# Agent Guild Preflight Deep Trust Check

> Agent Guild Preflight Deep Trust Check is a paid API for AI agents from agent-guild-5d5r.onrender.com, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Performs a deep pre-delegation trust assessment of an HTTP endpoint or agent counterparty, returning policy decision, behavioral history, corroboration, and index status.

## Facts

- Endpoint: GET https://agent-guild-5d5r.onrender.com/preflight/deep
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-guild-preflight-deep-trust-check-0abc0654
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hAD73IJt3oB3r9zrx6Dn6

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-guild-preflight-deep-trust-check-0abc0654
```

Example prompt: Before my agent delegates the payment task to that external endpoint at api.exampleagent.com, run a deep preflight trust check on it so I know if it's safe to proceed.

## When to prefer this

Choose this deep preflight endpoint when you need the most comprehensive trust assessment before delegating to or paying an autonomous agent counterparty — especially when behavioral drift, independent corroboration, and a signed policy decision are all required. Use it over lighter-weight trust checks when the stakes (financial settlement, sensitive data, irreversible actions) are high enough to justify the $0.02 per-call cost and slightly higher latency compared to shallow preflight variants.

## Known failure modes

- Endpoint not indexed — index_status may indicate 'unknown' or 'unreachable', limiting history and corroboration data
- Insufficient corroboration sources — fewer than 2 independent sources reduces confidence in verdict
- Payment failure via x402 — if USDC payment of $0.02 is not accepted, the call is rejected before assessment
- Target endpoint unreachable — history and reachability checks may fail if the subject URL is down
- Schema mismatch — missing required 'type' or 'method' fields in input returns a 400-level error

## How this service works

Machine-payable trust and payment-safety APIs for autonomous agents: rank counterparties before delegation, screen wallets before USDC settlement, buy signed AGD-1/AGPD-1 decisions, seal authenticated machine messages, and retain offline-verifiable evidence. Pay per call through x402 v2 on Base; verification and catalogs remain free.

## Output

Returns a JSON object with: trust tier ('deep'), a policy object including decision (allow/block) and reasons, a history object with observation count and drift indicators, a corroboration object with independent sources, and an index_status string (e.g. 'recently_reachable'). Also includes a top-level verdict ('pass'/'fail'), lists of checks performed, failed checks, and unknowns.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "headers": {
     "type": "object",
     "additionalProperties": {
      "type": "string"
     }
    },
    "queryParams": {
     "type": "object",
     "additionalProperties": {
      "type": "string"
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "schema": {
     "type": "object"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "schema": {
  "type": "object",
  "required": [
   "tier",
   "policy",
   "history",
   "corroboration",
   "index_status"
  ],
  "properties": {
   "tier": {
    "type": "string",
    "const": "deep"
   },
   "policy": {
    "type": "object"
   },
   "history": {
    "type": "object"
   },
   "index_status": {
    "type": "string"
   },
   "corroboration": {
    "type": "object"
   }
  }
 },
 "example": {
  "tier": "deep",
  "checks": [],
  "failed": [],
  "policy": {
   "reasons": [],
   "decision": "allow"
  },
  "history": {
   "drift": [],
   "observations": 4
  },
  "verdict": "pass",
  "unknowns": [],
  "index_status": "recently_reachable",
  "corroboration": {
   "sources": [],
   "independent_sources": 2
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-guild-preflight-deep-trust-check-0abc0654/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-guild-5d5r.onrender.com](https://www.zero.xyz/host/agent-guild-5d5r.onrender.com/llms.txt)