# Verity Suite Compass Pro — AI Decision Advisor

> Verity Suite Compass Pro — AI Decision Advisor is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Evaluates a set of candidate options against stated constraints and evidence, returning a calibrated verdict (recommend, tentative, gather_more_info, or no_viable_option) with confidence score and reasons.

## Facts

- Endpoint: POST https://verity-suite.onrender.com/compass/pro
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-compass-pro-ai-decision-advisor-e778cb7d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_KeCJl7lLbU4OyMeYWQjqJ

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 verity-suite-compass-pro-ai-decision-advisor-e778cb7d -d '<json body>'
```

Example prompt: I need to pick between three cloud storage plans — 'Plan A: 100GB for $3/mo', 'Plan B: 500GB for $8/mo', 'Plan C: 2TB for $12/mo' — my hard requirement is at least 400GB, I'd prefer to stay under $10/mo, and I want the best value per GB within those bounds. Can you run this through Compass Pro and tell me which to pick, how confident you are, and the main tradeoff?

## When to prefer this

Use this endpoint when an AI agent needs a principled, calibrated pick from a discrete set of options with explicit constraints — especially when fail-closed behavior (returning gather_more_info instead of guessing) and a confidence score are important. Prefer this over free-form LLM reasoning when auditability, structured verdicts, and calibrated probabilities matter.

## Known failure modes

- Missing required fields 'options' or 'constraints' results in a 422 validation error
- Empty options array yields no_viable_option verdict with no choice
- Contradictory hard constraints may produce no_viable_option even with good evidence
- Insufficient evidence with critical unknown facts triggers gather_more_info verdict
- Payment failure or x402 auth rejection blocks the call entirely

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

Returns a JSON object with a verdict enum (recommend/tentative/gather_more_info/no_viable_option), the chosen option string (verbatim from input, only when a pick is made), a calibrated confidence probability (0–1), an array of concrete reason strings naming tradeoffs, and optionally a missing_info array listing specific facts that would change the verdict.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "options",
  "constraints"
 ],
 "properties": {
  "options": {
   "type": "array",
   "description": "the candidate choices to pick among; one option per item, stated verbatim as you want it returned"
  },
  "evidence": {
   "type": "string",
   "description": "facts known about the options (specs, prices, availability, data); for any current or external fact, only what is stated here may be used"
  },
  "constraints": {
   "type": "string",
   "description": "the goal plus hard requirements (must-meet gates), soft preferences (weigh, don't gate), and any priorities or tradeoffs between them"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "compass_out",
 "required": [
  "verdict",
  "confidence",
  "reasons"
 ],
 "properties": {
  "choice": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "null"
    }
   ],
   "title": "Choice",
   "description": "the chosen option, copied verbatim from the options list; include ONLY when verdict is recommend or tentative; omit entirely for gather_more_info and no_viable_option"
  },
  "reasons": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Reasons",
   "description": "concrete reasons grounded in the actual constraints and evidence; for recommend/tentative must name the main tradeoff against the runner-up; for the safe verdicts must say what blocks a pick"
  },
  "verdict": {
   "enum": [
    "recommend",
    "tentative",
    "gather_more_info",
    "no_viable_option"
   ],
   "type": "string",
   "title": "Verdict",
   "description": "recommend=exactly one eligible option is clearly best on the stated constraints with a defensible margin; tentative=a leading option exists but the margin is thin, rests on an unestablished assumption, or two options are near-tied; gather_more_info=a fact needed to compare the options is missing, so no responsible pick is possible; no_viable_option=every option violates at least one hard constraint (or none can be confirmed to meet them from the evidence)"
  },
  "confidence": {
   "type": "number",
   "title": "Confidence",
   "maximum": 1,
   "minimum": 0,
   "description": "calibrated probability the stated verdict is correct: for recommend/tentative, the probability choice is truly the best of the given options under the stated constraints; for gather_more_info/no_viable_option, the probability that verdict itself is the right call"
  },
  "missing_info": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Missing Info",
   "description": "specific facts that, if supplied, would change or firm up the verdict; required (non-empty) when verdict is gather_more_info, optional otherwise"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-compass-pro-ai-decision-advisor-e778cb7d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-suite.onrender.com](https://www.zero.xyz/host/verity-suite.onrender.com/llms.txt)