Sales Research Agent: company research brief where every claim has a source

Give it a company name and it researches the company on the web, then writes a short sales brief: what they do, size, likely pain points, key people, recent signals, and an outreach angle.

The rule I built it around: every factual claim must cite a page the agent actually fetched during that run. If it can’t source something, it has to write “unknown” instead of guessing. A made-up fact in a sales email is worse than a gap.

How it works

• A ReAct loop written from scratch in Python (search, fetch, read, decide), no agent framework.
• A validator checks the brief’s schema and grounding before it’s accepted. If it fails, the problems go back to the agent and it keeps researching.
• One self-critique pass for quality, capped so it can’t loop forever.
• Blocks fetches to private/internal addresses, and treats scraped pages as untrusted text.

Works with Claude, any OpenAI-compatible API, or a local Ollama model. Batch mode turns a list of companies into a folder of briefs.

Code: https://www.twine.net/signin