Forest floor · web intelligenceSearch · scrape · enrich

Web intelligence API · for agents

Forage the live web. Return structure.

Truffen is a core AI/ML product: model infra for agents and GTM desks. One credit meter covers search, scrape, people and company enrich, and monitors. Waterfall routing picks a source, falls back, and hands typed rows instead of a pile of HTML. Truffen feeds agents. It does not ship an agent runtime of its own.

  • One meter search, scrape, enrich
  • Waterfall source, then fallback
  • Citations on every field
Claude 3.7 SonnetGPT-4oGemini 2.5Llama 3 70BGroqBedrockAnthropicOpenAI DirectLangChain Claude 3.7 SonnetGPT-4oGemini 2.5Llama 3 70BGroqBedrockAnthropicOpenAI DirectLangChain

AI features

Where the forage actually sits

Truffen is in the business of building a core AI/ML product for agents and GTM teams. Named jobs: search sized for a context window, scrape to schema, enrich with citations, monitors, and waterfall routing. This is model infra — not a hiring interviewer and not an agent framework.

AI feature · Waterfall routing

Source, then fallback, on one credit

For agents that cannot stall on a thin first hit

Waterfall routing picks a source, falls back, and still meters one credit. Each field carries a source, a confidence, and a URL the agent can show.

Objective → source 1 → fallback → typed row

AI feature · Search for agents

Ranked excerpts sized for a context window

For builders who POST a natural-language objective

Declarative search returns ranked excerpts, not a dump of HTML. Same credit meter as scrape, enrich, and monitor.

POST /v1/search → ranked excerpts

AI feature · Scrape to schema

JS pages and PDFs become markdown or JSON

For GTM and research desks that need structure

Messy DOM, JavaScript pages, and PDFs land as markdown or a JSON schema your tools already expect.

POST /v1/scrape → markdown / JSON schema

AI feature · Enrich and monitors

People, companies, and a watch on the ground

For desks that need citations, then a webhook when the page changes

People and companies from a name or a domain, with source citations. Monitors watch a query and POST a change object. Model families in plan: Claude 3.7 Sonnet, GPT-4o, Gemini 2.5, Llama 3 70B. Access: Bedrock, Anthropic, OpenAI Direct, Groq. Frameworks: LangChain and custom/homebrew. Truffen is not fine-tuning those models.

POST /v1/enrich · POST /v1/monitors

Marketing / analytics. Core AI/ML product. MVP stage — no invented customers, funding, or uptime claims. Feeds agents; does not ship an agent runtime.

Method

How Truffen ships

Ask the soil. Run the waterfall. Feed the agent one JSON object.

01

Ask the soil.

POST a natural-language objective or a structured filter.

02

Run the waterfall.

Truffen fans out, dedupes, and types the result.

03

Feed the agent.

One JSON object. Citations on every field.

Stack

Product pillars

Search

Declarative objectives. Ranked excerpts sized for a context window.

Scrape

JS pages, PDFs, and messy DOM become markdown or JSON schema.

Enrich

People and companies from a name or a domain, with source citations.

Monitor

Watch a query. Webhooks when the ground shifts.

Start

A first query this afternoon.

Write ceo@truffen.shop. You get a test token, a sample waterfall, and a 30-minute walkthrough on the people you want to find.

See pricing