# Escrow Evaluator: Agent Deliverable Verdict (ERC-8183) (`calcio_you/escrow-evaluator`) Actor

Neutral evaluator for agent-to-agent jobs: spec + deliverable -> pass/partial/fail, score, checked criteria and a signed EIP-712 attestation (ERC-8183 complete/reject reason). Holds no funds, sends no transaction. Pay per evaluation.

- **URL**: https://apify.com/calcio_you/escrow-evaluator.md
- **Developed by:** [Novarithm](https://apify.com/calcio_you) (community)
- **Categories:** AI, Developer tools, Automation
- **Security:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

Pay per event

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Escrow Evaluator: Neutral Verdict on an Agent Deliverable (ERC-8183)

A neutral third party for agent-to-agent work. Send the **job spec** (free text with measurable requirements, or JSON criteria) and the **deliverable** (text, JSON or a public URL); get a **verdict (pass / partial / fail)**, a **0-100 score**, each **checked criterion**, and an **EIP-712 attestation** whose digest is a ready-to-use bytes32 `reason` for ERC-8183 `complete(jobId, reason, optParams)` or `reject(jobId, reason, optParams)`.

Deterministic rule engine (word/char limits, required and forbidden terms, regex, JSON validity/fields/types, item counts, language, headings, links, CSV/Markdown format). Requirements rules cannot verify are flagged as soft.

### Input

| Field | What it does |
|---|---|
| `jobs` | Objects `{"spec": "...", "deliverable": "...", "job_id": "42", "contract": "0x...", "threshold": 80}`. One charged evaluation each. |
| `attestationTokens` | Tokens to verify (`attestation.token` from an evaluation). |
| `queries` | Advanced raw queries (`evaluate_deliverable`, `verify_attestation`). |
| `maxQueries` | Safety cap (default 1000). |

### Signing key: read this

- **In this Actor**, attestations are signed with an **ephemeral test key generated for each run** (Base Sepolia 84532 only, mainnet refused). They prove the run's result, but they are not linked to a permanent evaluator identity.
- For attestations signed by **Novarithm's permanent production evaluator key `0xD999A24d377086a2Fa887491f2986033Bfc3E26C`** (Base mainnet 8453 by default), use the hosted pay-per-call endpoint (x402, USDC on Base): https://gogeta2-u35175.vm.elestio.app/agents/v1/escrow/evaluate (catalog: https://gogeta2-u35175.vm.elestio.app/agents/catalog).
- The evaluator **never holds funds and never sends transactions**: it evaluates and signs off-chain.

### Pricing

Pay per event: **$0.25 per evaluation**, **$0.001 per attestation verification**. Specs that contain no checkable requirement, empty deliverables and invalid input are **never charged**.

### Limits (honest)

- Subjective quality (style, factual accuracy) is not judged; such requirements are marked soft.
- Spec ≤ 4,000 characters, deliverable ≤ 6,000 (otherwise pass a URL).
- Indicative evaluation, not legal or financial advice.

# Actor input Schema

## `jobs` (type: `array`):

Objects {"spec": "...", "deliverable": "...", "job_id": "42", "contract": "0x...", "threshold": 80}. One charged evaluation each.

## `attestationTokens` (type: `array`):

attestation.token values from an evaluation (same run key).

## `queries` (type: `array`):

e.g. \[{"endpoint": "evaluate_deliverable", "params": {"spec": "...", "deliverable": "..."}}]

## `maxQueries` (type: `integer`):

Safety cap: only the first N checks of the input are processed.

## Actor input object example

```json
{
  "jobs": [
    {
      "spec": "Write a product description in English of at least 40 words. It must mention \"waterproof\" and \"lightweight\". Include a title.",
      "deliverable": "# TrailLite Jacket\n\nThe TrailLite is a waterproof, lightweight shell built for hikers who move fast. It packs into its own pocket, weighs 280 g and keeps you dry in sudden storms. The price is $129 with free returns for 30 days, and it comes in four colours for men and women.",
      "job_id": "42"
    }
  ],
  "attestationTokens": [],
  "maxQueries": 1000
}
```

# Actor output Schema

## `results` (type: `string`):

All result items in the default dataset (JSON).

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "jobs": [
        {
            "spec": "Write a product description in English of at least 40 words. It must mention \"waterproof\" and \"lightweight\". Include a title.",
            "deliverable": "# TrailLite Jacket\n\nThe TrailLite is a waterproof, lightweight shell built for hikers who move fast. It packs into its own pocket, weighs 280 g and keeps you dry in sudden storms. The price is $129 with free returns for 30 days, and it comes in four colours for men and women.",
            "job_id": "42"
        }
    ],
    "attestationTokens": []
};

// Run the Actor and wait for it to finish
const run = await client.actor("calcio_you/escrow-evaluator").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "jobs": [{
            "spec": "Write a product description in English of at least 40 words. It must mention \"waterproof\" and \"lightweight\". Include a title.",
            "deliverable": """# TrailLite Jacket

The TrailLite is a waterproof, lightweight shell built for hikers who move fast. It packs into its own pocket, weighs 280 g and keeps you dry in sudden storms. The price is $129 with free returns for 30 days, and it comes in four colours for men and women.""",
            "job_id": "42",
        }],
    "attestationTokens": [],
}

# Run the Actor and wait for it to finish
run = client.actor("calcio_you/escrow-evaluator").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "jobs": [
    {
      "spec": "Write a product description in English of at least 40 words. It must mention \\"waterproof\\" and \\"lightweight\\". Include a title.",
      "deliverable": "# TrailLite Jacket\\n\\nThe TrailLite is a waterproof, lightweight shell built for hikers who move fast. It packs into its own pocket, weighs 280 g and keeps you dry in sudden storms. The price is $129 with free returns for 30 days, and it comes in four colours for men and women.",
      "job_id": "42"
    }
  ],
  "attestationTokens": []
}' |
apify call calcio_you/escrow-evaluator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,calcio_you/escrow-evaluator"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/gtcFDb5imPlMYWFdJ/builds/oHEZ1h0K2TOgbIwRw/openapi.json