Every company wants to be AI-first.
That takes people who already are.

AI does not replace a specialist — it multiplies one. Deigma turns that into something you can show: a passport built from your real work, not from what you write about yourself.

Read-only metadata · free while we are in early access
Work that shipped and stayed shipped
87%
between 82 and 91
214 episodes over 8 months
Model output checked before accepting
92%
between 88 and 96
610 accepted drafts
2of 2
Verified · Everything measurable in the way they work — proven.
IDE assists · 3 projects
an example passport — the anatomy is real, the person is not
01

Connect what you already use

GitHub for outcomes; a local CLI and editor extension for how you work with the model. No forms, no tests, nothing to fill in.

02

Your history counts from the first minute

We read up to six months of finished work — pull requests, and the runs of commits of anyone who works on main. For an active developer the first claim is proven before anything else is installed.

03

Share only what is proven

A claim appears when its own interval is tight enough. Nothing unproven is published anywhere — not on the profile, not on the badge.

The problem

Everyone says they work with AI.
Nobody can show it.

A résumé is a claim. A certificate tests theory. An interview is forty-five minutes of an artificial task — and most companies still ban AI during it, while the actual job is done with AI every day. Real skill lives in months of work, and nobody measures those months.

So companies buy tools, call themselves AI-first, and have no way to tell who inside them actually got stronger. That gap is what this is for.

Before anything else

Your work never leaves your machine.

We are asking you to run our software next to your own. That deserves a straight answer before anything else on this page.

What goes out

Pull request lifecycle and timestamps, CI conclusions, review states, salted hashes, counts and timings of your sessions. That is the whole list — and it is generated from the schemas the software is built against, so the traffic audit page cannot drift from what actually ships.

The proxy is fail-open by design: if anything inside it breaks, your call passes straight through and the measurement is dropped. Your tools working matters more than our data.

What never does

  • Source code, diffs, file contents
  • Prompts and model output
  • File names and paths
  • Screenshots, keystrokes, screen recordings
  • Clipboard, browser history, other applications
  • Time tracking outside episodes

Leaving takes one click. Deleting the account destroys the key your rows are encrypted with — backups included — and you get the audit event that recorded it.

What a passport says

Not a score. A set of claims that have been proven.

Each claim is measured on its own evidence and published only when it is measured well enough. Every value carries the range it was measured within — because a number without it would be a guess wearing a suit.

Work that shipped and stayed shipped
87%
between 82 and 91
214 episodes over 8 months
Model output checked before accepting
92%
between 88 and 96
610 accepted drafts over 8 months
2of 2
Verified · Everything measurable in the way they work — proven.
IDE assists · 3 projects · 8 months

An example passport — the anatomy is real, the person is not.

The set differs by how you work. Someone who delegates to an agent proves different claims than someone who accepts suggestions in an editor — and the passport says which way of working it measured, instead of penalising you for the one you chose.

Every week, in your terminal

The pulse speaks in evidence, never in nudges.

deigma pulse
Week 2026-08-17 — 2026-08-23
+6 episodes · 4 reached a final status
ETS 87% (90 % interval 82%–91%)
Trend 30 d: +2.4 pp
2 of 2 claims proven · IDE assists · Verified · measured across 3 projects
The rules we hold

Written down, and enforced by tests.

Nothing unproven is shown

Not the value, not a hint of it. A separate suite tries to pull an unproven number out through parameters, caches, link previews and address guessing — including reconstructing it from the width of an interval.

The passport belongs to you

Private by default. A private profile answers exactly like a handle that never existed — same body, same timing. A one-time link opens once, for one recruiter, and expires.

No automated decisions

No webhooks or exports triggered by anyone's score. No ranked lists through the API. A passport is evidence for a conversation, not a filter that runs without you.

Process never outweighs outcome

Claims about how you work are published only when real work stands behind them. An empty profile with rich telemetry is unreachable by design.

A passport first.
Then a place to find each other.

The people who are genuinely strong with these tools are hard to find, because the signal is buried under everyone claiming the same thing. Once passports exist, that changes.

Hiring that starts from workMonths of real evidence instead of an hour of interview theatre.
Cofounders and teamsFind people for whom frontier tools are not a phrase but the daily job.
Your own recordIt travels with you between companies, because it was never theirs.
Why trust the number

The method is open, and the snapshot is signed.

A measurement, not an opinion

A latent-ability model from the same family used to calibrate GRE, PISA and medical licensing exams. Task difficulty is inferred from data, so a run of easy work cannot buy a score.

Verifiable without us

Every snapshot is signed. Anyone can check the signature offline against the published key — and it attests the numbers without exposing anybody's work.

Honest about what is missing

The engine is validated computationally; external validation comes from a blind pilot that has not run yet. We say so here rather than after you find out.

Your work already says it.
Let it be readable.

Start with GitHubRead the methodology
Deigma · a passport of proven claimsPrivacy & cookies · Methodology · Traffic audit · Contact