# Batchloom Citation Evidence for Agents

> Batchloom Citation Evidence for Agents is a paid API for AI agents from batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site, paid per call via x402, $0.99/call, status unknown (last checked 2026-09-14).

Returns a JavaScript agent asset kit (render.mjs and related files with SHA-256 hashes) for verifying literal quotes against public source pages with source offsets

## Facts

- Endpoint: GET https://batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/v1/kit
- Price: $0.99/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/batchloom-citation-evidence-for-agents-2b7a7f42
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_BNXRcu1s5dRI9KJsqDkP4

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 batchloom-citation-evidence-for-agents-2b7a7f42
```

Example prompt: Can you check whether the quote 'the model achieved 94% accuracy on the benchmark' actually appears verbatim in the source article at that URL, and give me the SHA-256 hash and character offset as evidence?

## When to prefer this

Choose this endpoint when an AI agent needs cryptographically verifiable evidence that a literal quote exists within a specific public webpage, including exact character offsets and content hashes. It is particularly suited for fact-checking AI-generated citations, auditing research references, or building MCP-based citation pipelines that require tamper-evident proof of source content. Prefer it over generic web scrapers when you need structured, hash-anchored evidence rather than raw page content.

## Known failure modes

- 402 Payment Required if USDC payment on Base is not attached or insufficient
- Source page is not publicly accessible, returning no evidence
- Quote not found in source page, returning empty or null offsets
- Malformed properties parameter causing schema validation error
- Network timeout fetching the remote public source page
- SHA-256 hash mismatch if source page content has changed since snapshot

## How this service works

Check literal quotes against public source pages. Evidence with source hashes and offsets, for 0.01 USDC on Base. Prepare requests, compare snapshots and connect a local MCP buyer.

## Output

A JSON object containing the Batchloom Agent Asset Kit with an array of files (e.g. render.mjs JavaScript module source), each with its file path, SHA-256 hash, and content. Also includes a kit version string. This kit is used to configure a local MCP buyer for citation evidence verification workflows.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "name": "Batchloom Agent Asset Kit",
  "files": [
   {
    "path": "render.mjs",
    "sha256": "...",
    "content": "JavaScript module source"
   }
  ],
  "version": "1.0.0"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/batchloom-citation-evidence-for-agents-2b7a7f42/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site](https://www.zero.xyz/host/batchloom-studio-0913.xuikatwsicrdsidm.chatgpt.site/llms.txt)