Finance analyst
Company and FinanceBusiness, from January 15. Planned, not live. The plan matrix is flagged.
The problemAsk whether a Business customer can schedule an export, and Product, Support and Finance each answer from their own documents. The answers differ, and none says which one is current.
Pick a question. The answer names its records and its owner, or says nothing approved answers it.
The problemA rule changes in one place. The Support macro and the Finance plan matrix still say the old thing, and the help center bot keeps quoting it until a customer notices.
Approve a new version. The records that now disagree are flagged, and every assistant is asked again.
Press the button to watch one change move through the brain. Example data from the product's own test scenario.
Agents can propose. Only people publish. The history of one rule, from proposal to proof.
The problemPut every team's records in one place and the help center bot could quote Finance's internal notes, or someone who has left could still ask.
Access is applied when records are picked, before any prompt is built.

“Which plans include scheduled exports, and from when?”
Business, from January 15. Planned, not live. The plan matrix is flagged.
Business customers, from January 15. Planned, not available yet.
No answer. No access to the workspace.
The problemYour assistants come from different vendors, and you learn what they say when a customer quotes it back to you.
Any vendor. They read approved text and get asked check questions.
get_contextget_recordsearchpropose_changepropose_app
$ loopwright check loopwright.checks.yaml Help center bot 6 of 6 failed which-plans FAIL stale available-today FAIL overclaims Product assistant all 6 passed check failed (--fail-on critical)
The check runner works alone in a release pipeline: no server, no account.
One server and one web app.
A space per team, with a named steward.
Rules, policies and definitions with an owner and a history.
Goals, decisions and actions as linked records.
Anyone proposes. Only people publish.
Publishing flags the records that now disagree.
Ask every assistant before and after a change.
Answers with citations, over MCP and REST.
Five roles and a grant per assistant.
Small HTML apps in a sealed frame.
Text, Markdown, HTML, PDF and Markdown in Git.
Several in one deployment, with a hard AI spending cap. Export and restore.
Email and password, invitations, tokens for clients.
The tests ship with the source. No outside party has tested it yet.
Another company's identifiers return nothing.
A planted secret never reaches a prompt.
Denied on the next request.
Agents and apps end with a proposal.
Apps can't reach cookies or the network.
Calling a planned feature available fails.
Limits today. Tests use a stand-in model, so answer quality on real providers is unmeasured.
One container beside your Postgres, with your model endpoint.

The same server, run for you. No price or uptime commitment published yet.
TypeScript throughout. One Postgres. No outside service required.
Outlined in marigold: built, being verified.
@loopwright/serverAGPL 3.0@loopwright/webAGPL 3.0@loopwright/coreApache 2.0@loopwright/checksApache 2.0loopwrightApache 2.0@loopwright/appApache 2.0@loopwright/app-bridgeApache 2.0@loopwright/uiApache 2.0AGPL: run and modify it inside your company; publish changes if you offer it as a service. Apache: embed freely.
No. Records have an owner, a status and versions, and answers come only from the approved version. When nothing approved answers a question, it says so.
No. Assistants read over MCP or the REST API, or get approved text exported as Markdown or JSON.
Any OpenAI-compatible endpoint, including models on your own machines. The server also runs with no model.
It can propose one, with evidence. Only a person publishes.
Self-hosting is free under the open source licences. The hosted version is in early access with no published price.
Not yet. Tell us, because it helps decide whether to offer one.
Not today. Loopwright is new, with no certifications and no customers to name.
The public repository is not announced yet. Ask for source access and we will share it.
We run it on your infrastructure and show what every assistant says, before and after.
info@loopwright.com