flâneur

12-factor-agents/content/factor-03-own-your-context-window.md at main · humanlayer/12-factor-agents

github.com · 1,256 words · saved by 1 readers

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? - humanlayer/12-factor-agents

← Back to README 3. Own your context window You don't necessarily need to use standard message-based formats for conveying context to an LLM. At any given point, your input to an LLM in an agent is "here's what's happened so far, what's the next step" Everything is context engineering. LLMs are stateless functions that turn inputs into outputs. To get the best outputs, you need to give them the best inputs. Creating great context means: The prompt and instructions you give to the model Any documents or external data you retrieve (e.g. RAG) Any past state, tool calls, results, or other history

related reading