docs(tac): add codex product-work guidance

Capture the Codex product-work interview in TAC loop-engineering guidance. Preserve PRD/spec discipline, prototypes, human taste/systems review, receipt-gated background agents, and explicit ownership even when implementation gets cheaper.
This commit is contained in:
artale 2026-06-29 12:52:15 +02:00
parent 4f7ae7ffe1
commit becd314b8f
2 changed files with 15 additions and 0 deletions

View File

@ -23,6 +23,9 @@ def test_loop_engineering_meta_prompt_locks_safety_fields():
"Team manages agents", "Team manages agents",
"vault/proxy credential injection", "vault/proxy credential injection",
"YouTube `hLUGXO5DSpo`", "YouTube `hLUGXO5DSpo`",
"Product work with coding agents",
"human taste and systems thinking",
"YouTube `P3KDebPTUrw`",
"External research anchors", "External research anchors",
"NVIDIA Secure Agent Workspace", "NVIDIA Secure Agent Workspace",
"Infisical Agent Vault", "Infisical Agent Vault",

View File

@ -85,6 +85,18 @@ Every autonomous work-agent plan must include:
Reference: Latent Space, "The Blueprint for Autonomous Work Agents" with Gavriel Cohen / NanoClaw (YouTube `hLUGXO5DSpo`). Reference: Latent Space, "The Blueprint for Autonomous Work Agents" with Gavriel Cohen / NanoClaw (YouTube `hLUGXO5DSpo`).
## Product work with coding agents note
When implementation gets cheap, do not delete product discipline. Plans should use prototypes to explore, but still preserve the product loop:
- PRD/spec captures why, users, constraints, and success criteria;
- prototype makes options concrete and testable;
- human taste and systems thinking review whether the result fits the whole product;
- scheduled/background agents may gather context, but promotion still needs receipts and review;
- role boundaries can flex, but ownership, decision rights, and phase state must stay explicit.
Reference: Lenny's Podcast, "OpenAI Codex lead on the new shape of product work" with Andrew Ambrosino (YouTube `P3KDebPTUrw`).
## External research anchors ## External research anchors
Ground agent plans against external production guidance, not just video notes: Ground agent plans against external production guidance, not just video notes: