# Paul Graham Corpus Retrieval — researcher.now

> Paul Graham Corpus Retrieval — researcher.now is a paid API for AI agents from researcher.now, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Semantically and lexically searches Paul Graham's complete essay, talk, interview, and X post corpus, returning grounded evidence packets (claims, quotes, citations).

## Facts

- Endpoint: POST https://researcher.now/v1/x402/entities/paul-graham/retrieve
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/paul-graham-corpus-retrieval-researcher-now-592f8b89
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_poNaCt8d27NDXDL3QA_Yl

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 paul-graham-corpus-retrieval-researcher-now-592f8b89 -d '<json body>'
```

Example prompt: Search Paul Graham's entire essay and interview corpus for what he's said about the importance of talking to users — give me up to 10 grounded packets including direct quotes and claims with citations.

## When to prefer this

Choose this endpoint when you need source-grounded, citable evidence from Paul Graham's known body of work — essays, talks, interviews, and public posts — rather than a generated or paraphrased answer. It is superior to a general web search when you need precise attribution, when you want to avoid hallucinated PG quotes, or when downstream tasks require verified citations. Prefer the sibling 'Ask Paul Graham' endpoint if you want a conversational answer synthesized from the corpus rather than raw evidence packets.

## Known failure modes

- Query string missing or empty — returns 400 validation error
- Limit exceeds 100 — rejected by schema validation
- No matching packets found for a very narrow or obscure query — returns empty result set
- packetTypes filter contains unrecognized type strings — may silently ignore or return error
- Payment not settled via x402 — request blocked before processing
- Query too long (>1000 characters) — rejected by schema

## How this service works

Search Paul Graham's source corpus — a source-grounded persona of the Y Combinator co-founder and essayist, built from 13,000+ cited sources: his complete essays, talks, interviews, and X posts — by semantic + lexical query and retrieve grounded packets (graded claims, quotes, evidence with citations). POST a JSON body { query, limit? (<=100), packetTypes? }. Flat micro-price per query.

## Output

An array of grounded evidence packets, each containing a typed item (claim, quote, or fact), the verbatim or paraphrased text, a relevance/grade signal, and one or more citations pointing to the specific Paul Graham essay, talk, interview, or X post from which the content was sourced.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "required": [
      "query"
     ],
     "properties": {
      "query": {
       "type": "string",
       "minLength": 1,
       "maxLength": 1000,
       "description": "Semantic + lexical search query over Paul Graham's source corpus."
      },
      "limit": {
       "type": "integer",
       "minimum": 1,
       "maximum": 100,
       "description": "Maximum packets to return (default 20, matching the route default)."
      },
      "packetTypes": {
       "type": "array",
       "items": {
        "type": "string",
        "maxLength": 80
       },
       "maxItems": 20,
       "description": "Optional filter by packet type, e.g. claim, quote, fact."
      }
     }
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   },
   "required": [
    "type"
   ]
  }
 },
 "required": [
  "input"
 ]
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/paul-graham-corpus-retrieval-researcher-now-592f8b89/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from researcher.now](https://www.zero.xyz/host/researcher.now/llms.txt)