AI coding spend, reconciled to shipped code

Find out what your AI coding spend actually shipped.

See how much of your engineers’ AI coding spend turns into shipped code, and surface the spend that never does. Starts with Claude Code and GitHub.

See live demo
$48.2K
Reconciled this month
59%
Spend that shipped
4
Spend states
3
Confidence tiers

Spend review

March 2026 · Acme Engineering

$48.2K Claude spend

Mixed confidence

$28.4K became shipped code. $9.8K never tied to a merged PR.

Shipped
HIGH

$28.4K

59% · Tied to a merged pull request

In flight
MED

$7.1K

15% · Open PR or inside the attribution window

Unmatched
LOW

$9.8K

20% · No merged PR after 30 days

Other
LOW

$2.9K

6% · Other repositories or non-PR work

Sample data. Quick Start produces correlation; the capture plugin upgrades selected teams to SHA-level attribution.

How it works

  1. 1. Connect GitHub

    Securely link your repositories through the GitHub App to track what ships.

  2. 2. Track AI spend

    Capture Claude Code usage and cost across your fleet, automatically and zero-touch.

  3. 3. Reconcile ROI

    Match spend to merged pull requests and measure what your AI budget actually shipped.

Enterprise features

Team-level attribution

Spend and shipped rate per team. Aggregate by default, never a per-engineer ranking.

TeamSpendShipped
Platform$12.4K61%
Infrastructure$8.9K54%
Growth$5.2K48%
Mobile$3.1K57%

Automatic PR linking

Each captured session resolves to the pull request it shipped in, by branch and SHA.

PR #128

Checkout retry logic

Shipped

PR #131

Dashboard charts

In flight

PR #126

Spike: vector search

Unmatched

Security

Encrypted in transit and at rest. SSO on Enterprise. SOC-2 is on the roadmap.

Privacy first

Token counts, timestamps, and git refs leave the machine. Your prompts, code, and transcripts never do.

Audit ready

Export reconciliation logs for finance and FinOps. Full visibility into how AI spend maps to shipped work.

Spend over time

Watch the burn, by model

See daily Claude spend broken out by model version, with the percent that shipped traced on its own axis. The same chart you get on your dashboard.

Spend over time

$60,840Last 30 days

Daily AI spend (estimated + metered), by model version, against the spend that shipped.

$0.00$2,500$5,0000%50%100%May 20Jun 3Jun 18
Opus 4.8Sonnet 4.6Haiku 4.5Spend ($, left)Yield (% shipped, right)

Sample data.

Pricing

Start solo. Scale to your whole org.

Same attribution engine on every tier; team and enterprise unlock as you grow. A few percent of the spend you already manage. Card required, cancel anytime.

Solo

$15/mo

For one engineer.

  • Fleet-wide capture, zero setup
  • PR-level spend attribution
  • Spend by model + right-sizing
  • Your spend & yield reports
  • Metadata only, never your code

Team

Most teams

$50/engineer/mo

Up to 10 engineers.

Everything in Solo, plus

  • Team rollups & spend states
  • Per-engineer diagnostics
  • Agent flags & budget alerts
  • Multi-repo attribution
  • Shared team dashboards

Enterprise

Custom

Unlimited engineers.

Everything in Team, plus

  • SSO / SAML
  • Volume pricing & invoicing
  • Priority support & SLA
  • Security review & DPA

Start with one repo and one pilot team.