Automation for hiring · Runs after a meeting is transcribed
Candidate follow-up
A personalized follow-up email drafted after every candidate interview. Your assistant runs it after a meeting is transcribed and tells you when something needs your attention.
Candidate follow-up — Sep 17
Automation run • Sep 17
Candidate follow-up
Output
Juno, here is the follow-up draft for Dara Finch following your 10:00 AM screening call. The email is waiting in your Google Workspace drafts folder. Nothing has been sent.
Interview recap
- Candidate: Dara Finch
- Role: Portland Store Manager
- Hiring manager: Lena Vale
- Outcome: Advance to next interview stage
- Transcript context: Dara spoke about managing seasonal floor volume, visual merchandising, and team retention. Specific schedule availability for next week was not discussed.
Draft waiting in your drafts folder
Subject: Following up on our Harbor & Pine conversation
Hi Dara,
Thank you for taking the time to speak with me this morning about the Portland Store Manager role at Harbor & Pine. I enjoyed learning about your store leadership experience and your thoughts on supporting retail teams during peak seasons.
We would like to move forward to the next step, which is an interview with Lena Vale, our operations and buying lead. Please let me know a few times that work well for you early next week, and I will share a calendar invite.
Best, Juno
Automation steps. Your assistant follows these 3 steps each time it runs, using your connected email and calendar.
- 01
When an interview ends, read the notes or transcript and my recent thread with the candidate, and draft a follow-up email in my voice with clear next steps, matched to where they are: scheduling the next round, still in process, or a kind pass that leaves the door open.
- 02
Make it personal, referencing something real from the conversation.
- 03
Keep it candidate-facing: no scorecard, no internal read, no compensation talk.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Only draft follow-ups for candidates interviewing for the senior ecommerce engineer role.
- Hold draft creation if the transcript notes that internal review with Lena is needed first.
- Include a standard note in rejection drafts asking permission to keep resumes on file.
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
Drafts the email into your drafts folder 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 Candidate follow-up in the job library, and choose Add. If your Google Workspace or Microsoft 365 account is not connected yet, the card lets you connect it right away. The automation turns on to run after each recorded interview transcript finishes.
- What does the automation do on its own versus waiting for me?
- It reviews the interview transcript and writes a draft directly into your email drafts folder. It cannot send messages, delete items, or book calendar events on its own. Every draft waits for you to review and send.
- Where do my results arrive?
- Your assistant posts a summary and draft preview directly in your chat conversation, and it can send them to your inbox as well. If an interview has no transcript or requires no action, your assistant tells you briefly in chat.
- How does it decide what next steps to include in the draft?
- It checks the transcript and recent email history to see if you agreed on another round, promised an update, or concluded the process. It then frames the draft appropriately, whether asking for open dates with Lena Vale or providing a polite closing note.
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.