PlaysbyMoat8
Back to the library
The workflow guideSupport

Surface unresolved client questions from project conversations

Monitor permitted client chats and calls for questions or difficulties that the account team should address.

6 implementation stepsIntermediate

How this works

Monitor permitted client chats and calls for questions or difficulties that the account team should address.

Track explicit client questions across project conversations and distinguish waiting on the team from waiting on the client. The queue should reduce lost context without turning every negative phrase or repeated mention into a new incident.

Before you start

Defined operating scope

Ongoing client project conversations contain unanswered questions that need an owner.

Required source material

Obtain Authorized client conversations; Project ownership; Escalation criteria. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

The client repeats a question after receiving an answer. Check whether the answer addressed it; do not assume either resolution or hostility.

Prepare the inputs

conversation_records
Required

Permitted chats and call notes

Keep client, project, channel and timestamps.

project_ownership
Required

Account and delivery owners

Use current routing responsibilities.

issue_rules
Required

Question and escalation definitions

Separate requests, concerns and informal discussion.

resolution_evidence
Required

Replies, tasks and accepted outcomes

Check later context before marking unresolved.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check conversation_records, project_ownership, issue_rules, resolution_evidence 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 conversation_records and any missing required fields.

  2. Collect the relevant conversation scope

    • Collect the bounded client-project scope and note channels or dates that are unavailable.
    • Inspect the latest reply for each unresolved issue and preserve waiting-party state.

    Checkpoint: A saved intermediate result for: Collect the relevant conversation scope.

  3. Extract explicit questions, concerns, and unresolved requests

    • Extract explicit unanswered questions, stated difficulties and requested actions with their supporting turns.
    • Verify duplicate grouping never crosses client or project boundaries.

    Checkpoint: A saved intermediate result for: Extract explicit questions, concerns, and unresolved requests.

  4. Group duplicates and attach evidence

    • Merge references to the same issue and attach later replies, distinguishing answered, action pending and resolution unknown.
    • Inspect the latest reply for each unresolved issue and preserve waiting-party state.

    Checkpoint: A saved intermediate result for: Group duplicates and attach evidence.

  5. Route the review list to the account owner

    • Prepare an owner queue with evidence, agreed response dates and any escalation condition from the supplied rules.
    • Verify duplicate grouping never crosses client or project boundaries.

    Checkpoint: A saved intermediate result for: Route the review list to the account owner.

  6. Package the result and unresolved work

    • Do not infer customer sentiment from isolated phrases. Check context and keep each client’s data within its access boundary.
    • The account team owns interpretation and communication.

    Checkpoint: A client-issue review queue. Unresolved items remain visible in the review record.

Decisions along the way

The client repeats a question after receiving an answer.

Check whether the answer addressed it; do not assume either resolution or hostility.

A request is waiting on client information.

Label the dependency rather than treating it as a team failure.

Two projects share similar issue wording.

Keep client-project boundaries and avoid merging their records.

What you will produce

client-conversation-issue-monitor-result.json

JSON

A client-issue review queue. Label proposed and completed states separately.

Include: client_id · project_id · issue_id · question · waiting_party · latest_evidence · owner · escalation_reason · status · evidence_reference · review_note

client-conversation-issue-monitor-review.md

Markdown

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

Include: source_reference · question · owner · next_action

Check the result

  • Inspect the latest reply for each unresolved issue and preserve waiting-party state.
  • Verify duplicate grouping never crosses client or project boundaries.
  • Inspect conversation_records and project_ownership in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Do not infer customer sentiment from isolated phrases. Check context and keep each client’s data within its access boundary.

When something goes wrong

The client repeats a question after receiving an answer.

Check whether the answer addressed it; do not assume either resolution or hostility. Retain the affected evidence and recovery status.

A request is waiting on client information.

Label the dependency rather than treating it as a team failure. Retain the affected evidence and recovery status.

Two projects share similar issue wording.

Keep client-project boundaries and avoid merging their records. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Surface unresolved client questions from project conversations for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Client A asks for a launch date on Monday. The team requests an asset; the client sends it Wednesday, but no date response follows.

Expected result

Synthetic expected result: Queue the launch-date question as awaiting team response after Wednesday, with the asset dependency marked resolved and the relevant messages attached.

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 valid unresolved requests surfaced; time to owner acknowledgement and resolution.

Stop or revise

Two projects share similar issue wording. Pause affected records and apply this recovery: Keep client-project boundaries and avoid merging their records.

Keep the scope clear

  • The account team owns interpretation and communication.
  • Do not infer customer sentiment or employee performance from isolated phrases.

Check before using

Do not infer customer sentiment from isolated phrases. Check context and keep each client’s data within its access boundary.

Business activities

  • Deliver recurring client work
  • Resolve customer questions

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: Authorized client conversations · Project ownership · Escalation criteria

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 ↗