artale
/
agentic-ai-engineering
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs(tac): add open model harness guidance 

Capture the GLM 5.2 harness video in the loop-engineering meta-prompt. Require portable context, report/review phases, quality gates, and model/cost notes so TAC plans can run on lower-cost or open-source models without relying on frontier-model taste.
This commit is contained in:
artale 2026-06-29 12:17:36 +02:00
parent 432282f186
commit 05377c84e3
2 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
pipeline/test_loop_engineering_meta_prompt.py
View File

@ -16,6 +16,9 @@ def test_loop_engineering_meta_prompt_locks_safety_fields():
"end-loop guardrails",
"latency, token use",
"YouTube `GrNbuWWJYiI`",
"Open-source model portability",
"quality gate checklist",
"YouTube `dJI2GRG1GEE`",
"Model Workspace Protocol",
"00-intake/",
"40-ship/",

16
plans/meta-prompts/loop_engineering.md
View File

@ -50,6 +50,22 @@ LLMOps/hill-climbing only promotes a changed prompt, retrieval config, tool conf
Reference: Sean's AI Stories, "You Can Learn AI Agent Harness & Loop Engineering In 19 Min" (YouTube `GrNbuWWJYiI`).
## Open-source model portability note
A strong harness should make the task portable across model tiers, including open-source or lower-cost models. Plans must spell out enough context, phases, and quality gates that a non-frontier model can follow the work without relying on hidden taste.
For outbound/productized work, require:
- explicit prospect/input target;
- crawler or source gathering step;
- report generation step;
- cover letter or executive summary when the output is meant to sell or persuade;
- design/report review phase;
- quality gate checklist that loops back to the builder when review fails;
- model/cost notes when choosing GLM/open-source/local models over frontier models.
Reference: Jordan Urbs, "GLM 5.2 Proves Open Source AI Can Match Fable 5 (AI Harness Engineering)" (YouTube `dJI2GRG1GEE`).
## Model Workspace Protocol note
For sequential workflows with human review between stages, prefer folder-structured orchestration before multi-agent framework code. The Model Workspace Protocol pattern treats numbered folders as stages, markdown files as role/context carriers, and local scripts as the boring mechanical layer.