VAIBot V2 — Governance API

The AI agent circuit breaker

Intercept every agent tool call. Classify the risk. Enforce your policy. Issue a governance receipt — all before a single command executes.

Governance, not just logging

VAIBot acts before execution — not after. Every benefit below happens before the agent's tool call runs.

Risk classification

Every proposed action is scored low, medium, high, or critical based on tool type, target path, and scope — before a single byte changes.

Human-in-the-loop

High-risk actions pause and wait for your approval. Approve, deny, or escalate — every decision is logged against the receipt.

Policy enforcement

Define workspace boundaries, destination allowlists, and tool restrictions. Violations are hard-denied — no retries, no workarounds.

Governance receipts

Every decision produces a structured receipt: agent ID, action, risk level, policy reason, timestamp, and outcome. Searchable, exportable, on-chain-anchorable.

Three scenarios. One circuit breaker.

Select a scenario below to see how VAIBot classifies the risk, makes a policy decision, and issues a receipt.

VAIBot V2 — Live demo

The AI agent circuit breaker

An agent proposes an action. VAIBot classifies the risk, enforces your policy, and issues a governance receipt — all before a single command executes.

Review risky actions before they run
See exactly why the policy intervened
Keep a durable audit trail for every decision
Proposed action

Approval required — Unknown deploy target

VAIBot pauses high-risk outbound actions until a human approves.

Agent
Clawd M.
Tool
exec
Command
curl -X POST https://deploy-preview.example.com/release
Policy decision
High riskApproval required

Destination is outside the configured allowlist — execution paused pending review.

What happens next

⏳ Awaiting your approval — click Approve to unblock this agent action.

Governance receipt

Deploy webhook to unapproved destination

Approval requiredHigh risk
Decision timeline
Proposed
Agent action
Classified
High risk
Decision
Approval required
Outcome
Awaiting approval
Why

Destination is outside the configured allowlist — execution paused pending review.

Next step

⏳ Awaiting your approval — click Approve to unblock this agent action.

Human review required

Approve to let the agent proceed, or deny to block this action.

This is a live demo — no real action will execute.

What you get

Your governance dashboard

Every agent decision — allowed, gated, or denied — lands here. Approve pending actions inline, filter by risk or API key, export to CSV.

Governance dashboard
Demo data
47Total
31Allowed
9Gated
7Denied
2Pending
3Critical
2 actions pending approval
ApproveDeny
WhenActionRiskDecision
Apr 23 · 14:32
rm -rf /workspace/staging-data
deploy-agent · exec
CriticalDenied
Apr 23 · 14:28
curl -X POST https://deploy-preview.example.com/release
ci-agent · exec
HighGated
Apr 23 · 14:19
git push origin main --force
dev-agent · exec
HighGated
Apr 23 · 14:11
git push origin feature/auth-refactor
dev-agent · exec
MediumAllowed
Apr 23 · 13:58
npm install --save-dev @types/node
dev-agent · exec
LowAllowed
Showing 5 of 47 decisions · Sign in to see your live data

Works with every agent

Claude Code
Gate every Bash, Write, and Edit call before it executes
Cursor
Add audit trails to AI-assisted file and terminal operations
LangChain / AutoGen
Wrap tool execution loops with policy enforcement
Custom agents
One POST endpoint integrates with any HTTP-capable agent