Note on GitHub - Humanlayer/12-Factor-Agents: What Are the Principles We Can Use to Build LLM-powered Software That Is Actually Good Enough to Put in the Hands of Production Customers? via GitHub
Even if LLMs continue to get exponentially more powerful, there will be core engineering techniques that make LLM-powered software more reliable, more scalable, and easier to maintain.
• How We Got Here: A Brief History of Software • Factor 1: Natural Language to Tool Calls • Factor 2: Own your prompts • Factor 3: Own your context window • Factor 4: Tools are just structured outputs • Factor 5: Unify execution state and business state • Factor 6: Launch/Pause/Resume with simple APIs • Factor 7: Contact humans with tool calls • Factor 8: Own your control flow • Factor 9: Compact Errors into Context Window • Factor 10: Small, Focused Agents • Factor 11: Trigger from anywhere, meet users where they are • Factor 12: Make your agent a stateless reducer
Reference
- Notes
- llm, system-design
- GitHub - Humanlayer/12-Factor-Agents: What Are the Principles We Can Use to Build LLM-powered Software That Is Actually Good Enough to Put in the Hands of Production Customers?
-
Permalink to
2025.NTE.061
- Edit
← Previous | Next → |
Note on The Checklist Manifesto via Atul Gawande | Note on Is “Specification Repair” the AI Endgame? via Paul Ford |