Know what your AI spend delivered

The dashboards show users, models, and volume, but not whether the spend worked. FML follows spend along the path it took — intent, code, PR, deploy, outcome — and flags the expensive sessions with nothing linked.

Customer A

$850 / engineer / month

A large team with a standard AI coding rollout.

Customer B

$5,200 / engineer / month

A smaller, agent-heavy engineering team.

Different workloads may explain the gap. Usage alone cannot distinguish productive work from repeated discovery.

Where the spend went

Spend tied to the path it took, with the expensive sessions that produced nothing surfaced the week they happen.

Where the spend went · this week (illustrative)

$10.0k

Render-queue rewrite

$4.2k

shipped

Checkout retries

$1.1k

merged

Search reindex

$3.8k

stalled · no linked outcome

Onboarding flow

$0.9k

shipped

$3.8k with no linked outcome, surfaced the same week it happened.

Every session and dollar in one place

Spend, tokens, model mix, and session activity — per repo, per engineer.

Activity

Last 30 days

Active engineers
34
of 42 in last 30d
Sessions
128
Claude Code, Codex, Gemini
Spend
$3.8k
model cost estimate
Median session
$0.42
across agent runs

Team briefing

Your team ran 128 sessions across 9 active repos. Checkout has the richest setup, 7 skills were used in sessions, and estimated spend is $3.8k.

checkout 42platform 31growth 18

Recent sessions

Fix checkout retry path without widening PCI scope
$4.18
@patrickcheckout/main
Today
Trace signup latency from PostHog funnel to worker job
$1.42
@gusgrowth/experiment-212
Yesterday
Rebuild auth migration notes into a reusable skill
$0.88
@rohanplatform/auth
Mon

Findings

Needs attention
6
Review
11
Working well
7

Large-context sessions

6 sessions exceeded 150k tokens before the first useful edit.

Model & token mix

Top models · 8.5M tokens

Claude Sonnet 4.54.2M
GPT-5 Codex2.8M
Gemini 2.5 Pro1.5M

Practice library

Skills, commands, hooks, MCP

api-contract
7 active / 12 installed
Skill
54 calls
test-plan
19 active / 24 installed
Command
88 calls
sentry-context
4 active / 9 installed
MCP
17 calls

Connected systems

Signals attached to sessions

GitHub
23 PRs linked to sessions
synced
Sentry
4 incident fixes used prior context
synced
PostHog
Signup funnel tied to 9 tasks
connected
Notion
Architecture notes reused in checkout
connected

Talk to FML from
Slack, MCP, and CLI

Ask what the team shipped, what a session cost, or why a change landed. FML answers from the work record, posts a morning digest, and sends alerts from connected sources like Sentry and Linear.

#engineering· 12 members
fml
FMLAPP· 9:00 AM
Yesterday's AI work
12 sessions · 4h 18m active · $14
Top sessions
signup flow refactorClaude · 2h 14m
worker retry fixClaude · 1h 06m
Context injected into 9 of 12 sessions
G
gus· 9:04 AM
@fml what have we spent on the checkout work this month?
fml
FMLAPP· 9:04 AM
$212 across 38 sessions. Biggest was the retry-path refactor at $31. Most-reused context: May's PCI constraint work.
fml
FMLAPP· 11:32 AM
Alert · Sentry
checkout-retry errors spiking since 11:15
2 sessions touched retry logic yesterday · view sessions

What FML found in 600 sessions

~32%

of this team's AI spend went to repeated discovery and known dead ends

~$8K identified as avoidable
$25K+ analyzed

600

sessions

3

engineers

30 days

captured

Repeated discovery means the model would have acted differently with information already in the team's history, as opposed to a logic failure. Across customers and models the avoidable share runs up to ~40%; the share recovered at install time, before any tuning, is ~25–30%.

This is a retrospective classification, not realized savings. The pilot measures the before-and-after directly: a baseline with injection off, then injection on, compared on cost per shipped outcome with an agreed quality guardrail.

How it deploys

A plugin and CLI on engineer machines capture sessions; delivery systems connect for outcomes.

Live today

Plugin and CLI capture

Installs on engineer machines, captures sessions from the coding agents your team already runs, and syncs them for analysis. Git, CI, and review stay as they are.

Coming soon

Gateway capture

Capture at the LLM gateway layer — LiteLLM, OpenRouter, Cloudflare AI Gateway — for fleets of headless agents.

The FML offering

Memory and attribution are live today. Router evaluation and historical evals are coming soon, built on the same install.

Live today

Engineering memory

Agents inherit the team’s history before they generate the first token: prior work, failed approaches, decisions, production impact.

Live today

Engineering attribution

Spend tied to the path it took: intent, routing, code, PR, deployment, outcome, cost.

Coming soon

Router evaluation

A router picks a model. FML checks whether that pick produced a better engineering outcome, replayed against your own sessions and PRs.

Coming soon

Historical evals

Recurring tasks and past failures become evals, so agent changes are tested against your real work instead of benchmarks.

Security and deployment

FML cloud

The fastest path to a pilot.

Single tenant

A dedicated environment for your organization.

Your cloud

Capture, storage, and context inside your account.

What's captured?

Session transcripts, tool calls, and diffs from registered harnesses.

What's excluded?

Secrets and credentials, redacted at capture.

Who sees raw sessions?

The author, plus roles your organization designates.

How is context scoped?

By project and repository. Injection follows the repos an engineer already works in.

Can engineers inspect it?

Every injected fact is source-linked and reviewable by the engineer it's shown to.

Retention & deletion

You own the raw data. Windows are configurable; deletion is in your control.

Compliance

SOC 2 program run on Vanta, with a live trust center showing current status and controls.

The pilot

Measure the baseline, turn context on, and compare cost per shipped outcome with an agreed quality guardrail.

STEP 1

Capture the work

Measure real spend and shipped output with injection off.

STEP 2

Turn context on

Measure the same team and the same outcome again.

STEP 3

Expand or stop

Compare against the threshold agreed at the start.

Install FML on a few machines with injection off. Thirty days later you have a real baseline, we turn injection on, and we compare.