agentic-ai-engineering/plans
artale 55d6cd5333 docs(tac): add Memory vs Taste architecture pattern
Folds the Memory vs Taste concept into loop_engineering.md. Memory
is raw storage/retrieval (vector DB, full histories). Taste is
higher-order judgment (significance extraction, preferences, lessons).
Applied to TAC: skill_health.py as the bridge, deploy policy as taste,
25 containers + qdrant as memory.
2026-07-09 06:48:08 +02:00
..
meta-prompts docs(tac): add Memory vs Taste architecture pattern 2026-07-09 06:48:08 +02:00
schema feat(tac): add product factory loop hardening 2026-06-29 11:56:54 +02:00
templates feat(tac): add product factory loop hardening 2026-06-29 11:56:54 +02:00
README.md feat(tac): add product factory loop hardening 2026-06-29 11:56:54 +02:00

README.md

Plans

Living Plan F3 artifacts for Product Factory builds.

Plans are durable engineering artifacts consumed by humans, teams, and agents.

Required files per product:

plans/<product_id>/plan.md
plans/<product_id>/plan.html

Rules:

  • include frontmatter with product_id, purpose, and references
  • include required sections: purpose, problem, solution, files, phases, validation, references, notes
  • updates append ## Amendment <UTC timestamp> blocks
  • deploy remains guarded through git-proxy:8099/deploy