[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![aiDotEngineer Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1376308155626360837.png) AI Engineer [@aiDotEngineer](/creator/twitter/aiDotEngineer) on x 27.9K followers
Created: 2025-07-03 20:53:08 UTC

Want to learn more about Context Engineering? Start here.

🆕 12-factor Agents: Patterns of reliable LLM applications



next featured talk on our Agent Reliability track is the fan favorite manifesto by @dexhorthy, who, among many other things, coined Context Engineering!

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.  

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

![](https://pbs.twimg.com/card_img/1940883259925450759/Ib0fMbrL?format=jpg&name=800x320_1)

XXXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1940876485939564586/c:line.svg)

**Related Topics**
[llm](/topic/llm)
[context engineering](/topic/context-engineering)
[coins ai](/topic/coins-ai)

[Post Link](https://x.com/aiDotEngineer/status/1940876485939564586)