> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/more-in-this-section-6/span-level-scoring.md).

# Recipe: span-level scoring

Recipe — span-level scoring. Pointer to the cowork code-review pattern.

Stratix evaluates traces holistically by default. To target specific span kinds, build a judge whose evaluation goal references span shape and run via `client.trace_evaluations.create(trace_id=, judge_id=)`.

The cowork [`samples/cowork/code_review.py`](https://github.com/layerlens/stratix-python/blob/main/samples/cowork/code_review.py) demonstrates per-span review (the Instrumentor uploads code traces with span structure, the Reviewer evaluates with focused judges).

For trace investigation (errors, latency, anomaly detection per-span), see [`samples/core/trace_investigation.py`](https://github.com/layerlens/stratix-python/blob/main/samples/core/trace_investigation.py).

## See also

* [Concept: Traces and spans](/6.-build-wire-your-code/traces-and-spans.md)
* [Industry pattern: insurance missed escalation](/4.2-industry-use-cases/pattern-3.md)