PlaysbyMoat8
Back to the library
The workflow guideSales

Turn a warm introduction into a relationship record

A practitioner demonstrated an assistant finding an introduction email, researching the new contact, and recording the relationship context and agreed next steps in a local CRM.

6 implementation stepsIntermediate

How this works

A practitioner demonstrated an assistant finding an introduction email, researching the new contact, and recording the relationship context and agreed next steps in a local CRM.

Capture a specific warm introduction as a relationship event, preserving the introducer and what was actually agreed. Add only relevant professional background, and distinguish an invitation to talk from an accepted meeting or promise.

Before you start

Defined operating scope

Warm introductions create relationship context and commitments that should reach the CRM.

Required source material

Obtain Introduction email; Existing relationship context; Permitted public profile information. If connectors are unavailable, use authorized files with the same fields.

Decision and exception rules

The contact already exists under another address. Merge only after identity verification and preserve the new introduction event.

Prepare the inputs

introduction_message
Required

Selected email and thread

Identify introducer, recipient and introduced contact.

existing_records
Required

Contact and relationship matches

Check duplicates before creating a record.

public_background
Required

Permitted professional sources

Record dates and identity confidence.

next_step_rules
Required

Commitment and draft-follow-up criteria

Preserve the difference between suggestion and agreement.

Implementation, step by step

  1. Establish the working record

    • Confirm the selected records, effective versions and responsible owner.
    • Check introduction_message, existing_records, public_background, next_step_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 introduction_message and any missing required fields.

  2. Find the specified introduction and identify the people involved

    • Find the specified introduction and parse each person’s role in the thread, using addresses and context to resolve identity.
    • Verify identity and relationship roles from the original email thread.

    Checkpoint: A saved intermediate result for: Find the specified introduction and identify the people involved.

  3. Research the new contact’s relevant professional background

    • Research the new contact’s relevant current work without expanding into unrelated personal background.
    • Check commitments against actual acceptance and keep enrichment sources dated.

    Checkpoint: A saved intermediate result for: Research the new contact’s relevant professional background.

  4. Save a relationship record with sources and commitments

    • Create or propose a relationship record linking the introduction, professional evidence and explicit commitments.
    • Verify identity and relationship roles from the original email thread.

    Checkpoint: A saved intermediate result for: Save a relationship record with sources and commitments.

  5. Prepare a follow-up draft when needed

    • Prepare a concise follow-up draft if requested, referencing the introducer accurately and leaving unaccepted timing as a proposal.
    • Check commitments against actual acceptance and keep enrichment sources dated.

    Checkpoint: A saved intermediate result for: Prepare a follow-up draft when needed.

  6. Package the result and unresolved work

    • Check identity matches and distinguish promises from suggestions. This was a user-triggered experimental CRM workflow, not autonomous processing of the entire inbox.
    • Process the selected introduction, not the entire inbox.

    Checkpoint: A contact record with useful background and next steps. Unresolved items remain visible in the review record.

Decisions along the way

The contact already exists under another address.

Merge only after identity verification and preserve the new introduction event.

The introducer suggests a meeting but nobody accepts.

Record a proposed next step, not a scheduled commitment.

Public background matches a different person.

Discard the enrichment and keep the introduction record with background unknown.

What you will produce

capture-warm-introduction-in-relationship-record-result.json

JSON

A contact record with useful background and next steps. Label proposed and completed states separately.

Include: contact_id · introducer · introduction_reference · professional_context · relationship_event · proposed_next_step · status · evidence_reference · review_note

capture-warm-introduction-in-relationship-record-review.md

Markdown

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

Include: source_reference · question · owner · next_action

Check the result

  • Verify identity and relationship roles from the original email thread.
  • Check commitments against actual acceptance and keep enrichment sources dated.
  • Inspect introduction_message and existing_records in both the original and output; confirm that record identity and interpretation survived the transformation.
  • Check identity matches and distinguish promises from suggestions. This was a user-triggered experimental CRM workflow, not autonomous processing of the entire inbox.

When something goes wrong

The contact already exists under another address.

Merge only after identity verification and preserve the new introduction event. Retain the affected evidence and recovery status.

The introducer suggests a meeting but nobody accepts.

Record a proposed next step, not a scheduled commitment. Retain the affected evidence and recovery status.

Public background matches a different person.

Discard the enrichment and keep the introduction record with background unknown. Retain the affected evidence and recovery status.

A worked example

SYNTHETIC EXAMPLE · NOT A REPORTED BUSINESS RESULT

Request

Turn a warm introduction into a relationship record for the following bounded example; prepare the result for review.

Inputs

Synthetic example: Email I-3 says 'R-1, meet C-8; you may want to compare onboarding approaches.' C-8 has not replied.

Expected result

Synthetic expected result: Record R-1 as introducer and onboarding as context. Next step is optional outreach, not an agreed call. A draft can thank the introducer without claiming prior familiarity.

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 correct contact and commitment capture; time to a reviewed relationship record.

Stop or revise

Public background matches a different person. Pause affected records and apply this recovery: Discard the enrichment and keep the introduction record with background unknown.

Keep the scope clear

  • Process the selected introduction, not the entire inbox.
  • Saving a relationship draft does not authorize outreach or imply consent to a marketing sequence.

Check before using

Check identity matches and distinguish promises from suggestions. This was a user-triggered experimental CRM workflow, not autonomous processing of the entire inbox.

Business activities

  • Find and approach prospects
  • 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: Introduction email · Existing relationship context · Permitted public profile information

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 ↗