Outreach Message
Send personalized outreach from prospect to logged outcome. The AI drives Research, Draft, and a send checkpoint.
the steps, as stored
- 01Prospect Intake
Capture the prospect and the offer before researching.
Record: - Prospect — name, role, company, and contact channel - Your offer — what you are reaching out about, in one sentence - Desired outcome — a reply, a meeting, a demo - Any prior contact with this prospect or account
If this prospect came from a Prospect Research workflow, pull their entry from that list. If key details are missing, ask the operator.
Save the prospect and offer as a task note with task_notes_add. The next step — Research — reads this note.
- 02Research
Read the task notes with task_notes_list — the note from the Prospect Intake step contains the prospect and offer. Work from it.
Research the prospect and account to find a genuine, specific hook. What good looks like: - One concrete, current detail you can reference — a recent post, a hire, a funding round, a product change, a stated pain - Why that detail connects to your offer - The right angle for this specific person, not a generic pitch
A relevant hook beats a clever line. If you find nothing specific, say so rather than inventing it.
Save the research hook and angle as a task note with task_notes_add. The Draft step reads this note.
- 03Draft
Read the task notes with task_notes_list — the Research note holds the hook and angle, and the Prospect Intake note holds the offer and desired outcome. Work from them.
Write the message. What good looks like: - Opens on the specific hook, not "I hope this finds you well" - Connects the hook to the offer in a sentence or two - One clear, low-friction ask matching the desired outcome - Short — respect the reader's time - The right tone and length for the channel (email vs LinkedIn)
Save the full message as a task note with task_notes_add. The Send Review step reads this note.
- 04Send Reviewapproval gate
Read the task notes with task_notes_list — the note from the Draft step contains the message. Work from it.
Check the message before sending: - Right name, role, and company — no merge-field mistakes - The hook is accurate and the claim is true - The ask is clear and matches the desired outcome - Any link works
Ask the operator to approve the message for sending. This is a checkpoint — sending is irreversible, so the AI cannot advance until you approve. If you reject, the workflow returns to Draft.
- 05Log Outcomecontext gate
The message is approved and sent. Record the outcome so the next person — or a follow-up workflow — has the full picture.
Save a task note with task_notes_add capturing: - Who was contacted, on which channel, and the date - The message that was sent - The result so far — replied, no reply, bounced, meeting booked - The next action and when, if any
This note is the audit trail for this outreach and the named input for a Meeting Follow-Up workflow if the prospect responds. Close out the task.
use it for
- Write a cold email tailored to one prospect's role and trigger
- Draft a LinkedIn outreach message grounded in real research
- Reach out to a lead and record the outcome for follow-up
without it, with it
| without | with outreach message |
|---|---|
| A generic template goes out with the wrong first name and zero relevance to the prospect | The AI drives a Research step first, so the message lands on something specific about that account |
| The send happens before anyone checks the claim, the link, or the ask | The AI pauses at a send-review checkpoint so you sign off before the message goes out |
| Nobody remembers whether this prospect was already contacted or what the reply was | The AI logs the outcome as a note, so the audit trail of who was contacted and what happened is already there |