Agentic Governance™ with Authority Finality™

Before your AI agent acts,
one API call proves it was allowed.

Was the action allowed? Can you prove what happened? Did it close cleanly? The KYE™ Authority API answers all three on every consequential action (allow, deny or require approval) and returns a signed receipt your auditor can verify offline, years later. Know Your Entity™ at t=0: identity asks who; KYE™ proves whether it was allowed, the instant the action forms.

Decision centre: chain of authority, admissibility, finality

Computed

You learn: Who decided what, along which chain, why a request was held or denied, and that the record is final and verifiable. You can: Watch decisions arrive; approve as the delegate (the initiator cannot), verify a seal, revoke a delegation.

Approver's phoneDara Quinn, head of procurement
  1. KYE™ policy decision point

    Procurement agent orders above its approval threshold

    approval_threshold_breach

    ProcurementNeeds approval

    Chain of authority

    1. Orrin Logistics (demo) Principal
    2. Dara Quinn, head of procurement kye:authority:orrin.example:procurement-head-2026
    3. Procurement agent kye:authority:orrin.example:proc-04-2026q4
Approver consoleDara Quinn, head of procurement
  1. KYE™ policy decision point

    Drafting agent prepares a disclosure letter, with redaction

    permission_granted

    LegalAllowed

    Decision record sealed

    1. Decision allow_with_constraints
    2. Obligations kye:obligation:redaction

    ff8305bc6290ca7ef2d60b6290c4c2712c62b1280faf28be46d896685fdea90e

  2. KYE™ policy decision point

    Credit agent acts outside its jurisdiction

    jurisdiction_unsupported

    Financial servicesDenied

    Decision

    1. not_revoked grant in force
    2. within_time_window 2026-10-14T09:09:20Z before 2027-01-12T00:00:00Z
    3. action_in_scope credit.line.approve in [credit.line.approve]
    4. purpose_matches lending.adjudicate = lending.adjudicate
    5. within_jurisdiction US in [GB, IE]
    6. within_constraints GBP 4,200.00 ≤ GBP 25,000.00
agent-decisionsAgent platform team (demo)
  1. KYE™ policy decision point

    Accounts-payable agent pays a supplier invoice

    permission_granted

    Agent paymentsAllowed

    Chain of authority

    1. Brightmoor Retail (demo) Principal
    2. Ana Ruiz, finance lead kye:authority:brightmoor.example:finance-lead-2026
    3. Accounts-payable agent kye:authority:brightmoor.example:ap-11-2026q4
CISO dashboardCISO (demo)
  1. KYE™ policy decision point

    Clinical summarisation agent asks to read records for marketing

    permission_missing

    Healthcare data accessDenied

    Decision

    1. not_revoked grant in force
    2. within_time_window 2026-10-14T09:05:31Z before 2027-01-01T00:00:00Z
    3. action_in_scope record.read in [record.read, record.summarise]
    4. purpose_matches marketing.outreach ≠ clinical.summarise
    5. data_class_in_scope [health.record] in [health.record]
    6. within_jurisdiction GB in [GB]
  2. KYE™ policy decision point

    HR operations agent acts on a revoked delegation

    delegation_revoked

    HRDenied

    Signal

    1. Regional treasurer, EU Revoked
    2. Treasury agent (fx-router) Revoked by cascade
How this widget is built
Demonstrates
Decision feed and approvals
Components
  • Policy decision point (evaluate, kye_decide)
  • Chain of authority
  • Admissibility checks
  • Decision records and evidence packs
  • Revocation cascade
Flow
Each decision lands on the device of whoever must know or act: approvals on the approver's phone, denials on the CISO dashboard, allows in the team channel. Tapping one opens its chain, checks, seal or cascade. Architecture diagram
Used on
  • /examples/: On the examples page; it plays when scrolled into view (Play/Pause).
  • /: The home page, right after its opening.
  • /terminal/: The terminal: the decision centre on its devices.

The Authority Simulator™: pick a request, watch KYE™ decide

Demo data

You learn: Why an agent's request is allowed, held for approval or refused, and that the refusal lands before the side effect. You can: Pick a case and run it.

A rule-based execution agent places a small GBP 8,500 hedge adjustment on a permitted instrument — comfortably inside the desk's auto-approval limit. Nothing needs a human.

Action
trading.order_place
Purpose
place a small hedge adjustment within the desk mandate
Instrument
EQ:VOD.L
Side
buy
Amount
8,500

Allowed Passed every stage permission_granted

  1. The agent proposes the action

    KYE™ policy decision point

    Subject, action, purpose and context, as sent to KYE™.

  2. KYE™ resolves authority and purpose

    KYE™ policy decision point

    Delegation, scope, thresholds and approvals at decision time.

  3. KYE™ decides and seals

    KYE™ policy decision point

    Allow, require approval or deny, with a reason code, sealed into the Evidence Pack™.

  4. The side effect commits

    KYE™ policy decision point

    Only an allowed action reaches the rail; a held or refused one stops here.

How this widget is built
Demonstrates
KYE™ runtime decision (kye_decide)
Components
  • Demo scenario registry (kye.demo_scenario.v1)
  • Runtime evaluate engine
  • Reason Code Dictionary™
  • Evidence Pack™
Flow
Request → authority and purpose resolved → decision with reason code, sealed → the side effect commits only when allowed. Architecture diagram
Used on
  • /simulator/: The simulator itself: every case is runnable.
  • /: The simulator itself: every case is runnable.
  • /lab/: The simulator itself: every case is runnable.

Authority Finality™KYE Protocol™ enforces authority while the action is forming: it refuses out-of-scope AI-agent action before the side effect commits, and every refusal and approval is signed, replayable and verifiable offline.

Start where you are

Eight ways in. Every page, at most three clicks away.

Each section lists its groups and their pages; every page also links its neighbours and the pages that share its audience, industry, regulation or stage.

Platform

The platform

What KYE Protocol™ is and how authority is decided, enforced and proven.

  • Overview (The platform) · 9
  • How authority works · 15
  • Operating model (The platform) · 7
  • Concepts and model · 10
  • Maps of KYE™ · 10
  • The category and its governance · 12
63 pages
Products

Products

GovernedUI™, add-ons, authority packs, governed agents and the marketplace.

  • Platform and runtime · 14
  • Add-ons · 30
  • Authority packs and consoles · 17
  • Governed Agents · 46
  • Marketplace and apps · 6
113 pages
Industries

By sector

KYE™ by sector: sector packs, sector solutions and the foundry's packs.

  • Sector pages · 7
  • Sector solutions · 12
  • Sector Pack Foundry™ · 38
57 pages
Compliance

Compliance, conformance & certification

249 frameworks mapped, requirement by requirement, to the KYE™ artefact that enforces them.

  • Coverage · 5
  • Framework library · 11
  • Islamic finance standards · 21
  • Health and life sciences · 23
  • AI governance frameworks · 37
  • Privacy and data protection · 26
  • Security and resilience · 23
  • Audit, tax and accounting · 12
  • Financial services and AML · 27
  • Other frameworks · 69
  • Evidence and reports · 19
273 pages
Solutions

Solutions

Start from your role, your use case or your region.

  • KYE Protocol™ for your role · 15
  • Use cases (Solutions) · 17
  • Sovereign AI (UK · EU · Gulf · Public sector) · 9
  • Journeys · 8
49 pages
Developers

Developer portal

Build with KYE™: the API, SDKs, schemas, connectors and open source.

  • Build · 12
  • API reference · 22
  • Interfaces and connectors · 3
  • Libraries and ecosystem · 2
  • KYE™ Open Source · 12
  • Tools · 9
60 pages
Programs

Engage

Partner, pilot, certify, build and invest with KYE™.

  • Partner programs · 6
  • KYE™ Sector Pack Foundry™ · 1
  • Pilots and proofs of concept · 5
  • Certification and training · 7
  • Marketplace and community · 6
  • Startups and ventures · 3
28 pages
Resources

Resources

Learn, read, check our trust record, and find the legal terms.

  • KYE™ Learn™ · 10
  • Glossary · 191
  • Blog · 9
  • KYE™ Research Library™ · 14
  • Analyst Briefing · 7
  • KYE Protocol™ Trust Center · 8
  • Assess and operate · 3
  • Roadmap and updates · 6
  • Press and brand · 6
  • Legal · 9
  • More pages · 1
264 pages

FAQ

Questions we are often asked

What is KYE Protocol™ in one sentence?

The open contract that answers, for every action a human, service, AI agent, model, tool or workflow takes: who acted, on whose behalf, with what authority, under what scope, with what evidence?

Does KYE™ replace legal agreements or signatures?

No. KYE™ does not replace legal agreements, signatures, or regulatory obligations; it provides the technical control and evidence layer needed to support authority finality, accountability and legally defensible audit trails for agentic systems.

What does one call return?

A decision (allow, require_approval or deny) with a reason code from KYE™'s vocabulary, a replay-stable decision id, a receipt you can verify, and a sealed Evidence Pack™ that can be verified offline from published keys.

How is it different from IAM?

Traditional IAM answers who logged in. KYE™ answers everything that comes after: who or what acted, who they acted for, what authority they had, what capability they used, what state they were in, and what evidence proves it.

Can I try it without signing up?

Yes. The lab and the terminal run in your browser on fictional data; the free tools and the sandbox need no sign-up. An API key comes from the console.

What licence is the protocol under?

Apache License 2.0. KYE™, KYE Protocol™ and Know Your Entity™ are trademarks of the KYE Protocol™ project; see the trademarks page.

How is the information I enter in forms used?

Only to answer that request. Read the details in the and the full privacy policy.

Prove every agent action was allowed;
keep the proof.