Top 5 starter recipes
Five starter cookbook recipes hand-picked for new Stratix users. Cover the full Build → Observe → Evaluate → Improve arc in your first week.
Last updated
Was this helpful?
⌘Ctrlk
Five starter cookbook recipes hand-picked for new Stratix users. Cover the full Build → Observe → Evaluate → Improve arc in your first week.
The cookbook has 59 recipes. These are the five we'd hand to a new engineer on their first week — one per workflow stage, each delivering visible value in under an hour.
Run first-eval-5-minutes first if you haven't. These five build on top.
Why this one: before you can score real production traffic, you need traces. This recipe shows the two primitives — @trace and span() — that turn any Python function into something Stratix can see. It works whether you're calling OpenAI, a local model, a vector store, or your own custom orchestration. Five lines of decorators replace days of OTel wiring.
Stage: Build · Time: 15 min · Output: traces flowing into Premium → Traces
Why this one: you almost certainly already have logs — Postgres rows, JSONL files, Datadog exports — sitting somewhere. This recipe converts that history into Stratix traces in bulk so you can run evaluations against weeks or months of real production data on day one, instead of waiting for new traffic to accumulate. Highest leverage move you can make in week one.
Stage: Observe · Time: 30 min · Output: historical traces visible in Premium, ready to score
Why this one: hallucination is the #1 failure mode every team asks about first. This recipe wires up an LLM-backed faithfulness judge that flags answers unsupported by retrieved context. Works on freshly captured traces or backfilled history. The judge prompt is tunable, the threshold is tunable, and the per-row verdicts are inspectable — so you can trust the signal before you act on it.
Stage: Evaluate · Time: 20 min · Output: every trace gets a faithfulness score and verdict
Why this one: the moment your agent emits JSON, you need to guarantee the shape — required fields, types, enum values, nested structures. This recipe registers a code grader that runs a JSON Schema check against every output and emits a 0/1 pass score. Pairs naturally with #3: hallucination judges score content, schema graders score shape. Together they catch ~80% of the "my agent is broken" reports in CI.
Stage: Evaluate · Time: 15 min · Output: schema failures surface as failing rows in every evaluation
Why this one: the judges you bootstrap (recipe #3) start at 60–75% agreement with human labels. That's enough to find problems but not enough to gate on. GEPA — the platform's prompt-optimization loop — tunes the judge prompt against a small labeled set until agreement climbs past 90%. This recipe takes 30 minutes and converts a noisy first-draft judge into one you trust enough to wire into CI.
Stage: Improve · Time: 30 min · Output: an optimized judge with measurable agreement gain
In one week, you go from "we have a chatbot" to "we have measured quality across thousands of past interactions, with judges we trust enough to block bad releases on."
More recipes by problem, framework, industry, integration: All cookbook recipes
Guided learning paths instead: All tutorials
Task-shaped walkthroughs: All guides
Workflow context: The Stratix workflow
Last updated
Was this helpful?
Was this helpful?
1. Instrument → traces exist
2. Backfill → historical traces exist
3. Faithfulness judge → content quality scored
4. JSON schema grader → output shape scored
5. GEPA basics → judges sharpened