The Meeting Notes template makes your AI turn a meeting into shareable notes: save the raw record, extract the summary, decisions, owners and open questions, and format them for the team. It stops once, so you confirm the decisions and owners before anything is distributed. Every version is kept as a task note.
4 steps · 1 approval
example · the steps are this template's real steps
For team leads and operators who leave meetings with rough notes or a transcript and need clean decisions and owners the same day.
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.
4 steps, in this order. Below each one is the instruction your AI receives at that step, exactly as the template stores it.
Capture the raw record of the meeting before structuring anything.
Record:
If the record is incomplete, ask the operator for the missing pieces.
Save the raw meeting record as a task note with task_notes_add. The next step (Extract) reads this note.
Read the task notes with task_notes_list: the note from the Capture step contains the raw record. Work from it.
Extract clean structure. What good looks like:
Capture only what was said: do not invent decisions or owners.
Save the structured notes as a task note with task_notes_add. Then ask the operator to confirm the decisions and owners are right before distributing. This is a checkpoint: once notes go out they shape what people act on, so the AI cannot advance until you approve.
no rejection path · the run moves on only when approved
Read the task notes with task_notes_list: the note from the Extract step contains the confirmed notes. Work from it.
Format the notes for sharing:
Share the notes with the people who need them, or hand the formatted version to the operator to post.
Save the final shared notes as a task note with task_notes_add so the record of what was distributed stays on file.
The meeting notes are structured and distributed. Confirm the final notes are saved as a task note, then 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.
Once notes go out they shape what people act on. You confirm the decisions and the owners are right before the AI distributes anything.
what you review
no rejection path · approve to continue
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 Meeting Notes 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 Extract instruction says to capture only what was said and not invent decisions or owners. You then confirm the decisions and owners at the Extract approval before distribution.
Each step saves its output as a task note: the raw record at Capture, the structured notes at Extract, the shared version at Distribute. The next step reads the previous note, so a fresh session can pick up where the last one stopped.
Meeting Notes produces internal notes for the team. Meeting Follow-Up drafts a message to the other side of a call and gates the send.
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.