Injected context saves 25% in time and tokens.

FML injects compact task context from prior sessions, repo history, docs, tests, incidents, and product signals before the agent starts exploring.

Context injection

The bundle selected for one checkout agent run.

Prior sessions

17

checkout retry, auth migration, PCI review

Related PRs

5

merged fixes, reverted retry path, review comments

Docs and tests

8

architecture notes, runbooks, relevant test files

Production signals

4

Sentry incidents and PostHog events tied to the task

01

Session starts

Prompt: "fix checkout retry bug without changing PCI boundary"

02

FML retrieves context

prior sessions, related PRs, docs, tests, Sentry, PostHog, and team rules

03

Agent starts with the bundle

less repo-crawling, fewer clarification turns, fewer repeated mistakes

25%

faster in replay benchmarks, with fewer discovery turns and lower token spend

What changes when the agent starts with history

FML context injection completed comparable tasks about 25% faster with fewer turns.

Cold start

Agent explores from scratch

01Broad repo crawl before the first useful edit
02Retries approaches the team already rejected
03Finds constraints after spending tokens

With FML context

Agent starts with the useful bits

01Prior sessions explain what already worked
02Related PRs carry reviewer and PCI constraints
03Relevant docs and tests are opened first

About 25% faster on comparable tasks, with fewer turns and lower token spend.

How we measure it

The 25% figure comes from replay benchmarks on real work, not synthetic demos. Results vary by repo and task mix; 25% is what we see across the benchmark set.

01

Replay real tasks

Each benchmark task is a prompt from a real session, replayed in the same harness against the same repo state.

02

Run both conditions

One run starts cold. The other starts with the FML context bundle. Same model, same tools, same prompt.

03

Compare the runs

We compare time to completion, agent turns, and token spend. With injection, comparable tasks finished about 25% faster.

What gets injected

Small bundles of task-specific history, not a giant dump of everything the company knows.

Prior sessions

What engineers and agents already tried, where they got stuck, and which approach finally worked.

Related PRs and reviews

The code changes, comments, reverts, and reviewer constraints that explain the current task.

Tests, docs, and incidents

The checks, architecture notes, production issues, analytics events, and runbooks the agent should see early.

Team rules

Project-specific patterns that prevent agents from rebuilding the same thing from scratch.

Measure the savings on your own repos.