It acts at machine speed inside an envelope you wrote. High-risk actions wait for a person. Nothing goes unlogged.
{
"decision": "revoke_idle_token",
"actor": "agent",
"policy": "nhi-envelope@v3 / machine_speed",
"subject": "svc-vendor-sync",
"reason": "no activity for 41 days (limit 30)",
"evidence": "sha256:9f3a…c41e",
"prev": "sha256:71c0…08bd",
"reviewer": null
}
Illustrative ledger entry. A machine-speed decision has no reviewer; a checkpoint decision names one. Not a shipping file format.
Autonomy is only trustworthy when its boundary is explicit. These limits are written into the policy model before the agent ships.
Every action class is assigned a mode before the agent runs: machine-speed, checkpoint or human-gated. The agent cannot reclassify an action, widen its own scope or grant itself access. Changing the envelope is itself a human-gated, logged event.
Every decision, automatic or human, including the actions it chose not to take, is written to the ledger with a chain of custody as it takes effect.
Vault items are encrypted on the device with AES-256 and stay ciphertext in Sequrely’s cloud. Decisions are made on signals and policy, not on your secrets.
Deletions, vault exports, scope widening and access to systems you flag as critical are human-gated by default. The agent cannot move them out of that class.
The digital twin learns a baseline in observe mode first. Enforcement starts when you turn it on, per action class, not when the agent decides it is ready.
Three modes, assigned per action class. An example starting envelope.
Reversible, low-blast-radius actions: ending idle sessions, rotating an expired share, containing an identity whose drift score crosses the line you set. Executed in seconds, sealed, reviewable.
The agent prepares the decision and the evidence, then waits. A named approver signs off in one tap before it runs. Just-in-time grants and new-device authorizations live here.
Deletions, exports, scope changes, policy changes and access to systems you flag as critical. The agent can recommend; only a human can execute. Nothing moves this class down.
Agents get twins too; theirs are tighter, because a deploy bot has no reason to be curious.
A deploy bot’s token is presented from a network it has never used.
The twin flags token reuse plus new context. Risk crosses the envelope’s threshold.
revoke_on_token_reuse is a machine-speed action in this scope. No human is needed yet.
The token is revoked and the credential rotated. The CI runner picks up the new secret.
Inputs, score, mode, action and actor are written and hash-chained. The security lead sees it in the ledger, not in a 03:00 page.
Agent and human rows share one ledger. That is what makes bounded autonomy inspectable.
Illustrative investigation ledger. Example row: 09:41:02, Sequrely agent, Ended idle session · svc-payroll-bot · idle 31m, status Revoked.
Each entry carries the hash of the previous one. Edit a line and every line after it stops verifying. Export the chain as evidence for SOC 2 or ISO 27001 controls.
Illustrative ledger. Live telemetry is shown in product. Identifiers are fictional.
The targets the enforcement model is designed to hit. They are not customer results.
Illustrative design targets from the Sequrely enforcement model: autonomous triage inside the policy envelope and fewer alerts routed to people. Not measured customer outcomes.
An agent with live access to authenticated sessions is the largest trust surface in the product. It ships last, and only after review.
Encrypted vault, passkeys and TOTP, time-limited sharing with audit trail, organizations with roles. The lifecycle the agent will run is already in place.
Multi-step login completed by the agent on a real target, time-boxed, measured and written up. Findings decide whether it is productized.
Real-time connection to authorized browser sessions, managed login and logout, anomaly detection. Gated behind a written threat model and a planned external security review before any general availability.
Status as of the latest roadmap review. Research items may not ship. A design-partner program is forming; ask about it in a demo.
Low-risk decisions execute at machine speed. High-risk actions always route to a human.