Web frameworks
LLM observability for Flask
instrument_flask(app) is the whole integration; the request tree fills in from the auto-instrumented clients.
Set up Flask
The snippet is copied from the SDK README, not paraphrased. Keys shown as tk_live_... are the environment key from Settings › Environments.
# Flask
evalkit.instrument_flask(app)Copied from sdk-py/README.md § Web frameworks
Install → first trace
- 01
Install the SDK
pip install syntropylabs-evalkit or npm install syntropylabs-evalkit.
- 02
Call init() once
At the top of your entrypoint, with your environment key and a service name.
- 03
Call evalkit.instrument_flask(app)
Each incoming request becomes a root trace with downstream model, database and HTTP calls nested underneath.
- 04
Send one request and open its trace
The request appears in Traces as a root span; Services shows the endpoint.
What a turn looks like
Sample data in the product’s own table. Hover, focus or tap a claim to see the columns it points at.
Sample run
| Operation | Service | Status | Model | Latency | Tokens | ≈Cost | Score |
|---|---|---|---|---|---|---|---|
| support_agent.turn8f3a1c0d94e2session sess_4b1e | support-api | ok | gpt-4o-mini | 1.84 s | 3,412 | $0.0006 | 92%auto |
| refund_agent.turnc21d7e5a30b8session sess_9a02tool loop | refund-worker | ok | claude-sonnet-4 | 4.31 s | 7,905 | $0.0389 | 68%auto |
| claude-code.turn5be04f7d1a96session sess_f77c | Claude Code | unset | claude-sonnet-4 | 48.20 s | 61,208 | $0.19 | — |
| rag.answere9a2b6c4d015error | docs-bot | error | gpt-4o | 6.02 s | 9,880 | $0.0312 | 41%auto |
| voice.turn17c8d3f2a4e0session sess_20d1 | ivr-agent | ok | gpt-4o-realtime | 0.92 s | 1,104 | $0.0071 | — |
fig. 1 · the traces table this integration fills · sample data
What you see
Taken from the SDK READMEs’ coverage tables. with flag means the signal leaves your machine only when you opt in.
| Signal | Captured | Detail |
|---|---|---|
| Each incoming request becomes a root trace | yes | — |
| Model, database and HTTP calls nested under the request | yes | — |
| End-user identity from the request | partial | set it with evalkit.set_user(); the README’s automatic fill covers Django and FastAPI / Starlette |
| Request and response headers | yes | credential header values recorded as *** |
| Your own functions | yes | every function in your app’s source tree, on by default |
Limitations
- The README documents automatic user_id capture for Django and FastAPI / Starlette; for Flask set it yourself with set_user().
Next steps
Trace Flask today
Tracing is free for one project on every plan, coding-agent traces included. Evaluations, datasets and simulation are Pro and up.