Trace, debug, eval — without a second SaaS.
Full-fidelity traces of every LLM call and tool step. Token, latency, and cost on each. Replay traces, run evals against datasets, ship to your warehouse. LangSmith-grade observability, billed per trace.
Logs
LangSmith-grade observability. Full traces, token + latency + cost, replay, eval.
- Tokens
- Latency
- Provider
- Cost
- Status
- Webhooks
The three things logs actually does.
Every step in the chain.
Each LLM call, each retry, each tool step is captured. See the full agent run, not just the final response. Tokens, latency, cost on every step.
→ production debugging
200 · 120 ms
Replay any production trace.
Filter by user, model, route, status. Pin a slow request. Replay with a different model or prompt. Share a permalink with your team.
→ cost + latency
200 · 120 ms
Score traces against datasets.
Build datasets from production traces. Run evals on every commit. Compare runs side-by-side. Catch quality regressions before the user does.
→ eval + datasets
200 · 120 ms
Datadog for spend, BigQuery for cost views, a CFO spreadsheet for the receipts — it's three tools doing what should be one log table.
Urgent backstory
We watched five AI startups in a row hand-roll the same logs stack — and burn three weeks doing it. We packaged ours so you don't have to. Drop the SDK in once; this product, plus the rest of the suite, comes with it.
Four common
ways teams ship with Logs.
Production debugging
Filter, pin, and replay any trace. Compare runs side-by-side. Find the one slow tool call buried in a 12-step agent run.
Cost + latency
Per-user, per-model, per-route. Find your most expensive user in 2 seconds. Find your slowest provider. Reroute.
Eval + datasets
Build datasets from real traces. Run evals on every commit. Catch regressions before they ship.
Warehouse export
Webhook to Snowflake, BigQuery, S3. Stable schema, hash-chained, audit-ready.
Four steps, ten minutes.
Already on
Every call you make through the SDK is logged.
Search the dashboard
logs.search({ user, model, ... })Export rows
Webhook URL or scheduled S3 dump
Join in your warehouse
Same schema, same primary keys
The stack you already have.
First time we've had real numbers on AI cost per user. It changed the pricing conversation in the same week.
— Tom · COO, LoomstackFree to ship. Pay when you scale.
per request, after free tier. No markup on tokens. Cancel anytime.
Shipping this quarter.
Ship canonical AI logs this afternoon.
We onboard 1–2 indie startups a week. If you'd rather ship features than maintain a logs stack, talk to us.