# Agent Next Step Selector

> Agent Next Step Selector is a paid API for AI agents from agent-product-normalizer.vercel.app, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-18).

Ranks a list of candidate next actions against the current agent state to recommend the best next step

## Facts

- Endpoint: GET https://agent-product-normalizer.vercel.app/api/v1/choose-next-step
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-next-step-selector-9ee13cc3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_usMqvA1ox7KndP9hg-KC0

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-next-step-selector-9ee13cc3
```

Example prompt: I have an agent that just finished gathering user requirements and now needs to decide what to do next — here are its current state and three candidate actions separated by pipes: rank them so I know which one to execute first.

## When to prefer this

Choose this endpoint when an autonomous agent has a concrete list of candidate next actions and needs a lightweight, fast decision on which to execute given its current operational state. It is ideal for multi-step agent pipelines where the orchestrator must pick the next tool call without burning tokens on a full LLM reasoning pass. Prefer this over general-purpose LLM prompting when you want a consistent, cost-effective ranking signal specifically tuned for agent state-action matching.

## Known failure modes

- Missing required 'state' or 'actions' query parameters returns a validation error
- State or actions string exceeds 12000 character limit causing a 400 error
- Ambiguous or poorly formatted actions list (not separated by | or newlines) may produce unreliable rankings
- Empty actions list returns an error or empty ranking
- Service unavailability returns a 5xx error

## How this service works

Rank candidate next actions against the current agent state

## Output

Returns a ranked list of the candidate actions with the recommended best next step highlighted, scored or ordered by appropriateness relative to the provided agent state. Likely includes the top recommended action and a rationale or confidence ordering for the remaining candidates.

## 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": [
      "state",
      "actions"
     ],
     "properties": {
      "state": {
       "type": "string",
       "maxLength": 12000,
       "description": "Current agent state"
      },
      "actions": {
       "type": "string",
       "maxLength": 12000,
       "description": "Candidate actions separated by | or newlines"
      }
     },
     "additionalProperties": false
    }
   },
   "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-next-step-selector-9ee13cc3/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)