Skip to main content

What you’ll build

A structured deal room for an enterprise account, shareable with the buying committee.
  • Board per prospect with all deal intelligence in one place
  • AI-generated account brief from extracted prospect research
  • Competitive positioning notes for the whole team
  • Shareable link for the buying committee

Prerequisites

  • ChatGrid API key (get one here)
  • Node.js 18+ or Python 3.10+

Step 1: Create a deal room board

Save data.id from the response as your boardId.

Step 2: Add prospect research nodes

Add the prospect’s website and LinkedIn page as source nodes.

Step 3: Vectorize and generate an account brief

Vectorize extracted prospect notes, create a chat, then ask AI for a structured account brief.

Step 4: Add proposal and competitive positioning

Add a proposal template as a notepad and competitive intel as batch sticky notes.

What’s happening under the hood

Website nodes keep source URLs visible on the board. Vectorization chunks the text you provide and generates embeddings using pgvector. When you ask AI for an account brief, it runs a semantic search against those embeddings, then generates a response grounded in the actual prospect data — not generic knowledge. The batch endpoint applies multiple node operations in a single request for speed.

Next steps

Research Pipeline

Automate multi-source research and synthesis

Streaming Responses

Stream AI responses for real-time deal room chat