The Outreach Message template makes your AI send personalized outreach: capture the prospect and offer, research one specific, current hook, draft a short message with one clear ask, check it before sending, then log the outcome. Sending is irreversible, so it stops for your approval. Reject it and it redrafts.
5 steps · 1 approval · 1 loop back
example · the steps are this template's real steps
For founders and sales reps writing cold emails or LinkedIn messages who want each one grounded in research, not a template.
It is a stored workflow, not a prompt. Your AI client receives one step at a time from ConvOps over MCP, does the work, and advances. The engine holds the run at the approval until a person says yes.
5 steps, in this order. Below each one is the instruction your AI receives at that step, exactly as the template stores it.
Capture the prospect and the offer before researching.
Record:
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.
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:
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.
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:
Save the full message as a task note with task_notes_add. The Send Review step reads this note.
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:
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.
rejected → back to Draft
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:
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.
One step waits for a person. You answer in the chat; the engine records the verdict and the audit row records who gave it.
Sending is irreversible. The AI checks name, role, company, the hook's accuracy, the ask and any link. You approve or send it back to Draft.
what you review
reject → back to Draft
gates the engine checks without you
Read from the template's own steps: the tools they call, the files they write, and whether they touch code.
Connect your AI client first, then install Outreach Message from the catalog in the ConvOps app. See how to connect a client
An installed template is a workflow in your workspace. Ask your AI to change it in plain words; the edit lands on the one step that needs it.
new chat
more example prompts
The Research step tells it to say so rather than invent one. A relevant hook beats a clever line, and Send Review checks the hook is accurate.
Who was contacted, on which channel and when, the message sent, the result so far (replied, no reply, bounced, meeting booked) and the next action. It is the named input for a Meeting Follow-Up if the prospect responds.
Yes. Prospect Intake pulls the entry from a Prospect Research list when the prospect came from one.
Any MCP client connected to ConvOps. Verified clients: Claude Code, Claude (desktop, web, Cowork), OpenAI Codex, ChatGPT, Cursor, OpenCode. It needs no repository, so a plain chat client works.