surface↓extraction↓web_agent
Extractionscalar · returns table

WEB_AGENT

AI web research agent — no starting URL required (via Firecrawl)

Per-row — runs once for each row.

extractionexternal-apiurl

Arguments

nametypedescription
promptVARCHARResearch task description in natural language
schema_json(optional)VARCHAROptional JSON Schema for structured output, e.g. '{"name":"string","url":"string"}'

About

AI-powered web research agent. No URLs needed - describe what you want and the agent autonomously searches, navigates, and extracts data. SQL Usage: SELECT * FROM web_agent( 'Find the founding team of Firecrawl', '{"name": "string", "role": "string"}' ) SELECT * FROM web_agent( 'Find Y Combinator W24 batch AI companies', '{"company": "string", "description": "string", "website": "string"}' )

Nearby rabbit holes

same domain
scalar

CRAWL_BATCH

Crawl a website and extract structured data from each page (via Firecrawl)

extractionexternal-apiurl
scalar

EXTRACT

Extract specific information from unstructured text (zero-shot NER)

extractionnlispecialist-zootext
scalar

EXTRACT_LLM

LLM-backed extraction (escape hatch for EXTRACTS)

extractionllmllm-escape-hatchtext
scalar

EXTRACT_STRUCTURED

Extract structured fields from text per a user-supplied schema

extractionllmtext
aggregate

MERGE_TIMELINES

Merge multiple timelines into unified chronological sequence

extractionllmjson
scalar

PARSE

Extract information from text using natural-language instructions

extractionllmtext
Climb back to The Looking Glass