# Agent Constraint Extractor

> Agent Constraint Extractor is a paid API for AI agents from agent-product-normalizer.vercel.app, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-18).

Parses a free-text human request to extract hard constraints, soft preferences, exclusions, budgets, and deadlines into structured form

## Facts

- Endpoint: GET https://agent-product-normalizer.vercel.app/api/v1/extract-constraints
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-constraint-extractor-069077ca
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8XAy7C12INbI0-e3RNOnV

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-constraint-extractor-069077ca
```

Example prompt: Pull the hard constraints, soft preferences, exclusions, budget, and deadlines out of this user message: 'I need a non-stop flight to Tokyo under $800, ideally with a window seat, no layovers in Seoul, and I must leave by March 15.'

## When to prefer this

Use this endpoint when an agent needs to pre-process a raw human request before taking action — especially before searching, filtering, or routing — to ensure it respects the user's mandatory requirements, avoids exclusions, and stays within stated budgets and deadlines. Prefer this over general-purpose text parsing when the downstream task requires distinguishing hard vs soft constraints explicitly.

## Known failure modes

- Input text is too vague or empty — no constraints can be identified, returns empty or null fields
- Text exceeds 20,000 character limit — request rejected with validation error
- Ambiguous phrasing where it is unclear if a constraint is hard or soft — may misclassify preference type
- No budget or deadline present in text — those fields return null or empty
- Service unavailability returns a non-200 HTTP error

## How this service works

Extract hard constraints, soft preferences, exclusions, budgets and deadlines from a human request

## Output

A structured breakdown of the input text containing categorized hard constraints (non-negotiable requirements), soft preferences (nice-to-haves), explicit exclusions (things to avoid), budget limits, and deadline signals — ready for an agent to use when filtering options or routing tasks

## 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"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "maxLength": 20000,
       "description": "Human request containing hard/soft constraints"
      }
     },
     "additionalProperties": true
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-constraint-extractor-069077ca/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-product-normalizer.vercel.app](https://www.zero.xyz/host/agent-product-normalizer.vercel.app/llms.txt)