Proposal
Build a client proposal from requirements to client-ready. The AI drives through Scope, Draft, and two checkpoints.
the steps, as stored
- 01Requirements
Capture the client's requirements before scoping anything. Do not price yet.
Record: - Client and the project in one sentence - The problem they want solved and the outcome they expect - Deliverables they have asked for, explicitly - Constraints — timeline, budget signal, must-haves, exclusions - Open questions where the ask is still unclear
If this comes from a discovery call, pull from those notes. If requirements are ambiguous, list the questions for the operator rather than guessing.
Save the requirements as a task note with task_notes_add. The next step — Scope & Pricing — reads this note.
- 02Scope & Pricingapproval gate
Read the task notes with task_notes_list — the note from the Requirements step contains the client's needs, deliverables, and constraints. Work from it.
Define scope and pricing. What good looks like: - A scoped list of deliverables, each with what is and is not included - Timeline or phases - Pricing for each deliverable or a clear total, with the model (fixed, retainer, hourly) stated - Explicit exclusions, so scope creep has a boundary - Assumptions the price depends on
Save the scope and pricing as a task note with task_notes_add. Then ask the operator to approve the scope and the numbers before any drafting. This is a checkpoint — committing to a price is the judgment moment, so the AI cannot advance until you approve.
- 03Draft
Read the task notes with task_notes_list — the Scope & Pricing note holds the approved numbers and deliverables, and the Requirements note holds the client's context. Work from them.
Write the full proposal: - A short summary that restates the client's problem and your outcome - Scope and deliverables exactly as approved — no figure changes - Timeline and pricing as approved - Terms, assumptions, and exclusions - A clear next step for the client to accept
Save the full proposal as a task note with task_notes_add. If it exceeds 10,000 characters, split across notes or store where the operator keeps documents and record the location. The Client Review step reads this note.
- 04Client-Ready Reviewapproval gate
Read the task notes with task_notes_list — the Draft note holds the proposal and the Scope & Pricing note holds what was approved. Work from them.
Check the proposal before it goes to the client: - Every figure matches the approved pricing exactly - Deliverables match the approved scope — nothing added or dropped - The client's name, project, and details are correct - No placeholder text, broken formatting, or internal note left in
Ask the operator to approve the proposal for sending to the client. This is a checkpoint — sending to the client is irreversible, so the AI cannot advance until you approve. If you reject, the workflow returns to Draft.
- 05Completecontext gate
The proposal is approved and ready to send to the client. Confirm the final proposal is saved as a task note, then close out the task.
use it for
- Write a proposal for a fixed-scope client project from discovery notes
- Draft a quote for a services engagement with clear deliverables and price
- Turn a discovery call into a structured, client-ready proposal
without it, with it
| without | with proposal |
|---|---|
| A price gets quoted before the scope is nailed down, and the margin disappears mid-project | The AI pauses at a scope-and-pricing checkpoint so you approve the numbers before a word of the proposal is written |
| The proposal goes to the client with a wrong figure or a deliverable nobody agreed to | The AI pauses at a client-ready checkpoint so you sign off before it reaches the client |
| You draft half a proposal, lose the thread, and rebuild the scope and pricing from scratch | The AI saves the requirements, the approved pricing, and the draft as notes, so a later session resumes mid-proposal intact |
| When the client pushes back, nobody can reconstruct how the scope and price were decided | Every step — Requirements, Scope & Pricing, Draft, Client Review — is logged, so the reasoning is already on the record |