For builders / AI agents & digital assets

Your agent acts.
Prove why.

Equip autonomous agents with structured onchain evidence — and give your team an inspectable decision record before capital leaves.

Watch / response excerptSAMPLE

8G-S-2026-00005-G

A structured record your agent can inspect.

confidence
partial
indicators[]
Unlimited approvalhigh · R025
coverage[]
fixture · available
unknowns[]
Sample record. No live intelligence or safety conclusion.
Two integrated layers

Screen the move. Verify the basis.

01 / Watch API & MCP

What do onchain signals show?

Query any wallet, transaction, token or contract over HTTP or MCP. Receive rule-linked risk indicators, consulted sources and explicit unknowns for deterministic policy handling.

Watch API and MCP guide →
02 / Intelligence Workspace

Does the decision still hold?

Compare proposed actions against delegated mandates, trace changed claims across linked reports, record MFA-authenticated sign-off, and export signed Agent Evidence Receipts.

Intelligence API guide →

Your application orchestrates execution. Watch and Intelligence Workspace use separate scoped credentials so least-privilege boundaries hold end to end.

Built for real agent workflows

Your policy decides. Our evidence informs.

Autonomous payments

Vet every destination.

Evaluate public addresses and chains before settlement. Handle sanctions matches, partial coverage and source outages explicitly in code.

Tokens & permissions

Inspect contract authority.

Surface mint, pause and approval signals where supported. Keep signing keys and final execution strictly inside your own infrastructure.

Recurring renewals

Catch silent changes.

Supplier claims change after initial approval. Flag every linked decision automatically before an agent renews spend.

Agent Action Review & roadmap

Bind every action to its mandate.

Agent Action Review and Ed25519-signed Agent Evidence Receipts are live for early-access teams across 14 network configurations, with independent verification via /.well-known/8thguard-receipt-keys.json. Payment Preflight and RWA Preflight extend this architecture into paid APIs and tokenised real-world assets.

Watch integration

From public identifier to policy decision.

Explore the workflowIllustration · select a step
Explore how a check moves through your workflow

Your agent → Watch

Give the check a clear starting point.

Your agent submits a wallet, transaction or contract and its blockchain. No wallet connection is needed.

subject.kind
What you want to check
subject.chain
The blockchain to consult
subject.value
The public identifier

Inside Watch

Keep the source beside the signal.

Watch consults the available sources and applies versioned rules. Missing evidence stays visible.

coverage[]
Sources consulted, including failures
observations[]
What the evidence shows
rules_version
The rules applied to the check

Watch → Your agent

Understand what came back.

Read the indicators alongside coverage and uncertainty. An empty indicator list does not establish safety.

indicators[]
A signal, severity and rule reference
unknowns[]
What the evidence cannot establish
id
The issued record’s verification ID

Your application

Keep the decision in your workflow.

Your system can continue, pause or ask a person according to its own policy. Watch provides evidence; it does not execute the transaction.

Review
Evaluate the evidence against your policy
Escalate
Ask a person when the policy requires it
Record
Keep the proof with your decision
Interfaces & access

Choose the interface your agent uses.

HTTP API

Access by arrangement

Request public-chain evidence through an authenticated API. Contact the team for an issued key.

Read the HTTP API guide

MCP tool

Source integration

Connect through the Python source adapter with stdio or Streamable HTTP. Requires an authorised source checkout and engine access.

Read the MCP tool guide
Inspect the result

Keep signals and unknowns together.

Coverage and indicators.

The Watch response lists consulted sources, failures and rule-linked signals. An empty indicator list does not establish safety.

A record you can reference.

Keep the issued ID and rules version beside your application’s decision. The example below is synthetic and verifies only as a sample.

Evidence stays data.

Report text must not override your agent’s tools or authorisation. Your system handles execution and any escalation to a person.

Inspect the complete synthetic Watch response · contract 1.0
Snippet
{
  "contract": "1.0",
  "id": "8G-S-2026-00005-G",
  "sample": true,
  "subject": {
    "kind": "transaction",
    "chain": "evm:1",
    "value": "0x3333333333333333333333333333333333333333333333333333333333333333"
  },
  "tier": "quick",
  "issued_at": "2026-10-21T09:00:00Z",
  "rules_version": "2026.10.1",
  "coverage": [
    {
      "source": "fixture",
      "status": "available"
    }
  ],
  "observations": [
    {
      "rule": "R025",
      "text": "Synthetic test evidence only; no live allegation.",
      "source": "fixture"
    }
  ],
  "indicators": [
    {
      "code": "unlimited_approval",
      "severity": "high",
      "rule": "R025"
    }
  ],
  "unknowns": [
    "Sample record. No live intelligence or safety conclusion."
  ],
  "confidence": "partial",
  "next_step": "Run a real check with current source evidence.",
  "verify_url": "https://8thguard.com/verify/8G-S-2026-00005-G"
}
Verify the sample ID →