# Diffbot AI integration on Definable

> Diffbot provides AI-powered tools to extract and structure data from web pages, transforming unstructured web content into structured, linked data.

## What this connects

Diffbot provides AI-powered tools to extract and structure data from web pages, transforming unstructured web content into structured, linked data.

Vendor: https://www.diffbot.com

## Tools available

**35** tools available. First 12:

- `DIFFBOT_COMBINE_ENTITY_PROFILES` — Combine Entity Profiles — Combine multiple entity profiles into a unified view using the Diffbot Knowledge Graph. Returns enhanced person or organization data by matching on identifying attributes like name, email, employer, or URL. Use this to enrich partial entity data, merge duplicate profiles, or verify entity identity.
- `DIFFBOT_CREATE_BULK` — Create Bulk Extract Job — Tool to submit a bulk extract job to process multiple URLs with Extract APIs. Use when you need to process many URLs asynchronously using any Extract API. The job will process URLs in the background and provide downloadable results.
- `DIFFBOT_CREATE_CUSTOM_API` — Create or Update Custom API — Tool to create or update the parameters and ruleset of a Custom API. Use this when you need to define custom extraction rules for specific websites that require tailored parsing logic beyond standard Diffbot APIs. Allows defining URL patterns, CSS selectors, extraction rules, and preprocessing filters to extract structured data from websites with unique layouts.
- `DIFFBOT_CREATE_KG_BULK_ENHANCE` — Create Bulk Enhance Job — Tool to submit a bulk enhance job to enrich multiple entities asynchronously. Use when you need to process many Person or Organization records in batch. The API accepts entity descriptions and returns enriched data from the Diffbot Knowledge Graph.
- `DIFFBOT_DELETE_CUSTOM_API` — Delete Custom API — Tool to delete custom API definitions for a given URL pattern. Removes custom extraction rules from your account. Use when you need to remove previously configured custom APIs.
- `DIFFBOT_DELETE_KG_ENHANCE_BULKJOB` — Delete KG Enhance Bulkjob — Tool to delete an Enhance Bulkjob. Removes the bulk job and its results from the system. Use when cleaning up completed or failed jobs.
- `DIFFBOT_DOWNLOAD_BULK_RESULTS` — Download Bulk Job Results — Tool to download results of a bulk enhance job with filtering options via POST request. Use this to retrieve processed results from a completed or running bulk job. Supports multiple export formats (json, jsonl, csv, xls, xlsx) and various filtering options to customize the output. HTTP 200 indicates results are ready, HTTP 201 means the job is still executing.
- `DIFFBOT_ENHANCE_ENTITY` — Enhance Entity with Knowledge Graph — Enrich a person or organization with comprehensive data from the Diffbot Knowledge Graph. Provide identifiers like name, email, employer, or URL and receive detailed entity information including employment history, education, location, skills, and more. Use when you need to gather all publicly available knowledge about a specific person or organization from billions of web pages.
- `DIFFBOT_EXTRACT_JOB` — Diffbot Extract Job — Tool to extract structured job posting data from job listing pages. Returns job title, company, location, salary, requirements, skills, and other job-related information. Use when you need to parse and structure data from job postings.
- `DIFFBOT_EXTRACT_LIST` — Diffbot Extract List — Tool to extract structured data from list-style pages like news indexes, product listings, and directory pages. Returns an array of items with their titles, links, and descriptions. Use when you need to extract multiple items from a page organized as a list or index.
- `DIFFBOT_GET_ACCOUNT` — Get Diffbot Account Details — Retrieves comprehensive Diffbot account information including subscription plan details, credit balance, usage history, and account status. Returns account holder name, email, current plan, available credits, and daily usage statistics for the past 31 days. Use this to check your account's credit balance, monitor API usage patterns, verify account status, or retrieve account metadata.
- `DIFFBOT_GET_ANALYZE` — Diffbot Analyze — Automatically analyzes a web page to determine its type and extract structured data. The Analyze API intelligently classifies pages into types (article, product, discussion, image, video, organization, etc.) and extracts relevant structured data. Use this when you need to process URLs of unknown type or want automatic extraction without specifying the page type in advance.

## Auth

Auth schemes: `API_KEY`.

## How agents use Diffbot

Inside a Definable workflow, Diffbot is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → Diffbot** — the Researcher (GPT-5.5) pulls context from Diffbot (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → Diffbot** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into Diffbot (create record, post message, draft email).
- **Designer / Engineer → Distributor → Diffbot** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via Diffbot (attach file, open PR comment, post status).

The Verifier checks every Diffbot call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- artificial intelligence — https://definable.ai/apps/category/artificial-intelligence/
- ai web scraping — https://definable.ai/apps/category/ai-web-scraping/

## Related

- HTML page: https://definable.ai/apps/diffbot/
- Same category (artificial intelligence): https://definable.ai/apps/category/artificial-intelligence/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt