AI usage and estimated spend
Review AI usage evidence and estimated spend.
TelemetryEstimated spend4 privacy levels
See how AI tools are actually used.
Ingest coding-agent telemetry, break usage down by session, user, model, tool, and repo, and estimate spend from a dated price catalog, with privacy controls that decide what is ever stored.
estimated spend · trend
~$2,000
Trending up as adoption grows
projectedAI usage is part of the Evidence you keep.
One connected loop, held on the stage this capability serves. The other stages stay as context so you can see what feeds in and what comes next.
BD
Discovery
Feedback
Product
Engineering
Release
Reliability
Evidence
Evidence
Prove what happened.
Available now
Audit logs
Review supported workspace changes and their recorded context.
Where the estimated spend actually lands.
Read spend by team and model at a glance: each cell fills by its share, so a heavy team or an expensive model stands out. These are estimates from public token prices, not invoices.
teamopussonnethaiku
platform$820$310$90
web$540$260$120
mobile$210$180$60
data$130$90$40
estimated spend · darker fill means more
Ingest, estimate, break down.
From event to rollup.
Send OTLP or a custom JSON envelope. Each event carries tokens, duration, and git context, keyed so retries never double-count.
OTLP or JSONidempotency keyhourly and daily
- 01
Emit
OTLP or JSON envelope
- 02
Dedupe
by idempotency key
- 03
Cost
tokens x dated price
- 04
Rollup
hourly and daily
Estimated spend, summed as you watch.
Spend is grouped by the provider behind each model, computed from public token prices applied to reported tokens. The total counts up from the parts.
anthropicopenaigoogle
estimated · this month
$3,020
- Anthropic$2,000
- OpenAI$720
- Google$300
The same four-way split every time.
Cost comes from a dated price catalog, split four ways: input, output, cache read, and cache write. Read-time and backfill use identical logic.
dated cataloganomaly detectionoverride
- Output$0.62
- Input$0.28
- Cache read$0.14
- Cache write$0.09
Privacy is a control
Four ranked levels decide what a payload keeps, from metadata_only structural telemetry up to opt-in full_content. Gitleaks and redaction tripwires reject any batch that leaks secrets, and every privacy toggle is written to the audit log.
An honest limit
Spend is estimated from public token prices applied to reported tokens, not a bill. Git context fields are attribution hints, not proof of what shipped, and AI activity is usage evidence, not a productivity score or a causal ROI claim.
See the rest of the evidence stage.
Give leaders cost evidence without inventing a score.
Start free
Usage evidence with privacy controls.