← back
The Eyes Are The (Context) Window to The Soul: How Windsurf Gets to Know You — Sam Fertig, Windsurf
Takeaway
Coding agents that 'know you' rely on heuristics (user behavior) + hard evidence (codebase) plus relevance-first context retrieval — not bigger windows.
Summary
- Sam Fertig (Windsurf forward-deployed engineer) argues code generation is easy; generating code *for you* (your codebase, style, conventions) requires context, not bigger windows.
- Two context buckets: heuristics/user-state (code above/below cursor, open files, clipboard, terminal, what you're trying to do) and hard evidence/codebase-state (code, docs, rules, agent memories).
- Magic formula: relevant_output = prompt + codebase_state + user_state.
- Windsurf focuses on *what* context (relevance) not just *how much* (window size) — better than naively cramming, also helps latency.
- Stack of context tools: embedding search, memories, rules, custom workspaces, @-mentions, plain-text search, knowledge base, multimodal input, riptide, MCP, remote indexing, reranking, AST parsing — Exafunction GPU-optimization heritage.
windsurfcontext-engineeringcoding-agents
Original description
Sometimes it seems like Windsurf knows you a little too well. It's one thing to generate generic code, but to predict your next intent? From matching existing code patterns and styles to tracking how local changes affect the larger codebase, this talk digs into the technical challenges of context awareness and why simply indexing code falls short. Relive our journey tackling the core issue in the AI IDE space : balancing retrieval quality with latency constraints and scaling effectively as codebases grow. For those curious about the infrastructure behind context-aware AI, this talk offers insights into our approach of turning massive codebases into collections of useful context. About Sam Fertig Sam Fertig is a Deployed Engineer at Windsurf, where he helps deliver cutting-edge software solutions in complex operational environments. Prior to Windsurf, he worked at C3 AI, gaining experience at the intersection of data, engineering, and enterprise AI. Sam holds a degree in Computer Science and Politics from Oberlin College. Outside of work, he’s passionate about MMA and Jiu Jitsu, and enjoys playing guitar in his free time. Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter