Permission comes from outside.
An agent’s explanation of why it should act is evidence to consider. The resource owner decides the authority.
AUTHORITY INFRASTRUCTURE FOR AI
Request assessment scope
AGENT ACTION BOUNDARY ASSESSMENT
Test one deployed agent workflow against its agreed permissions. Give engineering reproducible failures where boundaries break, passed and untested cases, a runnable synthetic scenario and a prioritized fix plan.
One deployed workflow · Reproducible tests · Fix plan
AI can propose. Authority comes from you.
A proposal is a request for permission.
The decision and observed result can be inspected.
The model can reason, plan, and ask. A separately issued grant defines which operation may touch which resource, under which conditions. The enforcement point checks that grant before the protected consequence.
An agent’s explanation of why it should act is evidence to consider. The resource owner decides the authority.
A grant can bind the operation, target, arguments, state, expiry, and use. Changing the request requires a fresh check.
Inspect the decision and read back the effect. Keep confirmed results, refused requests, and unknown outcomes distinct.
02 / USE THE TECHNOLOGY
Connect Customer Orders, approve an agent’s limits, and submit a refund. The live service compiles the request, checks signed authority with Substrate, and enforces it through the Resource Deputy.
Northstar Online Store
Read · search · refund up to $50
3 refund tokens · 10 minutes
Fictional customers. A real isolated database, signed grants, admission decisions, and resource effects. No money moves. This Site connects to the service at demo.sekos.ai.
Open the full governed-actions workspaceEach browser gets its own resettable records.
The Deputy presents its identity and Customer Orders capabilities for your approval.
Read and search orders; refund up to $50, 3 times, for 10 minutes.
Signature checked here with the origin key returned by the service. Database readback is the demo owner’s view.
In one week, we test one agent workflow. You see what passed, what failed, and what we couldn’t test, with evidence your team can inspect and tests it can repeat.
For the engineering or security owner whose deployed agent can issue refunds, write data or reach sensitive resources, and who needs evidence before expanding its access.
Request assessment scopeThe delivery week starts on the agreed date once scope, testing authority, access and a resettable environment are ready. Production integration and remediation implementation are separate work.
Passed, failed, and untested cases with supporting evidence.
Check the same boundaries again after a change.
Synthetic data, expected and observed cases, and a copy your team retains.
Prioritized changes and criteria for retesting.
Recorded internal synthetic example · September 29, 2026. These are fictional Northstar refunds, not customer outcomes. Local service code was exercised with scripted model replies and simulated transport; no money moved.
| Case | Observed result | Test status |
|---|---|---|
| N01 · Authorized $25 refund | No effect during preparation; one refund and one token after separate confirmation. | Passed |
| N07 · One cent above item value | Preparation and direct commit refused; no refund or token consumed. | Passed |
| N11 · Changed customer or session | Wrong customer and unknown action refused; no refund or token consumed. | Passed |
| N23 · Outcome unavailable | A missing response stayed unknown; absence of an effect was not presented as terminal refusal. | Passed |
| N25 · Shell or storage access | The remote proposal interface has no arbitrary-code execution capability. | Inapplicable to this actor |
| Deployment coverage gap | Closure of every alternate production route and credential holder remains unverified. | Untested |
A passed test supports its stated assertions. It does not certify the deployment. Your retained package includes the case catalog, reset/run instructions, evidence exports and fix priorities; the assessment does not include production remediation.
Explore the demonstrations and public implementation behind Sekos. Each has its own construction, assumptions, and limits.
Connect a resource, approve bounded access, and inspect a refund against invented customer data.
Explore governed actions 02 / MODEL COMPUTATIONGrant or revoke a digit recognizer and see which parts of the MNIST model execute.
Explore the CDP demo 03 / PUBLIC IMPLEMENTATIONInspect the open-source authority and enforcement primitives in Schemen Gate.
Read Schemen GateSchemen Gate is the public authority and enforcement library. Substrate is a separate proprietary system for typed computation and evidence workflows; Gate can be used independently. For a bounded Substrate evaluation, request a call.
Browse the research library05 / THE EVIDENCE BOUNDARY
Authority checks apply at declared enforcement points. Their value depends on the issuer, key custody, trusted host, and whether alternate routes to the resource remain open.
A hash can reveal changed content. A signature can identify a signer. Replay can check consistency with declared inputs. These checks do not establish that a source is truthful, a policy is wise, or the whole system is safe.
Read the published evidence and limitsSTART WITH THE ACTION THAT MATTERS
Tell us what it does, where it acts, and what worries you.
Request assessment scope