name	ai-pipeline
description	AI feature engineering — llama, embeddings, RAG quality, inference reliability, cost/token discipline.
when_to_use	Model wiring, prompt boundaries, retrieval quality, embedding dims, inference failures, routing.

AI pipeline

Role

AI Engineer Lead uses this skill when changing how the product thinks (models, RAG, prompts), not just UI.

Load

Current stack from [ENGINEERING_REPO]/CLAUDE.md / agents/core/engineering-orchestrator.md (version state)
Prior long-form playbooks may exist in a bound source org repo; this pack relies on engineering-ai-engineer-lead.md + ai-pipeline instead of _archive/ paths.

Checklist

Grounding — RAG answers traceable to corpus; no fabricated OEM specifics
Embeddings — dimension and model match Qdrant config and ingest
Failure modes — timeouts, empty retrieval, model down — user-visible behavior defined
Cost / tokens — reasonable defaults; circuit breakers if applicable
Deferred inference migration — llama.cpp → vLLM is roadmap; do not silently change production path without explicit decision

Stop conditions

External capability claims → security-compliance-evidence + HQ claims matrix

Cursor

Subagents may probe prompts/tests; Mike integrates and validates against evidence.

Más de este repositorio

mismo repositorio

architecture-and-docs

MYBENAI-LLC/benai-agent-method

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

2026-04-242

backend-rag-integration

MYBENAI-LLC/benai-agent-method

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

2026-04-242

benai-code-sections

MYBENAI-LLC/benai-agent-method

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.

2026-04-242

data-and-ingest

MYBENAI-LLC/benai-agent-method

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

2026-04-242

decision-ledger-hygiene

MYBENAI-LLC/benai-agent-method

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

2026-04-242

frontend-implementation

MYBENAI-LLC/benai-agent-method

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

2026-04-242

name	ai-pipeline
description	AI feature engineering — llama, embeddings, RAG quality, inference reliability, cost/token discipline.
when_to_use	Model wiring, prompt boundaries, retrieval quality, embedding dims, inference failures, routing.

AI pipeline

Role

AI Engineer Lead uses this skill when changing how the product thinks (models, RAG, prompts), not just UI.

Load

Current stack from [ENGINEERING_REPO]/CLAUDE.md / agents/core/engineering-orchestrator.md (version state)
Prior long-form playbooks may exist in a bound source org repo; this pack relies on engineering-ai-engineer-lead.md + ai-pipeline instead of _archive/ paths.

Checklist

Grounding — RAG answers traceable to corpus; no fabricated OEM specifics
Embeddings — dimension and model match Qdrant config and ingest
Failure modes — timeouts, empty retrieval, model down — user-visible behavior defined
Cost / tokens — reasonable defaults; circuit breakers if applicable
Deferred inference migration — llama.cpp → vLLM is roadmap; do not silently change production path without explicit decision

Stop conditions

External capability claims → security-compliance-evidence + HQ claims matrix

Cursor

Subagents may probe prompts/tests; Mike integrates and validates against evidence.