Context Engineering - Making Every Token Count

Slides from my talk at O'Reilly AI CodeCon

Transcript

1. CONTEXT ENGINEERING ADDY OSMANI MAKING EVERY TOKEN COUNT
2. Based on illustration by dexhorthy
3. WHAT ARE TOKENS? https://platform.openai.com/tokenizer
4. WHAT’S A CONTEXT WINDOW?
5. CONTEXT WINDOWS ARE LIKE LIMITED RAM Curation of what fi ts into RAM is analogous to “context engineering” ANALOGY
6. PROMPT ENGINEERING Clear instructions for models so they can accomplish a task https://www.youtube.com/watch?v=ysPbXH0LpIE PRELUDE
7. PROMPT ENGINEERING FAILURES STEM FROM CONTEXT MISMANAGEMENT https://www.instagram.com/p/DMc4ujyTuk6/?img_index=6
8. CONTEXT ENGINEERING MEANS PROVIDING AN AI WITH ALL THE INFORMATION AND TOOLS IT NEEDS TO SUCCESSFULLY COMPLETE A TASK – NOT JUST A CLEVERLY WORDED PROMPT. DEFINITION
9. ADD CONTEXT CONTEXT WINDOW USE CONTEXT IN EDITORS & IDES
10. https://www.youtube.com/watch?v=ysPbXH0LpIE
11. https://context.addy.ie
22. GOOD CONTEXT IS HARD. PROBLEM
23. AI CODING PERFORMANCE OFTEN DIPS WHEN CONTEXT WINDOWS EXCEED ~50% FULLNESS PROBLEM
24. TOO LITTLE CONTEXT: VAGUE OR HALLUCINATED RESPONSES. TOO MUCH CONTEXT: DISTRACTED, UNABLE TO FIND RELEVANT INFO, OVER-INDEXING ON PATTERNS. BAD CONTEXT: POISONING, TRUSTING INCORRECT STATEMENTS OVER TRAINING.
25. TOO LITTLE CONTEXT: VAGUE OR HALLUCINATED RESPONSES. TOO MUCH CONTEXT: DISTRACTED, UNABLE TO FIND RELEVANT INFO, OVER-INDEXING ON PATTERNS. BAD CONTEXT: POISONING, TRUSTING INCORRECT STATEMENTS OVER TRAINING.
26. TOO LITTLE CONTEXT: VAGUE OR HALLUCINATED RESPONSES. TOO MUCH CONTEXT: DISTRACTED, UNABLE TO FIND RELEVANT INFO, OVER-INDEXING ON PATTERNS. BAD CONTEXT: POISONING, TRUSTING INCORRECT STATEMENTS OVER TRAINING.
27. PATTERNS FOR CONTEXT MANAGEMENT https://blog.langchain.com/context-engineering-for-agents/
28. AUTOMATIC CONTEXT OPTIMIZATION CURSOR CLINE
29. HOW TO FIX YOUR CONTEXT https://www.dbreunig.com/2025/06/26/how-to- fi x-your-context.html
31. •Be precise: Vague requests lead to vague answers. The more specific you are, the better your results will be. •Provide relevant code: Share the specific files, folders, or code snippets that are central to your request. •Include design documents: Paste or attach sections from relevant design docs to give the AI the bigger picture. •Share full error logs: For debugging, always provide the complete error message and any relevant logs or stack traces. •Show database schemas: When working with databases, a screenshot of the schema helps the AI generate accurate code for data interaction. •Use PR feedback: Comments from a pull request make for context-rich prompts. •Give examples: Show an example of what you want the final output to look like. •State your constraints: Clearly list any requirements, such as libraries to use, patterns to follow, or things to avoid. CONTEXT ENGINEERING FOR AI CODERS
32. CONTEXT IT’S NOT THE PROMPT, IT’S THE ADDYOSMANI.COM