the iterative new-adopter interview, creates ONBOARDING.md, proposes Wave 2 agents, and calibrates the startup sequence to the user's actual org size. Also governs session 2-3 refinement and ongoing roster pruning.

Use when writing or reviewing Python (scripts, services, tests): stdlib CLI patterns, logging, typing, Ruff/Mypy alignment, and safe defaults. Use for cross-org guidance; Engineering owns product code patterns in [PRODUCT_CODE_ROOT]/.

Convene a multi-agent roundtable to discuss and decide on a topic. Covers attendee selection, chair norms, minutes format, decision logging, and filing.

Run the [ORG_NAME] roundtable tech intelligence brief — web/search, stack filter, RTI- memory append, and optional brief-led micro-roundtable routing. HQ Chief of Staff-owned; not a separate agent role.