
How to Build a Meeting Prep Agent From Your Inbox
Who you're meeting, what you already discussed and what you committed to: a prep brief built from long threads, forwards and attachments, before every…
8 min read
Blog
Product news, engineering notes and practical guides for developers who build AI agents.

Who you're meeting, what you already discussed and what you committed to: a prep brief built from long threads, forwards and attachments, before every…
8 min read

For years RAG was the default way to connect AI to data, and it worked because the data didn't move. Why that stopped being…
6 min read

Unresolved complaints, tone drift, competitor mentions and slower replies: the churn signals hiding in email threads, pulled as structured JSON your product can route.
5 min read

What did we spend, on what, with whom? Pull every invoice, receipt, refund and renewal out of email into one structured list, from a…
7 min read

Connect Claude to your Gmail and Drive, install one plugin and ask real questions about your work, in about five minutes. No more pasting…
7 min read

Connecting an AI agent to email is a six-layer problem, and most teams only budget for two. Gmail API, Microsoft Graph, IMAP, parsing services…
4 min read

Every inbox has threads that fell through the cracks. Find the threads waiting on your users and the questions nobody answered, and route them…
3 min read

Engagement drops, unanswered objections, competitor mentions and overdue commitments: a deal risk detector built on iGPT's API, returning structured JSON.
3 min read

RAG works on documentation because it has clean structure and no concept of time. Email has neither. The six layers of email context, three…
3 min read

Chunk-and-retrieve works on documentation because each piece appears once. Email threads quote, repeat and reorder themselves. Where RAG breaks on email, and the fix.
7 min read
Bring the agent you already have. Agent200 provides and executes its external capabilities.