$ man slop-filtered-brief
/slop-filtered-brief
PRICE / CALL
$0.06
USDC · base mainnet · scheme: exact
──────────────────────────────────────────────────────────────────────────────
NAME
slop-filtered-brief — research a topic without ai-generated slop
SYNOPSIS
POST https://x402.agentutility.ai/slop-filtered-brief
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call → 402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.
DESCRIPTION
Research a topic without AI-generated slop. Composite: one call runs web-search, news-search, and x-search, then scores candidate sources through ai-content-detector and excludes anything at or above 0.65 probability_ai_generated. All three discovery legs are degradable, so one slow provider narrows the source mix instead of failing the paid brief; set include_x: false to skip X. A detector timeout keeps that source unscored rather than dropping it. Short sources stay unscored too. Returns kept sources grouped by type, excluded_ai_generated details, counts, and component timing. This is a style-signal heuristic, not forensic AI detection. Use it as an AI-slop-filtered research API, human-source brief, clean research digest, or pre-citation tool.
INPUT — request schema
| property | type | description | req? |
|---|
| topic | string | Topic to research, e.g. 'x402 payment protocol adoption'. Max 300 chars. | required |
| recency | string | How recent the sources should be: 'day', 'week', 'month', 'year', or 'any'. Default 'month'. | optional |
| include_x | boolean | Whether to include an X/Twitter search leg. Default true. | optional |
OUTPUT — response shape
| field | type | description |
|---|
| topic | string | — |
| kept_sources | string | — |
| excluded_ai_generated | string | — |
| counts | string | — |
| composed_of | string | — |
| components | string | — |
| degraded | string | — |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/slop-filtered-brief \
-H 'Content-Type: application/json' \
-d '{ }'first response = 402 Payment Required with payment requirements; sign + retry with X-PAYMENT.
EXAMPLE 2 · mcp
# Install the MCP package for this endpoint's cluster
npx -y @agentutility/mcp-<cluster>
# Required: EVM private key with USDC on Base
export X402_PRIVATE_KEY=0x...
# Then call the slop-filtered-brief tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- composeslopfilteredbriefslop-filtered-brief
- methods
- POST
- cluster
- compose
- price
- $0.06 USDC per call
ADJACENT — other endpoints in compose
| endpoint | description | price |
|---|
| agent-run-review | Agent run review / trace cost evals / post-run analysis / agent debugging in one call: hand it a raw agent execution trace and get a read… | $0.06 |
| authentic-sentiment | Authentic sentiment API: send a topic, brand, handle, or phrase and get back sentiment from real humans, not bots or AI astroturf. | $0.06 |
| brand-availability-sweep | Brand availability sweep API for a name availability check before you commit to a startup, product, or project name: trademark signal, do… | $0.06 |
| browser-workflow-repair | Browser workflow repair / self-healing automation / dom drift fix / flow memory in one call for agents whose CSS selectors broke after a… | $0.06 |
| competitor-snapshot | Snapshots a company for competitive intelligence in one call: profile, recent news, and news sentiment. | $0.06 |
| contact-golden-record | Turn 2-5 messy candidate contact records into one deduplicated golden record with per-field provenance. | $0.06 |
| content-authenticity-report | Check whether a page is AI-generated slop before your agent cites or acts on it. | $0.06 |
| cross-lingual-topic-monitor | Monitor a topic across non-English sources in one call: search the open web and X, detect what language each hit is actually in, translat… | $0.06 |
agentutility(7)