PlaysbyMoat8
Back to the library
The workflow guideSales

Use call evidence to review lead fit

Extract evidence from sales conversations against agreed qualification criteria so marketing and sales can review lead quality consistently.

6 implementation stepsIntermediate

How this works

Extract evidence from sales conversations against agreed qualification criteria so marketing and sales can review lead quality consistently.

Assess lead fit from what the customer actually said. Keep need, authority, timing and budget evidence separate, and use unknown when a criterion was never discussed rather than interpreting silence or speaking style.

Before you start

Defined operating scope

Lead qualification needs explicit call evidence tied to agreed business criteria.

Required source material

Obtain Call transcripts; Explicit qualification rubric; Customer-system records. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

Budget was not discussed. Mark unknown and propose a neutral follow-up; do not infer affordability.

Prepare the inputs

call_id
Required

Transcript and account reference

Preserve speaker attribution and surrounding turns.

qualification_rubric
Required

Criteria and allowed values

Define pass, fail and unknown separately.

customer_record
Required

Confirmed company and deal facts

Note dates and provenance of earlier information.

review_owner
Required

Sales owner

Identify who confirms the qualification result.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check call_id, qualification_rubric, customer_record, review_owner 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 call_id and any missing required fields.

  2. Read the conversation in context

    • Read the conversation before scoring individual phrases and identify the purpose of the call.
    • Ensure each criterion value has a supporting statement or explicit unknown marker.

    Checkpoint: A saved intermediate result for: Read the conversation in context.

  3. Extract stated needs, constraints, and relevant budget information

    • Extract explicit needs, constraints and budget statements, retaining ranges and conditional wording.
    • Check conditional language, negation and the date of any prior CRM fact.

    Checkpoint: A saved intermediate result for: Extract stated needs, constraints, and relevant budget information.

  4. Present evidence and uncertainties for each rubric item

    • Build a criterion-by-criterion evidence table with unknowns and contradictions rather than one opaque score.
    • Ensure each criterion value has a supporting statement or explicit unknown marker.

    Checkpoint: A saved intermediate result for: Present evidence and uncertainties for each rubric item.

  5. Let the sales owner confirm the qualification and correct errors

    • Present the proposed fit record for the sales owner to correct and identify targeted follow-up questions.
    • Check conditional language, negation and the date of any prior CRM fact.

    Checkpoint: A saved intermediate result for: Let the sales owner confirm the qualification and correct errors.

  6. Package the result and unresolved work

    • Do not infer finances, personality, or intent from speaking style. Keep customer data restricted and leave consequential decisions to people.
    • Do not infer finances, personality or intent from voice or speaking style.

    Checkpoint: A reviewable lead-fit record linked to conversation evidence. Unresolved items remain visible in the review record.

Decisions along the way

Budget was not discussed.

Mark unknown and propose a neutral follow-up; do not infer affordability.

The customer describes a conditional timeline.

Preserve the condition instead of assigning a fixed purchase date.

CRM and call statements conflict.

Show both dated sources and ask the owner to resolve the current fact.

What you will produce

call-to-lead-fit-review-result.json

JSON

A reviewable lead-fit record linked to conversation evidence. Label proposed and completed states separately.

Include: call_id · criterion · evidence · proposed_value · uncertainty · followup_question · owner_decision · status · evidence_reference · review_note

call-to-lead-fit-review-review.md

Markdown

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

Include: source_reference · question · owner · next_action

Check the result

  • Ensure each criterion value has a supporting statement or explicit unknown marker.
  • Check conditional language, negation and the date of any prior CRM fact.
  • Inspect call_id and qualification_rubric in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Do not infer finances, personality, or intent from speaking style. Keep customer data restricted and leave consequential decisions to people.

When something goes wrong

Budget was not discussed.

Mark unknown and propose a neutral follow-up; do not infer affordability. Retain the affected evidence and recovery status.

The customer describes a conditional timeline.

Preserve the condition instead of assigning a fixed purchase date. Retain the affected evidence and recovery status.

CRM and call statements conflict.

Show both dated sources and ask the owner to resolve the current fact. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Use call evidence to review lead fit for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Customer C-9 needs reporting automation and says a purchase is possible after board approval. No budget or decision authority is stated.

Expected result

Synthetic expected result: Need is supported; timing is conditional on board approval; budget and authority are unknown. Draft follow-up questions address those gaps without rejecting the lead automatically.

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 agreement with human-reviewed fit labels; missing evidence correctly left unresolved.

Stop or revise

CRM and call statements conflict. Pause affected records and apply this recovery: Show both dated sources and ask the owner to resolve the current fact.

Keep the scope clear

  • Do not infer finances, personality or intent from voice or speaking style.
  • The sales owner makes consequential qualification and communication decisions.

Check before using

Do not infer finances, personality, or intent from speaking style. Keep customer data restricted and leave consequential decisions to people.

Business activities

  • Handle inbound enquiries
  • 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 transcripts · Explicit qualification rubric · Customer-system records

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 ↗