Copy-paste prompt
Every day at 5pm while the role is open, read new applications in [inbox/folder]. Score each against [scorecard] using only job-related criteria, and quote the resume line behind every score. List anything missing rather than guessing. Draft a next-step email for each candidate. Don't send anything or make any hiring decisions.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- Applications inbox or export
- Role scorecard
How the agent does it
- Read each new application and resume.
- Score it against the must-haves and nice-to-haves, quoting the evidence.
- Flag missing information instead of guessing.
- Draft a next-step email: schedule a call or politely decline.
What you get
A candidate table (scores, evidence, gaps) and draft emails.
| Schedule | Daily at 5pm while the role is open. |
|---|---|
| Needs your approval | All hiring decisions and all candidate emails need the owner. Don't use protected characteristics. |
| How to check it worked | Each score quotes the resume line it came from. |
Common mistakes
- Bias. Score only against job-related criteria in the scorecard, and leave the final call to the human.
Setting it up in each agent
In Grok Bot
Ask the Bot to run the prompt once and review the result. Then say "Save the process we just used as a skill called 'Applicant screening summaries'" and "Create a routine that runs the Applicant screening summaries skill daily at 5pm while the role is open". Grok Bot's docs say a Bot can own up to 50 routines, schedules must be at least five minutes apart, and you should use Test run before you enable one.
In Meta Muse
Paste the prompt into Muse and ask it to remember the job and run it on the schedule. Muse asks for approval before outbound actions and purchases, so keep the 'don't send' line in the prompt. Before you rely on it, check that Muse can reach the apps this recipe needs.
In ChatGPT Dots
Give your dot the prompt as an ongoing goal and set the schedule. Dots can work between chats and ask for approval before sensitive actions. OpenAI says background work counts toward your plan's allowance, so match the frequency to what you actually need.
Run it by hand once with harmless inputs before you schedule it. A test run does real work.