Practical Agentic Engineering: Assigning Multiple AI Models by Role
brandon_galang · x · 2026-08-09
The author shares a practical mental model for agentic engineering: using different models for specific "roles" and upgrading them as new models release.
His current setup defines six core roles:
- Fast & in the loop (chatting): glm 5.2 high fast.
- Fast & in the loop (coding): grok 4.5 medium fast.
- In the loop, planning (precise): gpt 5.6 sol medium.
- In the loop, planning (ambiguous): fable 5 low.
- Sub-agent (codebase search): gpt 5.6 luna high.
- Coding (async): opus 5 medium.
More from coding & agent
- Open Source: Explore Claude Code Project Structure via Interactive Simulation — tom_doerr · 2026-08-09
- Filesystem as Memory: Paper Proposes Agent Architecture Halving Retrieval Costs — BLUECOW009 · 2026-08-09
- Hermes Agent Desktop Introduces HUD Mode: AI as an App Overlay Layer — Teknium · 2026-08-09
- DeepSeek-V3-Flash excels in overnight autonomous coding tasks — teortaxesTex · 2026-08-09
- Grapevine: Open-Source Plugin for Contextual Awareness Across Claude Code Sessions — daniel_mac8 · 2026-08-09
- AI Agent Refuses to Share Memory: Dev Faces Multi-Agent Orchestration Fail — alexcovo_eth · 2026-08-09