03Run
Assent runs the agents, inside the grant.
Assent is designed so that a managed runner does the work, repairs within a limit and pauses for the owners.
Concept UI · illustrative data
What this shows
- Run: Repairs within a limit, and a pause for both teams.
The usual way
Our hypothesisSomeone still operates the agents. Prompt by prompt, rerun by rerun.
Our working hypothesis: teams spend real time operating coding agents, writing prompts, managing sessions and branches, rerunning failed attempts and shepherding pull requests.
- Prompts rewritten for every attempt
- Sessions and branches managed by hand
- Failed runs restarted from scratch
- Pull requests shepherded to merge
- A task that quietly grows
Step by step
Synthetic exampleA run that stopped at the boundary, on purpose.
One repair would fix a failed contract test. Then a discovery outside the grant would pause the stage and go to its owners, with the dependent grant invalidated.
Start inside the grant
The managed runner would start from the execution contract: no production credentials, an egress allowlist, protected checks pinned outside the workspace.
Run the agent
Assent would operate the agent inside the declared restrictions, taking on the sessions, branches and retries a person would otherwise run.
Repair within the limit
When verification fails, the agent would diagnose and retry up to the configured limit, within the same grant. Protected checks wouldn’t be editable.
Pause or escalate
A material unknown would pause the affected stage for its owners. At the repair limit the stage would stop and escalate with its attempts and evidence.
What this shows
- GR-7f3a verified · DEC-0031 rev 2 · policy v14
- Isolated workspace · egress allowlist applied
- Handoff from DEC-0031 rev 2 · no one wrote a prompt
- Edited contracts/reservations.openapi.yaml
- Edited services/reservations/src/serialize.ts
- Edited services/checkout/src/expiry.ts
- Contract tests · 1 failed: timezone edge case
- Repair 1 of 2 · diagnosed and corrected
- Path scope · diff within granted paths
- Approved-contract comparison · matches the target
- Contract tests · pinned copy passed
- Pull request #218 opened · evidence attached
What this shows
- Decision needed: Persist reservation expiry across restarts?
- Keeping expiry across a restart would need a persisted value: a persistence decision outside this grant.
- Waiting on the provider and consumer owners. The dependent grant is invalidated; work resumes under a new one.
Capabilities
First buildall six capabilities
The design, in six parts.
Assent runs the agent
The first adapter is planned to be Claude Code in an isolated runner that Assent would operate. A second adapter would follow only after control-equivalence tests.
Bounded repair against protected checks
Failed verification would be diagnosed and retried up to a configured limit, inside the same grant. The agent would not be able to edit the checks it is judged by.
Escalation at the limit
When the repairs run out, the stage would stop and reach the attention list with its attempts and evidence. Repeated failure that suggests a missing decision would be treated as a material unknown, not retried.
New discoveries pause the work
When the agent finds a material question the decision didn’t cover, the affected stage would pause and the question would go to the owners. Work would resume only under a new grant.
Keys never enter the workspace
Managed runs would use organization-level provider credentials, injected by a proxy outside the sandbox. Personal credentials and subscriptions would never be used.
A runner that can’t reach production
No production credentials, outbound network limited to an allowlist and recorded, and an identity that would not be able to merge, approve or publish its own check.
Limits
What it won’t do, and what comes later.
Laterall three capabilities
- A second coding agentAdded only after it passes control-equivalence tests. Routing would never downgrade enforcement.
- Dependency-ordered and parallel stagesLarger changes would split into stages that run in dependency order, with independent authorized stages running side by side.
- An organization execution poolAuthorized stages scheduled by dependency, capacity, budget and policy, including freeze windows.
Missing permissions are not proof of isolation, so the environment itself would be tested.
Tests the agent writes would count only as supplemental evidence.
Content the agent reads can try to redirect it.
An allowlist, held-out keys and review would limit the damage; exfiltration through allowed channels can’t be fully excluded.
The first prototype would run one implementation stage per change.
Run03
Which coding agents does Assent run?
The first managed adapter is planned to be Claude Code, running in an isolated runner that Assent would operate. A second adapter would follow only after it passes control-equivalence tests.
Agents you run yourself, outside Assent, would receive an advisory export. We make no claim of mediated actions, reliable pause or complete audit for those runs.
Who pays for agent compute?
Every offer would state it up front: either your organization’s own provider accounts, or usage managed by Assent with a visible meter and caps. Personal subscriptions would never be pooled.
Can the agent change the checks it is judged by?
No. Protected checks would run from a pinned copy registered outside the workspace.
Design partners
Bring one recent cross-team change.
We reconstruct it with you before showing a solution.
Each stage earned by the one before
Concept diagram
- 01Conversation
- 02Assisted comparison
- 03Shadow analysis
- 04Bounded evaluation
The program ends with a dated decision to continue, revise or stop.
Will it merge or deploy on its own? Not in the first evaluation: people approve decisions and merge. FAQ