Ask the model to behave.
A model can be persuaded, confused or simply wrong, so a rule it is told to follow is only as strong as its compliance. Inktomi’s rules sit outside the model; the model never holds the authority.
Inktomi is the first product built on Constitutional Computing. An agent may propose an action; that does not give it authority to act. Inktomi evaluates the proposal before execution, and the integrated tool verifies a single-use permit before it commits the change.
One run, every decision
A decision
agent-1 asked to write a file.
✕ Refusedwrite_file {
"path": "demo/workspace/.env",
"content": "[redacted: secret material]"
}3 of 24 checks failed
no_secret_materialtarget_not_protectedno_approval_requiredThe file was never written. The decision, its policy version and all 24 checks are kept as evidence.
A replay
A refused write by gemini-mcp, derived again from its recorded inputs under the rule running now.
rule 47f121a7…922b1eMost controls for AI agents either instruct the model or watch traffic as it passes. Inktomi checks each consequential action at every stage it governs, from the agent host to the tool, and the integrated tool itself refuses to act without a single-use permit for that exact action.
A model can be persuaded, confused or simply wrong, so a rule it is told to follow is only as strong as its compliance. Inktomi’s rules sit outside the model; the model never holds the authority.
A gateway, including an MCP gateway, controls the calls routed through it. A call that goes around it, straight to the tool, is not stopped. A tool that requires an Inktomi permit refuses a direct call without one.
They answer whether a request fits the rules, or whether a credential grants access to a system. Inktomi binds the decision to the exact action and its arguments, issues a signed single-use permit, and records which rule version decided it.
Inktomi works alongside these controls, not instead of them. Tools outside its enforcement path need their own controls; a coverage report shows which paths a deployment governs.
A policy engine asks whether a request satisfies a rule set. Inktomi goes further: it binds authority to the proposed action, the governing version and the evidence required before that action may become committed state.
Precedence between rules is specified mathematically, so the outcome does not depend on the order in which rules happen to be evaluated.
Rules are bound to a reviewed, signed version. Every decision records the version it was made under.
Replay derives the decision again from the recorded inputs and governing version. Agreement is shown; a changed rule or altered record cannot silently stand in for the original.
A credential grants access to a system. It does not settle whether a particular release, payment or record change is authorized.
Inktomi evaluates the proposed call and its arguments. When the requirements are met, it issues a signed, single-use permit. The integrated tool checks that permit before acting.
Authority is bound to the specific operation, target and arguments—not to a general ability to use the tool.
Policy, evidence and any required human approval are bound to that exact action.
A valid permit allows execution. A call without one is refused by the integrated tool.
A gateway controls traffic that passes through it. A tool that requires an Inktomi permit also refuses a direct call without one. Tools outside this enforcement path need their own controls.
Console views of governed agent decisions, replay and reach.
Open the action, its arguments, and the integrity, identity and access checks recorded for it.

Replay derives the decisions again. Reconciliation reports observed activity that the permits do not account for.

Inspect the tools an agent holds, and the tools its policy names but does not make available.

In the self-hosted profile, Inktomi runs on your hosts and at your network edge. Your organization keeps its policies, its identity provider and its approval responsibilities.
Decision service, MCP proxy, approver desk and signed journal. The agent’s own tools connect through the host hook.
Your identity provider authenticates approvers over OIDC. Your proxy enforces network egress. OCSF events export to your SIEM.
Each integrated tool verifies the signed permit. The evaluation establishes how every tool on the selected path performs that check.
| Connects to | Examples | Status |
|---|---|---|
| Agent hosts | Claude Code, Codex, Gemini CLI, Mistral Vibe, Hermes Agent, OpenClaw | Available for evaluation |
| Agent hosts, MCP only | Antigravity: MCP tool calls are governed; its built-in tools are not yet | MCP only |
| Tool servers (MCP) | Your MCP servers | Available for evaluation |
| Identity providers | OIDC-based identity providers; specific products and versions are verified during evaluation | Protocol support |
| SIEM | OCSF event export; destination compatibility is verified during evaluation | Available for evaluation |
| Payment, records and filing systems | Your systems of record | Customer integration |
Start with one workflow. Run it in shadow first, recording what Inktomi would decide, then enforce. Agree tool coverage, acceptance tests, integration effort and end-to-end overhead in your environment. Inktomi’s decision engine is operational; production enforcement integrations are under development, with initial enterprise evaluations targeted for December 2026.
Three checkpoints can refuse in the path. Two observe and report after the fact. The deployment determines which paths are governed.
| Control | What it does | When it acts |
|---|---|---|
| Host control Host hook | Checks the host’s own tool calls before they run. It runs inside the agent’s host, so it is not the last line: an integrated tool still refuses a call without a permit. | Can refuse |
| Tool control MCP proxy and integrated tool | Routes MCP calls through the decision service. Integrated tools verify permits. | Can refuse |
| Network control Your proxy enforces the allowlist | Restricts destinations through your egress proxy. | Can refuse |
| Change detection Workspace watch | Finds changes in the agent’s workspace. | Detects after |
| Credential reconciliation Vendor audit logs | Matches observed vendor activity against permits. | Detects after |
Host, MCP, workspace and reconciliation records write to the signed chain. Egress is enforced and logged by your proxy, outside that chain, so an allowlist error is not caught by the journal. Read all coverage limitations
No. The decision comes from signed, versioned rules evaluated deterministically: the same inputs under the same rule version always produce the same result, and replay can derive it again. Some agent security tools use a model to judge an action’s intent. Inktomi keeps the model out of the decision.
They do different jobs and can run together. Endpoint tools find the agents running on employee devices and control what those agents do there. Inktomi binds authority to one consequential action, and the system that commits it verifies the permit before acting.
Many gateways grant standing approvals: an identity may use a tool, within a scope, until an expiry. Inktomi approves one exact action. The permit is bound to the operation, the tool and its arguments, lasts 60 seconds and can be used once. The next call needs its own decision.
No. Inktomi addresses action-level authorization, enforcement and evidence. Your identity, access, approval and monitoring controls remain in place. Its role alongside your broader governance program is established during scoping.
Kihan’s recorded harness measured the governance decision at 1.22 ms median and 1.62 ms at the 95th percentile. These figures are not end-to-end workflow latency. An evaluation measures overhead on your own path.
The integrated tool does not carry out the call. The decision record captures the outcome and the facts behind it. Where policy requires human approval, the action waits for an approval bound to that exact call.
A scoped workflow, agreed acceptance tests, a decision journal with replay, a coverage report and written findings. Evaluations are paid engagements. Scope and terms are agreed before installation.
Explore Inktomi end to end: how it governs agent actions, handles exceptions, exposes evidence and replay, and fits your environment—with time for your questions.