From e3bc60b0c92de8b83782e1f912eed30a8c982279 Mon Sep 17 00:00:00 2001 From: artale Date: Tue, 7 Jul 2026 15:27:23 +0200 Subject: [PATCH] docs(tac): add Kelsey Hightower software factory critique Folds Kelsey's observation that AI 'software factories' are a remix of existing SDLC (CI/CD, compilers, gRPC, low-code) with added token costs. Ties to MVI principle: does the AI add new capability, or just burn tokens on work that commodity hardware already handles? --- plans/meta-prompts/loop_engineering.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/plans/meta-prompts/loop_engineering.md b/plans/meta-prompts/loop_engineering.md index b1d675a..b72fff8 100644 --- a/plans/meta-prompts/loop_engineering.md +++ b/plans/meta-prompts/loop_engineering.md @@ -280,3 +280,17 @@ Reference: NVIDIA ComputeX 2026 keynote — Adel (Senior Director AI Agents) and **ServiceNow case study:** 90% of L1 tickets resolved by autonomous agents using AIQ blueprint. System of models (frontier for orchestration, open for specialist researchers) with human-in-the-loop for escalation. **Practical takeaway:** TAC already aligns with the system-of-models pattern (see Model routing appendix). The next step is OpenShell-style policy gating around the Hermes/OpenClaw agents in the factory — sandbox the agents that have access to internal data sources (email, forgejo, git-proxy deploy) and keep human approval on policy changes. + +## Kelsey Hightower on AI software factories + +Reference: Kelsey Hightower LinkedIn, July 2026. + +**Core observation:** AI-powered "software factories" are a remix of the existing SDLC — CI/CD pipelines, gRPC definitions, compilers, libraries, frameworks, and low-code platforms already automate the mechanical parts of software delivery. A mature team with a dialed-in pipeline already has a software factory that lets developers focus on high-level logic. + +**The MVI question for agentic factories:** does the AI agent add a *new capability* that CI/CD + compilers + low-code cannot deliver? Or is it just a more expensive (token-burning) way to do the same work — especially for parts of the process that are easily reproducible and could run on commodity hardware? + +**Implications for TAC:** +- The token-cost question reinforces the Model routing appendix: route mechanical/reproducible work to cheap models or bare CI/CD pipelines, reserve frontier models for planning, design, and novel problem-solving. +- The RSI loop (cron + skill_health.py + deploy-webhook + git-proxy) already follows this pattern: the deterministic monitoring runs on commodity hardware (cron, Python), while the planning/review layer uses AI. +- Kelsey's framing aligns with the Platform Engineer skill's MVI principle: "What happens if we don't add this?" Every agent in the factory should earn its token cost vs a deterministic alternative. +- The factory inventory's 25 containers include deterministic infrastructure (prometheus, grafana, forgejo, redis) alongside AI-driven agents — the split between commodity SDLC and AI augmentation is already in place.