From d6fba4953688ea5df3a667ddac717715aa62c999 Mon Sep 17 00:00:00 2001 From: artale Date: Mon, 29 Jun 2026 13:30:14 +0200 Subject: [PATCH] docs(tac): tighten product artifact stage gates Deepen the Codex product-work guidance with explicit artifact stages, production-readiness receipts, model-timing assumptions, and a deletion/simplification review criterion so cheap implementation does not create ungoverned prototype slop. --- pipeline/test_loop_engineering_meta_prompt.py | 4 ++++ plans/meta-prompts/loop_engineering.md | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/pipeline/test_loop_engineering_meta_prompt.py b/pipeline/test_loop_engineering_meta_prompt.py index fb86286..96d8d03 100644 --- a/pipeline/test_loop_engineering_meta_prompt.py +++ b/pipeline/test_loop_engineering_meta_prompt.py @@ -24,7 +24,11 @@ def test_loop_engineering_meta_prompt_locks_safety_fields(): "vault/proxy credential injection", "YouTube `hLUGXO5DSpo`", "Product work with coding agents", + "artifact declares its stage", + "production-looking prototypes must not imply production readiness", "human taste and systems thinking", + "model-timing assumptions", + "deletion/simplification", "YouTube `P3KDebPTUrw`", "External research anchors", "NVIDIA Secure Agent Workspace", diff --git a/plans/meta-prompts/loop_engineering.md b/plans/meta-prompts/loop_engineering.md index eaf4901..e64eb82 100644 --- a/plans/meta-prompts/loop_engineering.md +++ b/plans/meta-prompts/loop_engineering.md @@ -91,9 +91,13 @@ When implementation gets cheap, do not delete product discipline. Plans should u - PRD/spec captures why, users, constraints, and success criteria; - prototype makes options concrete and testable; +- every artifact declares its stage: exploration, prototype, beta, or ship candidate; +- production-looking prototypes must not imply production readiness without receipts; - 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. +- role boundaries can flex, but ownership, decision rights, and phase state must stay explicit; +- model-timing assumptions are explicit: some artifacts are kept to retest when model capability changes; +- complexity budget is tracked because autonomous loops tend to add code; deletion/simplification is a first-class review criterion. Reference: Lenny's Podcast, "OpenAI Codex lead on the new shape of product work" with Andrew Ambrosino (YouTube `P3KDebPTUrw`).