Authorization infrastructure for AI actions

Prevent AI workflows from making uncontrolled operational changes.

APPROVEDREJECTEDREVIEW_REQUIRED

One verify call returns APPROVED · REJECTED · REVIEW_REQUIRED

Pause risky actions before CRM, payments, or records change.

Add once in your n8n template—every client workflow inherits the verify step.

Agencies use BiDigest to make AI workflows easier to approve internally and safer to deploy to clients.

  • Add approval checks to AI workflows in minutes
  • Human review for risky actions
  • Execution receipts with receipt_id for every verify call

Partner intake — API key in minutes

What changes for your agency

Ship faster with reusable approval infrastructure—better client conversations, not another compliance workshop.

BeforeWith BiDigest
“Trust us, the AI usually behaves.”Every action returns a receipt and an approval verdict.
Clients fear autonomous workflowsClients see approval controls and human review paths
Rebuild approval logic per clientSame verify call reused in every client template
Harder enterprise security conversationsClearer security and operations story for procurement
Ambiguous blame after incidentsExecution receipts with timestamps and receipt_id

See it on a real workflow

Real n8n capture: verify every path, branch on the verdict, log an execution receipt before CRM or payment tools run.

Real workflow · n8n

Loading workflow preview…

What happens on REVIEW_REQUIRED?

Human-in-the-loop by verdict—your workflow pauses until a human decides, same pattern agencies already use for refunds and CRM writes.

REVIEW_REQUIRED is the operational pause between AI autonomy and human accountability—not a blended trust score.

  1. REVIEW_REQUIRED

    Verify returns a verdict + receipt_id; downstream steps wait.

  2. Notify your team

    Webhook, email, or agency console—wire the channel you already use.

  3. Human approves

    Operator reviews context; approves or rejects in your tool of record.

  4. Workflow resumes

    Continue the automation with the receipt on file for the client.

Start with one protected workflow

Price by protected workflows and verify volume. Add approval infrastructure to automations—not seat licenses or observability dashboards.

Starter

Free

Solo builders and first client demos

  • 1 protected workflow
  • Low verify volume
  • Execution receipts + REVIEW_REQUIRED branching
  • Simulator access
Start with protected refund template

Team

From $99/mo

n8n / Make agencies shipping client automations

  • Multiple protected workflows
  • Higher verify volume band
  • Review-required gating before Stripe / CRM
  • Receipt logging on every path
Open agency console

Growth

From $500/mo

Agencies with reusable templates across many clients

  • Template library + audit exports (roadmap)
  • Shared receipt management
  • Priority support
Talk to us

Regulated enterprise deployments use scoped authorization architecture—not self-serve checkout. Scoped authorization assessment

How it works

  1. 1

    Your AI workflow proposes an action

    Refund, CRM update, payment, claim, or copilot step—whatever you already automate.

  2. 2

    BiDigest returns a verdict

    APPROVED, REJECTED, or REVIEW_REQUIRED in one HTTP call—before money, records, or approvals change.

  3. 3

    You store the execution receipt

    Verification receipts for clients, disputes, and enterprise onboarding—log receipt_id in every run.

5-minute integration

Copy, paste, verify—then reuse the same verify call in every client template. Not per-client consulting—reusable infrastructure.

[COMING SOON] Typed npm SDK for agencies. Today: copy fetch or curl below (works with any stack).

const res = await fetch('https://bidigest.com/api/v1/admissibility/verify', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.BIDIGEST_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    jurisdiction: { regionCode: 'us-fed', industrySector: 'financial' },
    intent: {
      agentId: 'agency-agent:client-acme',
      actionType: 'refund_approval',
      proposedPayload: { action: 'refund_approval', amount: 500, clientId: 'client-acme' },
    },
    sessionContext: {
      sessionId: 'session-acme-refund-001',
      userId: 'support_agent',
      sessionStartTime: new Date().toISOString(),
    },
    groundTruthBinding: {
      domain: 'agency-automation-demo.bidigest.com',
      regulatoryId: 'AGENCY_AUTOMATION_DEMO_V0',
    },
  }),
});
const data = await res.json();
// Map API response → agency verdict (see /partners/ai-automation/recipes)
Full HTTP recipes for n8n, Make, and Zapier

Works inside workflows built with

HTTP Request, webhook, or REST only—no native n8n/Make/Zapier marketplace apps yet. Open Integration recipes for copy-paste curl.

  • n8n
  • Make
  • Zapier
  • OpenAI Agents
  • LangChain
  • CrewAI
  • Flowise
  • Langflow
  • Retool
  • HubSpot
  • Salesforce

Learn the operational model

Verdict reference & topology
AI agent

BiDigest verify

APPROVEDREJECTEDREVIEW_REQUIRED
CRM · payments · ERP
Returns exactly one verdict per call.

Inline authorization check

Verify the proposed action before CRM, billing, or payments change—then branch on a single verdict.

Developer path: POST /api/v1/admissibility/verify — copy-paste recipes on this site.

Examples: AI actions → verdicts

Train clients to think in operational authorization—not chatbot moderation.

Monitoring is not authorization.

AI actionVerdict
Approve $5,000 refundREVIEW_REQUIRED
Delete CRM contactREJECTED
Read FAQ / low-risk lookupAPPROVED
Trigger invoice paymentREVIEW_REQUIRED
Escalate support ticket with billing changeREVIEW_REQUIRED
Why AI workflows now require authorization

Why agencies are adding approval infrastructure

AI workflows are moving from generating text to changing records, approving payments, and triggering operational actions.

Clients increasingly ask: “What controls the action?” Agencies that ship authorization look responsible—not reckless.

  • Monitoring after the fact is no longer enough for higher-trust client deals
  • Shipping without approval infrastructure will eventually look negligent to procurement
Observe → Review → Enforce rollout

Start lightweight

Pick a mode—no policy workshops on day one. Most agencies begin with Observe or Review; add Enforce when clients require hard stops.

APPROVEDREJECTEDREVIEW_REQUIRED
ModeWhat happens
ObserveNowLog receipts only
ReviewNowPause risky actions
EnforceOpt-inStop on REJECTED
More workflow examples

Real agency use cases

  • Refund approval bots

    Auto-approve small refunds; REVIEW_REQUIRED above your threshold.

  • AI SDR workflows

    Gate outbound sends and CRM writes before they hit production.

  • CRM enrichment agents

    Block destructive updates; approve high-impact field changes.

  • Support escalation agents

    Pause ticket actions that need a human sign-off.

  • Insurance claim review flows

    Receipt every decision for regulated client accounts.

  • Invoice approval agents

    Verify payment and billing actions before execution.

Partner onboarding

Get started in under 5 minutes

Trust signals agencies use in decks, workflows, and client QBRs—partner intake unlocks co-branding.

  • Protected by BiDigestWorkflow trust mark
  • Approval receipts enabledPer-run proof
  • Human review enforcedREVIEW_REQUIRED path

Connect, pick a workflow type, copy a recipe, run a live verify—no policy mapping on day one.

  1. 1. Protect your first workflowPartner intake provisions your org and API key. Protect your first workflow
  2. 2. Pick a workflow typeRefunds, CRM, claims, payments, or internal ops.
  3. 3. Copy an integrationcurl, n8n, Make, or TypeScript. Open HTTP recipes
  4. 4. Run a live verifySimulator or your stack—every run returns a verdict + receipt_id. Try a live verify
  5. 5. Ship to every clientAdd the same verify call to every client template; console shows REVIEW_REQUIRED queue. Agency console

Protected workflow templates

Download n8n JSON from recipes—refund and CRM update agents ship today; more packs follow demand.

  • Protected Refund Agent (shipped)
  • Protected CRM Update Agent (shipped)
  • Protected Invoice Approval Flow
  • Protected SDR Agent
  • Protected Claims Review Flow

Agency console

Integration recipes

No marketplace download—use HTTP Request (n8n), Webhook (Make), or POST (Zapier) with the curl body below.

Open full HTTP recipes (curl, n8n, Make)

Starter rules (included)

Defaults ship in code—customize via verifyIntent thresholdRules. No framework workshop required.

WorkflowDefaultOutcome
Refund over $500Human review before bindREVIEW_REQUIRED
refund_approval / wire_transfer / coverage_changeAlways reviewREVIEW_REQUIRED
CRM contact deleteDeny in examplesREJECTED
Policy / FAQ lookupAuto-approve when API allowsAPPROVED
Developer docs

Developer docs

n8n · Make · Zapier · LangChain · OpenAI Agents SDK · CrewAI · Flowise · custom backends

Architecture (one call)

AI agent / workflow
    → BiDigest verify API
    → APPROVED | REJECTED | REVIEW_REQUIRED
    → CRM · ERP · payments · claims

Copy-paste examples

Verify from your backend—map to APPROVED, REJECTED, or REVIEW_REQUIRED.

{
  "admissibility_status": "APPROVED",
  "reason_code": "200_ADMITTED",
  "decision_receipt": { "receipt_id": "rcpt_84721…" }
}

Verify endpoint: POST /api/v1/admissibility/verify

[COMING SOON] Typed npm SDK for agencies. Today: copy fetch or curl below (works with any stack).

curl -sS -X POST "https://bidigest.com/api/v1/admissibility/verify" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jurisdiction": { "regionCode": "us-fed", "industrySector": "financial" },
    "intent": {
      "agentId": "agency-agent:client-acme",
      "actionType": "refund_approval",
      "proposedPayload": { "action": "refund_approval", "amount": 500, "clientId": "client-acme" }
    },
    "sessionContext": {
      "sessionId": "session-acme-refund-001",
      "userId": "support_agent",
      "sessionStartTime": "2026-05-17T12:00:00.000Z"
    },
    "groundTruthBinding": {
      "domain": "agency-automation-demo.bidigest.com",
      "regulatoryId": "AGENCY_AUTOMATION_DEMO_V0"
    }
  }'

Demo policy defaults (integrators): agency-automation-demo.bidigest.com · AGENCY_AUTOMATION_DEMO_V0

When the verdict is REVIEW_REQUIRED

  1. Branch on REVIEW_REQUIRED—not only HTTP 403.
  2. Notify a human (Slack, email) with receipt_id.
  3. Continue or stop after human decision.

What BiDigest is not

  • Not an LLM vendor or chatbot platform
  • Not observability-only or a blended AI safety score
  • Not native n8n, Make, or Zapier marketplace connectors (HTTP only today)
  • Not day-one governance transformation or policy workshops
  • Not kernel or network severance on this page—API verdict branching in your workflow
Enterprise deployments

Enterprise deployments

Same verify API for higher-trust programs—separate enterprise hub for audits and trustee paths (not required for agency HTTP integrations).

Enterprise governance hub · Legacy visibility agency program

Sovereign KB · IFQ · per-LLM — ask here