PlaysbyMoat8
Back to the library
The workflow guideSales

Qualify new enquiries with a voice assistant

Respond to new enquiries, answer common questions, and transfer suitable conversations to a salesperson.

6 implementation stepsAdvanced

How this works

Respond to new enquiries, answer common questions, and transfer suitable conversations to a salesperson.

Qualify an enquiry through a bounded voice conversation and a reliable handoff. The assistant should disclose itself, confirm it is speaking to the intended person and capture stated needs without turning a polite response into purchase intent.

Before you start

Defined operating scope

New enquiries require a repeatable, disclosed qualification conversation and human handoff.

Required source material

Obtain New enquiry; Product information; Qualification questions; Handoff rules. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

The person says they did not submit the enquiry. Stop qualification and flag an identity or source error.

Prepare the inputs

enquiry
Required

Source, contact and request

Verify permission and appropriate calling context.

product_reference
Required

Approved capabilities and prices

Use the current offer version.

qualification_questions
Required

Required facts and allowed branches

Keep unknown separate from negative answers.

handoff_rules
Required

Sales route and callback preferences

Define unavailable-agent and failed-transfer behavior.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check enquiry, product_reference, qualification_questions, handoff_rules 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 enquiry and any missing required fields.

  2. Trigger a call when an enquiry arrives

    • Validate the enquiry’s contact and calling permissions, preventing duplicate calls for the same active enquiry.
    • Verify captured facts against the conversation and preserve unknown answers.

    Checkpoint: A saved intermediate result for: Trigger a call when an enquiry arrives.

  3. Disclose the virtual assistant and ask qualification questions

    • Disclose the virtual assistant and ask the required questions conversationally, confirming uncertain names, dates and numbers.
    • Test stop requests, wrong-person calls and unsuccessful handoffs.

    Checkpoint: A saved intermediate result for: Disclose the virtual assistant and ask qualification questions.

  4. Answer supported product questions and capture the outcome

    • Answer only supported product questions and save the customer’s actual responses, including requests to stop.
    • Verify captured facts against the conversation and preserve unknown answers.

    Checkpoint: A saved intermediate result for: Answer supported product questions and capture the outcome.

  5. Transfer to a human or arrange an appropriate follow-up

    • Transfer an interested enquiry or prepare the agreed callback with context, then verify whether the handoff or booking actually completed.
    • Test stop requests, wrong-person calls and unsuccessful handoffs.

    Checkpoint: A saved intermediate result for: Transfer to a human or arrange an appropriate follow-up.

  6. Package the result and unresolved work

    • Check consent, product claims, call outcomes, and reliable human handoff.
    • Respect calling permissions, disclose automation and honor requests to stop.

    Checkpoint: A qualified enquiry and a conversation summary for sales. Unresolved items remain visible in the review record.

Decisions along the way

The person says they did not submit the enquiry.

Stop qualification and flag an identity or source error.

A required answer is unclear.

Ask a focused clarification and keep unknown if unresolved.

No salesperson can take the transfer.

Offer the approved follow-up path and record the customer’s preference rather than claiming a connection.

What you will produce

cs-video-voice-lead-qualification-result.json

JSON

A qualified enquiry and a conversation summary for sales. Label proposed and completed states separately.

Include: enquiry_id · identity_check · stated_needs · qualification_answers · contact_preference · handoff_receipt · outcome · status · evidence_reference · review_note

cs-video-voice-lead-qualification-review.md

Markdown

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

Include: source_reference · question · owner · next_action

Check the result

  • Verify captured facts against the conversation and preserve unknown answers.
  • Test stop requests, wrong-person calls and unsuccessful handoffs.
  • Inspect enquiry and product_reference in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Check consent, product claims, call outcomes, and reliable human handoff.

When something goes wrong

The person says they did not submit the enquiry.

Stop qualification and flag an identity or source error. Retain the affected evidence and recovery status.

A required answer is unclear.

Ask a focused clarification and keep unknown if unresolved. Retain the affected evidence and recovery status.

No salesperson can take the transfer.

Offer the approved follow-up path and record the customer’s preference rather than claiming a connection. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Qualify new enquiries with a voice assistant for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Enquiry E-2 asks about inventory software. Caller confirms the request, says they manage two locations and asks for a demonstration next week; no budget is stated.

Expected result

Synthetic expected result: Record two locations, demo interest and next-week preference; budget remains unknown. Route a scheduling request and confirm only when a real appointment exists.

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 accurate captured qualification fields; successful handoffs and customer opt-outs.

Stop or revise

No salesperson can take the transfer. Pause affected records and apply this recovery: Offer the approved follow-up path and record the customer’s preference rather than claiming a connection.

Keep the scope clear

  • Respect calling permissions, disclose automation and honor requests to stop.
  • Do not promise prices, features or appointments beyond approved information and confirmed system state.

Check before using

Check consent, product claims, call outcomes, and reliable human handoff.

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: New enquiry · Product information · Qualification questions · Handoff rules

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 ↗