Proposal first draft from discovery notes
An agent combines discovery call notes with your approved service descriptions and pricing rules to produce a proposal first draft for the owner to refine.
The use case
Writing proposals from scratch eats evenings for owners of agencies, consultancies, and trade businesses. Most proposals reuse the same building blocks: problem summary, scope, deliverables, timeline, assumptions, and price. A proposal agent reads the discovery notes and the deal record, pulls matching sections from an approved library of service descriptions and terms, and assembles a first draft in your template. It flags anything the notes did not cover, such as budget or start date, instead of guessing. The owner reviews scope and pricing line by line, edits the language, and sends the final proposal personally.
Example workflow
- A deal reaching the proposal stage in the CRM triggers the workflow.
- The agent reads discovery notes, call summaries, and deal fields such as budget range and timeline.
- It selects matching service blocks, assumptions, and terms from an approved library stored in Notion or Google Docs.
- Claude drafts the proposal in your template, restating the client's goals in plain language and marking gaps as questions.
- The draft is saved to the deal folder and the owner is notified for review.
- The owner verifies scope, pricing, and dates, edits the draft, and sends it to the client personally.
- The final version and any edits are saved so the library can be improved over time.
Tools
- Google Docs
- Notion
- Claude
- HubSpot or Pipedrive
- Zapier
- PandaDoc or similar e-sign tool
Risks and guardrails
- Wrong pricing or scope can become a binding commitment; never let the agent set final prices and require line-by-line owner review.
- The draft may promise outcomes you cannot guarantee; keep outcome language in the approved library and avoid generated guarantees.
- Confidential details from one client could leak into another proposal; generate each draft only from that deal's notes and the shared library.
- Gaps filled by guessing create misunderstandings; instruct the agent to mark missing information as questions.
Related recipe
Security Questionnaire First-Draft Agent with Cited Sources: An agent drafts security questionnaire answers from your own trust documents and approved answer library, cites every source, and marks gaps NEEDS OWNER for a responsible person to sign.
Want it set up for you? Request a quote.
Sources
Written by Agents Lookup. Credits and official pages for the tools this use case names:
- Notion MCP server (official page): developers.notion.com/guides/mcp/overview (checked 2026-11-09)
- Claude (official page): claude.ai (checked 2026-11-09)
- HubSpot MCP server (official page): developers.hubspot.com/ai-tools/mcp (checked 2026-11-09)
- Pipedrive (official page): www.pipedrive.com (checked 2026-11-09)
- Zapier MCP (official page): zapier.com/mcp (checked 2026-11-09)
- PandaDoc MCP server (official page): developers.pandadoc.com/docs/use-pandadoc-mcp-server (checked 2026-11-09)