CapabilityAI harness

    An AI harness: the controlled workplace an agent runs in

    Short answer

    The agent does the repetitive work inside a harness: one work order, frozen inputs, a written mandate, your checks on every output, one run record and a named person signing every release.

    HarnessPer run
    Inputshashed, versions pinned
    Agentinside a written mandate
    Checksyours, on every output
    Recordone per run and rerun
    Releasenamed person signs
    How one run movesWork order to record
    1. 01Work orderone deliverable · a revieweraccepted whenthe deliverable, its tests and its reviewer are written down
    2. 02Inputs frozenhashed · pinnedaccepted whena rerun on the same inputs gives the same result
    3. 03Agent worksmandate · steps loggedaccepted whenthe agent can use only the tools its mandate lists
    4. 04Checks decideyour checks · pass/failaccepted whena failed check sends the work back
    5. 05Person signsnamed · releaseaccepted whennothing is released before a named person signs
    6. 06Record keptper run · per rerunaccepted wheninputs, steps, checks and review sit in one record

    Parts

    What a harness is made of

    H01

    Work order

    One named deliverable with its inputs, acceptance tests and a named reviewer. The agent works on nothing else.

    H02

    Frozen inputs

    Data, specifications and reference versions are hashed and pinned before the run, so a rerun gives the same result.

    H03

    Mandate and tools

    A written list of what the agent may read and do, enforced by the tools it is given. No credentials it does not need.

    H04

    Checks

    The checks your team already trusts run on every output: rules, validators, comparisons and reconciliations. A failed check sends the work back.

    H05

    Run record

    Inputs, versions, every agent step, check results and the review, stored as one record per run and rerun.

    H06

    Named sign-off

    Nothing is released until a named person reviews the findings and signs. The agent holds no release rights.

    Division of labour

    Judgement stays with people

    People decide

    • What the specification means where it is silent
    • Whether a finding is a real defect or an explained exception
    • Whether the output is fit to release, and they sign for it

    The harness does

    • Freezes inputs and pins versions
    • Runs the agent inside its mandate and captures every step
    • Runs the checks and blocks release until a named person signs

    How we would start

    1. Scoping

      We map one workflow from input to sign-off, the checks you already run and the first deliverable for the pilot.

    2. Parity on past work

      The harness redoes completed work and we compare it with what your team delivered. Nothing touches live work.

    3. Live, under review

      The agent takes one seat in the live workflow, for example the independent check. People adjudicate every difference.

    4. Enablement

      Your team learns to build the next harness on the same controls.

    Common questions

    Q01Is a harness a product?

    No. It is the way we build AI into a regulated workflow. Each harness is built around your checks, your data and your sign-off rules, and you keep it.

    Q02Which work fits a harness?

    Work that already has objective checks: rules, validators, reconciliations or a second person comparing outputs. The checks are what make the agent's work safe to accept.

    Q03Which models do you use?

    The model is a replaceable part. The run record stores which tool, model and prompt version produced each output, as provenance and never as a verdict.

    Q04How is it priced?

    A fixed-fee scoping, then milestones against acceptance tests agreed in writing. No price before scope.

    Next step

    Which of your workflows already has the checks?

    A scoping call with Oleg. We pick one workflow and plan a parity study on your own past work.

    Oleg Pun

    CEO, Vareger

    Oleg Pun, CEO, Vareger