Control plane for AI engineering

One standard for how your engineers work with AI.

Every developer sets up Claude, Copilot, and Cursor their own way, and no one can see the sprawl. baseline turns it into a single versioned standard, ships it to every repo and laptop, and shows you exactly who's on it.

Works with Claude Code Copilot Cursor Gemini
baseline · coverage · Acme Engineering
0%
of your codebase is on baseline
38 / 42 repos · updated 2m ago
RepoPackVerState
acme/websoftware-engineer1.2.0On baseline
acme/apisoftware-engineer1.2.0On baseline
acme/paymentssoftware-engineer1.1.0Behind
acme/ml-platformtoken-efficiency1.0.0On baseline
acme/infraNot yet
0 / 14
laptops on baseline
2 need attention · 2 not paired
DeveloperLaptopSyncedState
Maya ChenMacBook Pro2m agoOn baseline
Jonas EkwuemeThinkPad X118m agoOn baseline
Priya NairMacBook Air3d agoBehind
Diego SantosMacBook Pro5m agoOn baseline
Sam OkaforneverNot paired
adoption · last 30 days
The problem

Twelve engineers, twelve ways of working.

AI showed up one laptop at a time. Everyone picked their own tools and wrote their own rules, so nothing matches — and none of it is visible. You can't standardize what you can't see, and you can't improve what isn't standard.

before baseline · unmanaged
Today, across the team
0
shared standard
6
tools in play
none
of it visible
DeveloperToolConfigState
Maya ChenClaudeCLAUDE.md · 340 linesStale
Jonas EkwuemeCopilotinstructions · emptyMissing
Priya NairgenericAGENTS.md · her ownOff-book
Team BCursor.cursorrules · from a blogUnverified
InfraGeminiGEMINI.md · unownedOrphaned
no baseline · nothing enforcedand this is only what we could find
The shift

Working well with AI is a standards problem, not a model problem.

The leverage was never a smarter model. It's agreeing on how your team works with AI — then keeping every repo and every laptop on that agreement as it changes. baseline is where that standard lives, ships, and holds.

How it works

Audit, standardize, distribute, govern.

Four steps, each producing something concrete the next one builds on.

01

Audit

Point baseline at a repo. It reads the stack and names the pack that fits.

$ baseline audit ./web
langs: ts, tsx
tests: vitest ✓
→ software-engineer
02

Standardize

Pick a pack, or shape your own. One source renders config for every AI tool.

AGENTS.md
CLAUDE.md
.claude/agents/
copilot-instructions.md
GEMINI.md
03

Distribute

Open a pull request in every repo. The desktop app carries it to laptops, leaving local work alone.

$ baseline distribute
✓ PR #128 → acme/web
✓ PR #129 → acme/api
04

Govern

See which repo and which laptop is on baseline, at which version, right now.

acme/web on baseline
maya on baseline
acme/infra not yet
Governance

Know exactly who's on baseline.

Not a claim in a slide about "AI transformation." A live count of how much of your codebase — and how many of your engineers' laptops — run the standard you set. Down to the repo, down to the person.

Coverage repos + developers
90%
repos on baseline
12 / 14
laptops on baseline
4
need attention
Repo / DevPackVerPRState
acme/websoftware-engineer1.2.0#128On baseline
acme/paymentssoftware-engineer1.1.0#131Behind by one
maya · laptopsoftware-engineer1.2.0On baseline
priya · laptoptoken-efficiency0.9.0Behind
acme/infraNot proposed yet
Key: on baseline · behind · not yetupdated 2m ago
Packs

Your standard, versioned like code.

A pack is your team's way of working with AI, written down: the agents it runs, the commands it exposes, the rules it holds people to. Versioned, reviewed, and rendered for every tool. Start from a curated one, drag your own together in the visual builder, or describe what you want and refine the AI's validated draft — nothing saves until you approve it.

software-engineerv1.2.0

Software-engineer harness

The disciplined default: plan, build, then an independent review. TDD, scoped sessions, and guardrails that keep changes surgical.

3 agents4 commands2 hooks
token-efficiencyv1.0.0

Token-efficiency harness

Cuts AI spend without cutting output: session hygiene, model tiering, thinking caps, and a budget on every autonomous run.

scout · haiku/handoff/usage-audit
test-loopv1.0.0

Builder / checker loop

Two roles, one rule: an independent checker re-runs the tests itself before any change counts as done.

checker agent/build-and-check
The harness

A pack carries more than config.

Config is instructions, rendered once. A harness is state that accumulates over the life of a repo — memory, a task ledger, a wiki, a design system, a codegraph — held by the pack and kept current as things change. Turn on what you need; each capability names its own method, and one that isn't built yet says so instead of pretending.

memoryLive

Facts that survive the session

/remember writes a durable entry; session start reads the relevant ones back in. Org-shared memory syncs to every laptop through the agent; repo-local memory ships in the PR.

method: filesorg + repo
designLive

One DESIGN.md, on-brand everywhere

Theme, palette, type, components, do's and don'ts — the nine-section spec AI tools already read — so generated UI matches your brand instead of a generic template.

method: from brand colorfrom existing site
tasksRolling out

A ledger that outlives the run

Plans and progress recorded as they happen, so a session that gets interrupted — or a different engineer entirely — can pick up exactly where it stopped.

method: PLAN.md + ledger
wikiRolling out

Read before, write after

Agents check the wiki before touching a file and update it after. Most knowledge tools only read; this one writes back, so it doesn't go stale.

method: baselineread + write
graphComing soon

A map, not a guess

A queryable map of how the codebase actually connects, so agents stop re-deriving structure they could just look up.

planned: tree-sitter
For the developers who live in it

Your setup, on every machine you touch.

  • one sourceEvery tool from one file. Claude, Cursor, Copilot, and Gemini configs render from the same pack — no more hand-syncing five files.
  • the CLIRuns in your repo. baseline audit and apply show you every change before a single file moves.
  • the appPairs once, stays current. A small desktop app keeps your laptop on the org standard and never overwrites the tweaks you've made yourself.
Download for macOS Windows Free · pairs to your team in one click
~/acme/web
$ baseline apply . --pack software-engineer
rendering for 5 tools…
✓ AGENTS.md · CLAUDE.md · .claude/ · copilot · GEMINI
your local edits: kept · overwritten: 0
$ baseline agent status
● paired · acme · on baseline · synced 40s ago
Get started

Put your whole org on baseline.

Sign up, publish your first pack, and watch it reach your repos and laptops. Free to start.