PlaysbyMoat8
Back to the library
The workflow guideSales

Find relevant service requests in public discussions

Monitor selected public communities for requests that match a service offering and collect relevant opportunities in a shared review list.

6 implementation stepsIntermediate

How this works

Monitor selected public communities for requests that match a service offering and collect relevant opportunities in a shared review list.

Look for explicit requests that match the service offering, not merely people discussing a related topic. Preserve the post’s timing, context and community norms so reviewers can distinguish a live opportunity from advice, promotion or an old resolved request.

Before you start

Defined operating scope

Your service matches explicit requests people make in selected public communities.

Required source material

Obtain Permitted community sources; Service-fit criteria; Positive and negative examples. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

The post offers a service rather than requests one. Exclude it as supplier promotion.

Prepare the inputs

source_scope
Required

Approved public communities and access method

Use permitted public content only.

post_records
Required

IDs, timestamps and thread context

Retain original wording and resolution signals.

service_fit
Required

Needs served and exclusions

Include positive and negative examples.

review_rules
Required

Freshness, deduplication and outreach criteria

Specify acceptable contact channels.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check source_scope, post_records, service_fit, review_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 source_scope and any missing required fields.

  2. Collect recent posts from approved sources

    • Collect the requested time window through available permitted connectors or manual exports, recording incomplete coverage.
    • Check the full available thread for resolution and whether the author is actually requesting help.

    Checkpoint: A saved intermediate result for: Collect recent posts from approved sources.

  3. Filter them against a defined request and customer profile

    • Classify whether each post expresses an actual need and compare that need with the service criteria.
    • Measure distinct genuine requests rather than the number of keyword matches.

    Checkpoint: A saved intermediate result for: Filter them against a defined request and customer profile.

  4. Remove repeated or irrelevant posts

    • Deduplicate cross-posts and exclude resolved, promotional or irrelevant discussions with a reason.
    • Check the full available thread for resolution and whether the author is actually requesting help.

    Checkpoint: A saved intermediate result for: Remove repeated or irrelevant posts.

  5. Present the original context to a person before any outreach

    • Present the original context and a factual relevance explanation to the reviewer without initiating unsolicited contact.
    • Measure distinct genuine requests rather than the number of keyword matches.

    Checkpoint: A saved intermediate result for: Present the original context to a person before any outreach.

  6. Package the result and unresolved work

    • Do not infer private needs from unrelated activity. Verify context, platform rules, and outreach appropriateness.
    • Public visibility does not imply permission for automated bulk messaging.

    Checkpoint: A curated opportunity list grounded in expressed needs. Unresolved items remain visible in the review record.

Decisions along the way

The post offers a service rather than requests one.

Exclude it as supplier promotion.

A later reply says the need was filled.

Mark resolved and remove it from active opportunities.

The collection method cannot access permitted context.

Keep coverage incomplete; do not bypass private-community access controls.

What you will produce

public-demand-signal-leads-result.json

JSON

A curated opportunity list grounded in expressed needs. Label proposed and completed states separately.

Include: post_id · expressed_need · fit_reason · freshness · resolution_state · duplicate_of · review_action · status · evidence_reference · review_note

public-demand-signal-leads-review.md

Markdown

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

Include: source_reference · question · owner · next_action

Check the result

  • Check the full available thread for resolution and whether the author is actually requesting help.
  • Measure distinct genuine requests rather than the number of keyword matches.
  • Inspect source_scope and post_records in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Do not infer private needs from unrelated activity. Verify context, platform rules, and outreach appropriateness.

When something goes wrong

The post offers a service rather than requests one.

Exclude it as supplier promotion. Retain the affected evidence and recovery status.

A later reply says the need was filled.

Mark resolved and remove it from active opportunities. Retain the affected evidence and recovery status.

The collection method cannot access permitted context.

Keep coverage incomplete; do not bypass private-community access controls. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Find relevant service requests in public discussions for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Post P-7 asks for help migrating a shop this month; a later reply says a provider was hired. P-8 describes a current migration need with no resolution.

Expected result

Synthetic expected result: Mark P-7 resolved. Shortlist P-8 only if it fits the service scope, retaining its date and the exact need for human review.

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 genuine requests in the shortlist; reviewer time per qualified opportunity.

Stop or revise

The collection method cannot access permitted context. Pause affected records and apply this recovery: Keep coverage incomplete; do not bypass private-community access controls.

Keep the scope clear

  • Public visibility does not imply permission for automated bulk messaging.
  • Do not infer private needs from unrelated personal posts or join private groups without authorization.

Check before using

Do not infer private needs from unrelated activity. Verify context, platform rules, and outreach appropriateness.

Business activities

  • Find and approach prospects

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: Permitted community sources · Service-fit criteria · Positive and negative examples

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 ↗