Automation for hiring · Runs after a meeting is transcribed
Meeting debrief
A structured debrief with action items and drafted follow-up emails. Your assistant runs it after a meeting is transcribed and tells you when something needs your attention.
Meeting debrief — Sep 17
Automation run • Sep 17
Meeting debrief
Output
Here is the debrief from your Portland store manager candidate review with Lena Vale on September 17 at 10:30 AM.
Key takeaway Lena recommends advancing Dara Finch to the final reference check and store walkthrough for Harbor & Pine.
Action items
- Juno Pell: Request two professional references from Dara Finch by Friday.
- Lena Vale: Outline the in-person walkthrough schedule at Portland Warehouse and the retail floor.
- Transcript ambiguity: The audio was unclear when Lena mentioned target start dates. It sounded like either October 12 or October 19. Please confirm the date with Lena before finalizing next steps.
Draft follow-up email This draft is waiting in your Google Workspace drafts folder. Nothing has been sent.
To: lena@example.com Subject: Next steps for Dara Finch
Hi Lena,
Thanks for debriefing today on Dara Finch for the store manager role at Harbor & Pine. I will ask Dara for two professional references today.
Once you have the walkthrough outline ready, let me know. Also, please confirm whether your target start date is October 12 or October 19, as the recording cut out briefly during that part.
Best, Juno
Automation steps. Your assistant follows these 3 steps each time it runs, using your connected email and calendar.
- 01
After each meeting, write a structured debrief with the action items assigned to the right attendees.
- 02
Draft follow-up emails to the attendees in my voice.
- 03
Flag any spot where the transcript was ambiguous so I can confirm it before anything goes out.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Only debrief meetings that include candidates or hiring managers.
- Skip follow-up email drafts for internal catchups with Lena Vale.
- Include direct interview scorecard questions in the debrief notes.
Results arrive as a message from your assistant. Each run posts to your conversation with your assistant, and can email you too. The automation keeps a log in your knowledge base and reads it before each run to see what has changed.
What starts this automation
Runs after a meeting is transcribed.
Only useful reports
When nothing needs attention, the run says so in a line or stays quiet. When there are findings, you get them with a link to the full run.
What it does on its own
Writes the debrief and drafts emails on its own. Every follow-up waits for you to send. An automated run has no tool that sends, posts, shares, or deletes anything.
This automation reads your email and calendar. Connect Google Workspace or Microsoft 365 to Fieldwork. The automation uses whichever you connect. It also uses your meeting notes when connected.
More automations for hiring.
Questions about this automation.
- How do I set this up?
- Open your assistant on the Agents page in Fieldwork, locate Meeting debrief in the job library, and select Add. If your Google Workspace or Microsoft 365 account is not linked, the card lets you connect it along with Granola or Fireflies before activating.
- What does it do on its own, and what waits for me?
- It produces the summary and creates draft emails on its own after each transcript is ready. It will never send an email, share notes, or edit your calendar, so every drafted follow-up waits in your drafts folder for your review.
- Where do my debriefs arrive?
- Your debrief arrives in your Fieldwork chat thread, and you can choose to have it emailed to you as well. If a transcribed call has no notable action items, your assistant lets you know briefly or stays quiet.
- What happens if a transcript is incomplete or hard to hear?
- The debrief calls out any ambiguous sections, missing names, or unclear commitments under a dedicated section so you can clarify them before reaching out to attendees.
Security first
No training on your data
Neither we nor our model providers train on your data. Inference runs with zero retention wherever the provider supports it.
Access
Agents only see what the person asking can see. Conversations, files, apps and connections stay private until shared, and admins have no way into conversations.
Encryption and isolation
Data is encrypted at rest and in transit. Each user's code runs in its own microVM, and secrets reach models by name only.
Continuity
Continuous backups, replicated to a second region. Data is exported on request and deleted within 30 days of a contract's end.