IARPA Solutions Marketplace · Awardable 2026

    Ship autonomy.Stay in control.

    Let AI agents act for yourbusiness and customers,with limits you set andproof anyone can verify.

    Get Started

    More AI. More access. More consequences.

    Agents now act across systems, data, budgets, payments, and workflows at machine speed. When an agent goes off course, every connection widens the blast radius.

    Different failures. Same governance gap.

    Your agents can already do more. Now you can let them.

    Refund a customer. Update a record. Change access. Decide which actions your agents can take, when they need approval, and independently verify the authorization evidence afterward.

    The right amount. The right payment. Your rules.

    Give agents the authority to request payments, while you define how much they can spend and when approval is needed.

    Explore

    Give agents access without giving away control.

    Let helpdesk agents request a specific group change for a support or contractor account. Okta reference.

    Explore

    Let agents work with data. Keep sensitive changes in check.

    Let administrative agents request changes to permitted fields and the checked version. Synthetic records.

    Explore

    Ship the revision you approved. To the target you intended.

    Review the software revision before an agent requests deployment to a designated service.

    Explore

    Your rules. Their actions. Your control.

    Set the boundaries. Keel enforces them.

    Keel

    ai-platform-prod

    Production

    Overview

    7d rolling window · refresh while visible

    9 actions need your review Waiting

    Keel has paused these actions before execution. Approve or deny each request.

    Anomaly detected184 denied decisions need review in the last 7 days.

    Unauthorized impact

    $4,830.00

    Spend and risk evaluated before execution

    Recent decisions

    View all

    Showing 4 of 12,731 decisions

    Top enforcement reasons

    Inspect the decision behind each control.

    Active controls

    Budget caps

    $5,000/day · $75,000/month

    Enforcing

    Model allowlist

    4 approved models

    Restricting

    Prompt firewall (baseline)

    Baseline enabled

    Enforcing

    Model routing

    Agents use the model they ask for

    Off

    Overage (block-only)

    Budget caps active

    Active

    Permit service health

    Enforcing

    Governed traffic

    12,762

    Last 7 days activity

    Failure rate

    1.4%

    184 failed requests

    Review backlog

    9

    Pending human reviews

    Throughput

    1.3 req/min

    Requests in the last 7 days

    Tracked spend

    $3,142.00

    3/3 integrations ready

    Evidence & trust

    Hash chain (per decision)

    Last check passed

    12,731 records checked

    External checkpoint

    Published

    Latest checkpoint available to check

    Timestamp receipt (TSA)

    Present

    Receipt present

    Compliance exports

    Ready

    Export creation enabled

    Quick actions

    Every decision is a permit.Every permit leaves evidence.

    Zero Trust in action: every request needs an AI Permit before it runs. Allow, deny, throttle, or review—each outcome leaves evidence your team can inspect later.

    AI-PTP

    AI Permit-to-Pay

    Full AI Permit

    Review required

    Waiting for a decision

    If no one approves before the review window closes, nothing runs. The agent must ask again.

    What this action does

    Pay $250,000.00 to one recipient.

    Requested by treasury-agent

    Checked by Keel · exact facts bound to this request

    Amount
    $250,000.00 USD
    Recipient
    Hidden
    Payment rail
    Stripe Payment Intent
    Payment environment
    Test
    Runs
    Once (single use)

    A person must approve payments over $10,000.00

    $ keel-verify export ai-ptrm-a66f7f81.json --reportAI Permit-to-Restart-Machine — Verification ReportEvidence:  VERIFIEDFinding:   Permit decision ALLOW.  Permit: a66f7f81-e371-4512-94f7-36ab51311d75  Decision: allow  Issued: 2026-08-21T20:26:06.875563+00:00  Expires: 2026-08-21T21:26:06.875563+00:00  Subject: df277bd2-2fbe-4fc0-b7a3-cab4b1c8a4b3Authorized action  Action: cloud.machine.restart  Scope: d1503f92-bb36-4bc0-9a13-6c2bcaedeeaa  Target commitment: sha256:ab80413e31aec14baf53596075dd01236b8d28b6f40d941b62036a5a41875fbbAuthenticity  ✓ Evidence bundle structure and signature validAuthorization  ✓ Permit decision signed by the issuing key (issuance-time)  ✓ Permit type and fact profile bound to the signed request  ✓ Exact target facts signed and schema-valid  ✓ Material request facts verified  ✓ Human review transition signed by the issuing keyHuman artifact  Status: Authorized, not dispatched  Presentation: cloud_machine_restart.r1 (keel.presentation_registry.v17)Summary  Keel authorized this subject to restart the bound machine.  No provider dispatch is represented.Verifier 3.30.0Trust mode: (not determined)Semantics profile: keel.pre_pinning_default.v0Verified at: [local run time]Input: sha256:6b2d38f9f4c1fd5cfa0deb943413b7808d727b67610b4cfcdbba2c0609dc99a8
    Full evidence coverage
    Permit decision signature: verified
    Permit type and fact profile: verified
    Exact target facts: verified
    Material request facts: verified
    Human review transition: verified
    Operator approval: not provided
    Counter-signature: not provided
    Co-signer key assertion: not provided
    Co-signature quorum: not provided
    Managed MCP mapping binding: not provided
    Governance interpretation: not provided
    Structural hold evidence: not provided
    Dispatch eligibility: not provided
    Dispatch: not provided
    Closure: not provided
    Revocation: not provided
    Timestamp: not provided

    An auditor in 2035 should need the evidence file and the verifier, not our website, our API, or our continued existence.

    Logs can be edited.
    Evidence can be verified.

    Every AI Permit is backed by signed evidence. It shows what was requested, which checks passed, and what evidence is missing. Anyone can verify it independently without a Keel account. If verification depends on taking our word for it, we’ve failed.

    Not alteredThe report shows that the exported evidence still matches the signed manifest.
    Trust mode visibleThe trust mode is visible near the top, so weak modes cannot look stronger than they are.
    Independently verifiedThe report shows the permit, authorized action, verified checks, and missing evidence.

    One control layer for your agents

    However your agents arrive, Keel adds a provider-neutral authority layer to your existing stack. Integrate once through a single API. Keel applies your rules, ties approvals to the exact action, and records authorization evidence you can independently verify.

    Build

    You build the agent yourself.

    Vercel AI SDK · OpenAI SDK · Anthropic SDK · agent harnesses · your own code

    Compose

    Off-the-shelf parts, shaped by your own logic.

    APIs · MCP tools · webhooks · tool hooks

    Buy

    Complete agents, straight from a vendor.

    wherever they expose an API or tool hook

    Copilots · vendor voice agents · workflow agents · vertical SaaS agents

    Keel
    Agent control infrastructure

    Your rules. Your approvals. Your evidence.

    Models · Tools · Data · Access · Workflows · Payments · Deployments

    See it in action, or find your risk

    Watch how a request is evaluated, enforced, and recorded — or run a free assessment on your stack.

    Free to explore. Production subscriptions use self-service checkout.

    Keel doesn't observe your AI.

    It decides if the request runs.

    Built for production systems where control is non-optional.

    Fails closed

    No silent passthrough.

    If the policy can't be evaluated, the request doesn't run. Safety mechanisms that fail quietly aren't safety mechanisms.

    Enforced before execution

    The invoice isn't the alert.

    Budget and policy enforced before the request reaches your provider.

    Decision-level audit trail

    Hand it to your auditor. Walk away.

    Every decision recorded with policy version, outcome, and reason - at the moment it's made.

    Verifiable without us.

    Your auditor walks the chain themselves.

    No account. No API key. Even if Keel disappears.

    Don't take our word for it.

    Ask your AI if Keel belongs in your stack.

    Have the AI you already use independently evaluate Keel, where it fits, its limitations, and whether you actually need it.

    Copies the question and opens the selected AI service in a new tab.

    We provide the question. Your AI provides the answer, including if the answer is no.

    You already started building the control layer.We finished it. One integration.Audit-ready on day one.

    One integration. Authorization, budget enforcement, audit trails, and multi-tenant isolation — governed before execution, not observed after.