Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.chatgrid.ai/llms.txt

Use this file to discover all available pages before exploring further.

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 the prospect’s own website
  • 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

curl -X POST https://api.chatgrid.ai/v1/boards \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Acme Corp - Enterprise Deal"}'
Save the board_id from the response.

Step 2: Add prospect research nodes

Add the prospect’s website and LinkedIn page. ChatGrid fetches and vectorizes the content.
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "website", "data": {"url": "https://acme-corp.com/about"}}'

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "website", "data": {"url": "https://linkedin.com/company/acme-corp"}}'

Step 3: Vectorize and generate an account brief

Vectorize the prospect content, create a chat, then ask AI for a structured account brief.
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/documents/vectorize \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://acme-corp.com/about"}'

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/chats \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Deal Strategy"}'

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/chats/{chatId}/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Based on the prospect materials on this board, write a 1-page account brief: company overview, business priorities, pain points we can solve, and talking points for our first call.",
    "stream": false
  }'

Step 4: Add proposal and competitive positioning

Add a proposal template as a notepad and competitive intel as batch sticky notes.
curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type": "notepad", "data": {"content": "# Proposal: Acme Corp\n\n## Executive Summary\n[Brief goes here]\n\n## Solution\n- ...\n\n## Pricing\n- Tier 1 / Tier 2\n\n## Timeline\nWeek 1-2: Discovery | Week 3-4: POC | Week 5+: Rollout"}}'

curl -X POST https://api.chatgrid.ai/v1/boards/{boardId}/nodes/batch \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "nodes": [
      {"type": "sticky_note", "data": {"content": "vs. Competitor A: Native integrations, no middleware. 40% faster onboarding."}},
      {"type": "sticky_note", "data": {"content": "vs. Competitor B: 30% lower per-seat pricing at 500+ users."}},
      {"type": "sticky_note", "data": {"content": "Key differentiator: Real-time collaboration. Theirs is single-player."}}
    ]
  }'

What’s happening under the hood

When you add a website node, ChatGrid fetches the page, extracts text content, and stores it. Vectorization chunks the text 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 creates multiple nodes in a single transaction for speed and atomicity.

Next steps

Research Pipeline

Automate multi-source research and synthesis

Streaming Responses

Stream AI responses for real-time deal room chat