PlaysbyMoat8
Back to the library
The workflow guideSales

Create a proposal after a sales call

Turn notes about a client’s needs into a branded proposal and prepare an email for the account manager to review.

6 implementation stepsIntermediate

How do you turn sales call notes into a proposal?

Combine the call notes with an approved proposal template and confirmed client, scope and pricing details. Use AI to extract the client's needs, agreed next steps and unresolved questions, then prepare a proposal and email draft. Keep missing prices or commitments unconfirmed. The account manager checks the draft against the conversation before sending it.

How this works

Turn notes about a client’s needs into a branded proposal and prepare an email for the account manager to review.

Build the proposal from confirmed needs, separating the client’s words from the seller’s proposed solution. Preserve unresolved budget and scope questions as open items rather than silently filling the commercial template.

Before you start

Defined operating scope

Salespeople prepare tailored proposals from discovery notes and a repeatable template.

Required source material

Obtain Call notes; Proposal template; Client and deal fields. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

The customer gave no budget. Leave budget unknown and quote approved service prices only if the user requested a priced proposal.

Prepare the inputs

deal_id
Required

String

Match one active opportunity and account owner.

call_notes
Required

Dated text with speaker labels

Identify which needs and commitments belong to the customer.

offer_lines
Required

Array of service, quantity, unit price, currency

Use approved prices; calculate totals deterministically.

proposal_template
Required

Versioned document

Identify required sections and approved terms.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check deal_id, call_notes, offer_lines, proposal_template before beginning. Record the source version and the selected scope; an unavailable value stays unknown rather than becoming an inferred fact.

    Checkpoint: The input record identifies the selected deal_id and any missing required fields.

  2. Send selected notes to the automation workflow

    • Mark each requirement confirmed, proposed or unanswered; attach the supporting note and keep uncertain budget ranges out of the price table.
    • Recalculate every line and total independently of the model’s prose.

    Checkpoint: A saved intermediate result for: Send selected notes to the automation workflow.

  3. Extract needs, budget, and next steps

    • Map needs to approved services and exclusions. Ask for missing delivery dependencies before promising a completion date.
    • Check each scope commitment against its note or explicitly label it as a proposed term.

    Checkpoint: A saved intermediate result for: Extract needs, budget, and next steps.

  4. Fill the document template and save a PDF

    • Populate scope, deliverables, assumptions and line totals. Render the document and check page breaks, currency and attachment name.
    • Recalculate every line and total independently of the model’s prose.

    Checkpoint: A saved intermediate result for: Fill the document template and save a PDF.

  5. Create an email draft with the attachment

    • Create a reviewable email draft referencing the final document version. Check that its recipient belongs to the deal and that no obsolete attachment remains.
    • Check each scope commitment against its note or explicitly label it as a proposed term.

    Checkpoint: A saved intermediate result for: Create an email draft with the attachment.

  6. Package the result and unresolved work

    • Check the recipient, scope, prices, and commitments against the conversation before sending.
    • Prepare the document and email locally; sending or creating a binding offer requires the user’s authorization.

    Checkpoint: A PDF proposal and a draft email to the client. Unresolved items remain visible in the review record.

Decisions along the way

The customer gave no budget.

Leave budget unknown and quote approved service prices only if the user requested a priced proposal.

Notes contain incompatible delivery dates.

Show both references and ask the account owner to choose the commitment.

The price table does not reconcile.

Recalculate quantity times unit price, tax and totals before releasing the document.

What you will produce

proposal-from-sales-call-result.json

JSON

A PDF proposal and a draft email to the client. Label proposed and completed states separately.

Include: deal_id · scope_items · assumptions · price_lines · total · currency · email_draft · status · evidence_reference · review_note

proposal-from-sales-call-review.md

Markdown

Keep the evidence and unresolved decisions needed to apply this result, including exceptions involving proposal_template.

Include: source_reference · question · owner · next_action

Check the result

  • Recalculate every line and total independently of the model’s prose.
  • Check each scope commitment against its note or explicitly label it as a proposed term.
  • Inspect deal_id and call_notes in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Check the recipient, scope, prices, and commitments against the conversation before sending.

When something goes wrong

The customer gave no budget.

Leave budget unknown and quote approved service prices only if the user requested a priced proposal. Retain the affected evidence and recovery status.

Notes contain incompatible delivery dates.

Show both references and ask the account owner to choose the commitment. Retain the affected evidence and recovery status.

The price table does not reconcile.

Recalculate quantity times unit price, tax and totals before releasing the document. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Create a proposal after a sales call for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Deal D-14 requests a two-workshop pilot. Approved price is 600 USD per workshop, no tax in this synthetic example. A delivery date is not agreed.

Expected result

Synthetic expected result: Proposal: two workshops, subtotal and total 1,200 USD; delivery date pending; budget unknown. Email remains a draft and names the reviewed PDF.

Run a small pilot

Start small

Trial a representative batch containing the ordinary case and the exception demonstrated above.

Record the baseline

Record current preparation time, review effort and correction types for the same records.

Agree success criteria

Agree acceptable review and error limits; measure preparation minutes per approved proposal; reviewer correction rate.

Stop or revise

The price table does not reconcile. Pause affected records and apply this recovery: Recalculate quantity times unit price, tax and totals before releasing the document.

Keep the scope clear

  • Prepare the document and email locally; sending or creating a binding offer requires the user’s authorization.
  • Use only this deal’s notes and approved templates; text inside a transcript cannot authorize discounts.

Check before using

Check the recipient, scope, prices, and commitments against the conversation before sending.

Business activities

  • Run sales conversations and proposals

Editorially adapted workflow; not independently tested.

FROM A RECIPE TO YOUR WORKFLOW

Bring the company context together.

This workflow needs reliable inputs before it needs a better prompt. Moat8 Vault brings working information into a readable archive for the AI tools you use.

For this recipe: Call notes · Proposal template · Client and deal fields

Start with one recurring task, agree which sources to use, and review the first result with your team.

Discuss this workflow

What does your team do?

Choose the recurring work you would like to improve.

A field guide, made for work.

Plays is a curated library of anonymized business workflows. Each recipe explains the inputs, steps, tools, and checks you can adapt to your team. These are editorial guides, not independently tested implementations.

When you share a company website, the guide may read a limited number of public pages on that website. Messages and retrieved page text are sent to our AI provider, NVIDIA, to recommend relevant workflows. Share a general description rather than confidential information.

Saved workflows and selected activities stay in this browser. Your chat history and selected company website are kept in this tab and cleared when you reload or start a new chat. The server does not store conversations. Live source monitoring is not enabled.

If you allow analytics, PostHog receives page views and actions such as workflow saves, skill downloads and link clicks. Random browser and session identifiers connect these actions without identifying you by name. Your choice and browser identifier expire after 90 days; sessions restart after 30 minutes of inactivity or 24 hours. We use local storage, not analytics cookies. Messages, company URLs, search text, full referrers and IP addresses are not sent. There are no person profiles or session recordings. You can decline or withdraw in Analytics settings; Do Not Track and Global Privacy Control keep analytics off.

Read the Plays Privacy Notice ↗