Automation for hiring · Runs after a meeting is transcribed
Interview write-up
A completed scorecard and interview notes formatted for your tracker. Your assistant runs it after a meeting is transcribed and tells you when something needs your attention.
Interview write-up — Sep 17
Automation run • Sep 17
Interview write-up
Output
Here is the scorecard and interview summary for Dara Finch, candidate for store manager for Portland at Harbor & Pine.
I recommend advancing Dara to the hiring manager interview with Lena Vale.
Candidate scorecard
- Candidate: Dara Finch
- Role: Store Manager, Portland
- Stage: Recruiter screen
- Recommendation: Advance
- Retail leadership: Strong. Managed a team of 14 at an outdoor specialty store, handling scheduling, floor merchandising, and cash closing.
- Brand alignment: High. Showed familiarity with Harbor & Pine outerwear lines and customer service standards.
- Inventory control: Solid floor experience, though vendor replenishment planning is limited. Lena Vale can probe this further.
- Compensation: Looking for $72,000 to $76,000 USD base salary, which aligns with the posted band.
- Availability: Two weeks notice.
Interview notes
- Background: Six years in apparel retail, with three years as assistant store manager. Supervised daily opens and seasonal staff training.
- Customer service: Gave concrete examples of handling return disputes calmly under store policies.
- Team management: Built weekly shift schedules and handled conflict directly between floor associates.
Proposed next step
Advance Dara Finch to the hiring manager stage in your tracker. Lena Vale would conduct the next 45-minute interview. No changes have been made in your tracker or calendar.
Automation steps. Your assistant follows these 4 steps each time it runs, using your connected email and calendar.
- 01
When an interview ends, pull the notes or transcript and what we know about the candidate and the role.
- 02
Draft my scorecard and a clean set of interview notes in the exact format my scorecard uses, ready to paste into my tracker, and suggest the stage change (advance, hold or reject) with my reasoning.
- 03
Keep candid notes, concerns and compensation internal.
- 04
Ask me for my scorecard's fields and stage names the first time if you don't know them.
Adjust the automation in chat
Tell your assistant what to do differently and it sets up that version for you.
- Only draft scorecards for calls that match candidate interview calendar events.
- Add a dedicated section for suggested follow-up questions for Lena Vale.
- Flag any candidate whose salary expectation is above our posted band.
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 scorecard and notes on its own. Changes nothing. 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 files, 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 Interview write-up in the job library, and choose Add. If your calendar in Google Workspace or your meeting tool such as Granola or Fireflies is not connected yet, the card offers to connect it first. It triggers automatically after each recorded interview transcript finishes.
- Does it update my recruiting tracker or message candidates?
- No, it only drafts the scorecard and notes inside your conversation for you to review and copy. It never posts updates, changes candidates stages in external tools, or sends emails to applicants.
- Where do the completed write-ups arrive?
- Results arrive as a message in your conversation with your assistant, and Fieldwork can email them to you as well. If a transcribed call is not an interview, the assistant stays quiet or notes briefly that no review was needed.
- How does it learn my scorecard fields and stage names?
- Your assistant asks for your scorecard fields and preferred stage names on the first run if it does not know them. You can also paste your standard scorecard template or stage criteria into chat at any time.
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.