AI engineer at Evertune
Notes on making language models hold up in production.
I'm Said Yaka. I write about retrieval, evaluations, agent interfaces, and the unglamorous work of shipping LLM systems people can trust.
Recent writing
All postsEnd the Meeting With a Decision
A design review that ends with "let's sync again" is not unfinished thinking. Here is how I write the question, name options, timebox, decide who decides, and leave with a written next step.
Write Design Docs That Drive Decisions, Not Theater
A design doc that never forces a choice is theater. Here is how I write ones that decide: when to write, how to frame the problem, and how to run review so it ends.
Latency Budgets for LLM Features That Need to Feel Fast
Users feel LLM latency before they feel model quality. Here is how I set a per-feature budget, spend it on first token and streaming, and watch p50 and p95.
Estimating Your NYC Marathon Finish Time
A numbers-literate guide to predicting an NYC Marathon finish time from race formulas, long runs, and the five-borough course, then pacing it honestly.
Onboard Engineers So They Ship in Their First Week
A tour and a stack of docs is not onboarding. Here is how I prepare before day one, pick a scoped first change, pair without taking the work, and make week one a team outcome.
Treat Prompts Like Code Before They Break in Production
Shipped prompts drift and break silently. Here is how I version them next to the calling code, review diffs, gate on evals, pin models, and roll them back.