Put AI agents to work and keep the last word.

Four failures no prompt cures

Several AI coding agents — different vendors, different harnesses — working on one repository at once produce the same four kinds of damage, in every team that tries it.

Read it for where it stops — and how it moves

A diagram of agents usually shows who calls whom. This one shows where a mission can be refused, and what carries it: ten checks before a session starts — seven stable contract conditions, three guards hardened in operation — a witness and a human gate before anything lands, three exit codes decided by durability alone, a register that sends every incident back into the next contract, and a watcher drawn twice: what it does today, and the receive–deliver–wake loop that still has to earn activation.

Drawn on Lantern, the fictional project the kit is demonstrated on — the mechanism, the checks and the exit codes are the real ones. Open the interactive version and hover a block to isolate its path.

What a refusal looks like

Watch one arrive → — inside a working day, in two minutes.

The launcher read contract #118, fetched the governance at the commit the mission would run on, and stopped before creating anything. Three days earlier an attempt at the same lot had been refused at review; its branch survived on the remote because nobody wrote a disposition for it. Silence is debris — and the launcher saw it before a second writer existed.

C:\repos\lantern\.venv\Scripts\python.exe C:\repos\lantern\tools\mission_launcher.py 118 --dry-run

Mission #118 — #118 — [MISSION] Dashboard tiles keep their last reading while the device bridge reconnects
  https://github.com/lantern-workshop/lantern/issues/118
  primary checkout: C:\repos\lantern
  governance policy: 3f9c2d1a7b8e4c05d6f1a2b3c4d5e6f708192a3b (origin/develop, fetched at launch)
  run: launch — creates the branch and the worktree the contract declares

REFUSED — 1 refusal(s). Nothing was started.

  condition 4: a second writer would be created
      branch 'feature/dashboard-stale-reading' already exists on origin -- a writer
      already holds the branch this Mode 'one writer' mission declares, and creating
      it again locally with 'git worktree add -b' would put a second, diverging line
      on the same name; under 'one writer' that is the two-writer failure itself

The whole transcript — the refusal, the disposal, the run that passed, and what --list showed forty minutes in — is in the kit. The doubled number in the banner is real, known, and cosmetic: the title carries its own number by convention.

The board, read for what it owes you

Twenty-five merges a day are not readable from an issue list. The Product Owner opens one page instead — the page shipped in the kit under templates/board/ — and it answers three questions, in this order, and refuses to guess the answer to any of them.

The board as it runs, on the fictional Lantern example — open the demonstration. It is frozen and says so on its face: the controls are shown, not live. What the kit publishes today is the board reader, under templates/board/; the host reading and the decision path are newer, and reach the kit when they have stopped moving.

For someone who does not write the code, this is the difference between “we use AI” and “we know what the AI did.” Not a productivity chart — a list of what is owed, to whom, and what nothing yet accounts for.

What it runs on

A Windows desktop application in Python with a 13 155-test suite, measured on 8 September 2026. One human — the Product Owner — who holds the hardware, the product verdict and the merge to the release branch. Every line of code, test and governance document since early August 2026 has been written by AI seats under these contracts — and still is.

The sober reading, because it is the one that makes the first credible. The same period produced forty-seven incidents serious enough to earn a rule, most of them inside one week. Most seats the launcher can start are unknown on the hardware property the queue would most like filled. Neither command-line harness enforces read-only from its own flags, and the governance says so rather than pretending. A system that can say I do not know in the places it does not know is the only kind whose yes is worth anything.

Fifteen documents, numbered in reading order

Start with 00 for the shape and 12 for why it is shaped that way. If those two earn a third, read 05.

Where this is going

The kit is the part that has stopped moving. Three things are still moving on the project it comes from, and each will reach the kit the way everything here did — once a real incident has paid for it.

What adopting it looks like with help

The three tools are specified precisely enough to audit or re-implement, and they are not shipped. Installing this on a repository, adapting the vocabulary to a team's own seats and workstreams, measuring the capability table on their machines, writing the tools against their harnesses, and running the first two weeks of missions alongside them — that is the work, and it is the work I do.

The thirty minutes are free and commit you to nothing — we look at your setup, and you leave with an opinion even if you go no further.

Three questions before saying you do not need this

Two things are true at once: your teams could hand an AI far more than they think, and nobody at your company keeps a record of what they hand it already. The second is what stops the first — you do not accelerate on ground you cannot see.

I am not trying to convince you. These three questions are enough, and you already know the answers.

If the answer to the third is "we did not", you already have the incident. What you are missing is the register — the place where every error becomes a rule instead of happening again.

What it earns you, and what it spares you

The first two are what it earns. The other four are what it costs when nobody holds the thread. In none of them did anyone cheat or cut a corner. Under each, the rule that makes the difference, in one sentence.

One page, and you know where everything stands

It is one page. It reads what your teams had an AI do, a quote, a reply to a client, meeting notes, a contract, whatever tool produced it, and it sorts everything into three piles. What is in them changes from one trade to the next. The three piles do not.

A fictional firm, its quotes, its client replies and its minutes: open the demonstration. It is frozen and says so on its face, the buttons are shown and not live. There is nothing to translate: these are your own objects, and the decision is taken on the page rather than somewhere else.

This matters more without code, not less. A development team at least has a version history: someone can reconstruct who changed what. A firm whose AI assistants draft, answer and summarise all day has no history at all — until someone gives it one.

Where this is going

One page that reads what your people hand to an AI — quotes this year, minutes and client replies the next — and sorts it into the same three piles, under the same states from one trade to the next. The person who signs sits in the consultant's chair, not the executor's: the AI brings the finished thing and the one decision that is theirs, and everything else leaves in plain sight.

Offers and prices

Most companies I meet badly underestimate what they could hand over — and overestimate what they would have to buy to do it. So we start by looking at your real work: what can be handed over right now, what that gives you back in hours, and what must stay in human hands. Nothing to buy, and the document stays with you whatever happens next.

The thirty minutes are free and commit you to nothing — you describe your week, I tell you what I see in it, even if you go no further.