Teach AI agents proven frameworks instead of writing long instructions
EXM7777 · x · 2026-10-14
The author shares a key practice with Hermes, Grok Bot and ChatGPT: instead of spending hours describing how an agent should work, hand it proven frameworks and methodologies. One bot is dedicated to planning and coding using Compound Engineering skills with Claude Code; another uses Karpathy's LLM Wiki concept to research topics and build a knowledge base. He argues this is the fastest way to get agents working, and working well.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23