For your agent

The work finishes before we know enough to judge the method. By the time we do, everyone has moved on.

You may already help your organisation teach, review changes, plan campaigns or hand work over to another team. You have a way of doing it. When the later answer arrives — what someone remembered, what broke, what the next team could use — can you connect it to the method and criteria you used, and bring that experience into the next attempt?

labbel is infrastructure for that connection. It keeps a method, the runs that used it and the outcomes reported later together, across sessions and agents. Your organisation supplies the expertise; you do the thinking with your own model, tools and working context. A recipe gives the method a shared home, with explicit criteria and room for your judgement in carrying it out.

You can bring your own kind of work. With your organisation's expert, define its criteria and when an outcome is worth following up, prepare a domain for a person to examine at the bench, and author recipes within its stamped edition. The service connects each new run to its criteria, helps you find follow-ups that are due, and preserves reports and version history for the next decision. Someone in your environment still needs to arrange your return and supply the evidence.

From the first use, the benefit is concrete: a shared method, visible criteria and a record you can return to. Over time, reports may give you reasons to keep or revise the method. Whether delayed field outcomes lead to useful improvements is the hypothesis we are testing; the working infrastructure is not proof of that result.

We build for increasingly capable agents. Our expectation is that better models can make better use of well-grounded experience while needing more room to exercise judgement. A method's history gives a new model something to examine and improve, without requiring it to repeat the previous model's approach. The Recipe Economy develops this argument: why expertise can give a method its beginning, why later outcomes should be able to change it, and what that could make possible across agents and organisations.

The loop, in three lines

A recipe describes the purpose, constraints and criteria of the work, leaving the agent room to decide how to carry it out.
A run is one use of it; the server stamps what it checked and keeps what the agent declared, beside it.
The outcome arrives later and is reported against that run; that is what a criterion can be revised from.

What exists today

Built-in domain: code-review. Code review gets a served recipe because a review method is general. Work in steps belongs to an organisation-authored domain; under the learning profile, the guide for writing its recipe is requested with profile: "learning". Organisation-authored domains follow their own criteria, stamped by a person at their bench.
Assessment briefs supply the material for a later assessment, in both built-in and organisation-authored domains. Built-in briefs exist for: code-review. For an organisation-authored domain, the brief supplies the chosen run's frozen criteria and follow-up rule, never earlier reports.
In an organisation-authored domain, your organisation defines what to assess. Reports use a general format for each criterion — met, not met or could not verify — alongside reflections. Built-in domains also have specialised signal formats for their particular work. The number of signal types is not the number of criteria you can assess.
Historical reads: retrieve retained versions of your organisation's recipes, a selected stamped edition of your organisation's criteria, and a chosen trace with its available decision records. The built-in review recipe and built-in criteria are served at their current versions.
Provenance: each stored row of a report carries three facts the server observed as it wrote the row. waited: the report came after the run's horizon, not that a later outcome was observed. with a reference: a work reference was registered and not taken back, not that its content was reached or supports the outcome. through the brief: the report carries the handle of a brief that was handed out, not that the brief was read. The service does not observe what an agent has read, and three facts together are not a certificate of truth. Rows stored before 2026-10 keep the session class they were stamped with. Rules version 6.
Follow-up is initiated by the caller: list_due_runs answers which of an organisation's runs — and which of the connected participant's own finished runs in steps — have follow-up work remaining past a window, and report_signals is where the report goes. Another participant's runs are never listed, whatever the connected account's role in the organisation. Nothing here reminds anyone — labbel never pings, and the service's scheduled maintenance is not an agent returning to assess outcomes. manage_follow_up records what is happening to the work on one unit — a wait with a reason and a date to look again, or an attempt given up with nothing verifiable — shown apart from the outcomes and never counted as one. manage_work_reference files where the work of a run is, stored apart from the outcomes and removable by an authorized holder; the work itself is never stored.

A first trial in your work

Choose one recurring process and compare what labbel would preserve with the memory, documents and tools you already use. A useful trial has one method, a real use and a planned return: what later evidence could change your view of the method, who can obtain it, and who will arrange the follow-up? The first result to look for is a record worth consulting at the next attempt. Improvement over time remains something to test.

Cost

labbel is currently free to use, within its access and usage limits. Your model and working environment remain your own costs. We are exploring future payment tied to the value methods and infrastructure provide; no future price is set here. The guide explains the current offer and responsibilities.

Connection and its effects

The door: https://mcp.labbel.ai/mcp — one address, and OAuth is the only way in. A request without a token is answered 401 with the OAuth challenge, and nothing is created. There is no trial door and no key: an anonymous initialisation gets that same 401. Organisations are opened by invitation at present: write to hello@labbel.ai.
Earlier addresses: https://mcp.labbel.ai/mcp/org and saved trial links under https://mcp.labbel.ai/mcp/t/ answer 410 and name the address above. Neither is a door any more.
Reading a recipe through MCP changes nothing about how a later report is stamped (see provenance above).

Publication versions

The publication snapshot identifies the website document set, not a server deployment or production review. Document revisions describe each document separately. If pages show different snapshots, you may have received different publication generations: fetch them again and compare with the document manifest before treating their statements as a current contradiction. Matching snapshots identify a shared publication, not proof that every claim is correct.

labbel