Workable candidate screening to Slack: automatic AI fit scores

PromptCreate

When a new candidate is created in Workable, I want an agent to screen the application against the role they applied for and post a recommendation to our hiring channel in Slack. Use a poll trigger on Workable's new candidate event so each application is screened as it arrives.

First, work out which job the candidate applied to and pull that job's full description and requirements using the Workable List Jobs operation. This is the yardstick the candidate gets measured against, so keep the requirements, the responsibilities, and any stated must haves versus nice to haves.

Then pull the candidate's detail using the Workable List Candidates operation, filtered by that job and by the candidate's email address. Take their profile, resume detail, and their answers to the screening questions. Important: our Workable integration exposes list operations only (List Candidates, List Jobs, List Stages, List Events) and there is no single candidate lookup, so always retrieve candidate detail through List Candidates using its job, stage, email, and date filters rather than trying to fetch one candidate by id.

Have the agent compare the candidate against the role requirements and produce a short structured verdict with exactly these parts: a fit score out of 10, three bullet strengths, up to two concerns or gaps, and a clear advance or hold recommendation with one line of reasoning. Keep it tight and specific, citing what the candidate actually said or showed rather than generic praise. If the application is thin, for example there is no resume or the screening questions were skipped, say so explicitly and let it pull the score down. Never invent experience the candidate did not claim.

Post the result to the hiring channel with the Slack Bot Send a Message operation. The header line should carry the candidate name, the role title, and a link back to the Workable candidate profile so a recruiter can open the full application in one click.

Put the fit score threshold at the top of the workflow as a clearly labelled, user-editable setting, defaulting to 7 out of 10. When the score is at or above the threshold, post the full structured write-up. When it is below, post a single compact line instead, carrying the name, role, score, a very short reason, and the profile link, so the channel does not get noisy when a job is receiving heavy inbound. The Slack channel should be editable in the same place as the threshold.

This workflow is read only on the Workable side. Do not move candidates between stages, do not disqualify anyone, and do not send any email to the candidate. Every hiring decision stays with the team; the workflow only reads and reports.

Example output

🟢 Priya Raghavan | Senior Backend Engineer | View in Workable Fit score: 8/10, Advance Strengths • Six years building payment systems in Go, matching the core requirement • Led a monolith to services migration at a company of similar size • Answered the on-call question with specifics, including an incident she owned end to end Concerns • No Kubernetes experience mentioned, which is listed as nice to have • Based in Berlin, the role is hybrid in Dublin Recommendation: Advance. Strongest payments background in the pipeline so far, and the only gap is a nice to have. --- ⚪ Tom Whelan | Senior Backend Engineer | 4/10, Hold. Mostly frontend work, no backend systems experience. View in Workable

What does this prompt do?

Watches Workable and picks up each new candidate the moment their application lands.
Reads the description and requirements for the role they applied to, then their profile, resume detail, and answers to your screening questions.
Writes a short verdict: a fit score out of 10, three strengths, up to two concerns, and a clear advance or hold call with one line of reasoning.
Posts the full write-up to your hiring channel for candidates at or above your score threshold, and a single compact line for everyone below it.

What do I need to use this?

A Workable account containing the jobs and candidates you want screened.
An administrator in Workable, since only admins can connect the account.
A Slack workspace and the channel where your hiring team follows applications.
Job descriptions in Workable that actually spell out requirements, since that is what candidates get measured against.

How can I customize it?

Change the score threshold. The default posts a full write-up at 7 out of 10 and above, and a single line below that.
Point it at a different Slack channel, or route different roles to different channels.
Adjust what the verdict covers, such as how many strengths it lists or whether it comments on location and salary expectations.

FAQs

Does this screen candidates for every job, or can we limit it?

Out of the box it screens every new candidate in your account. You can narrow it to specific roles so it only runs for the jobs where you actually want a second opinion.

Will this flood our Slack channel?

No. That is exactly what the score threshold is for. Only candidates at or above the score you set get the full write-up. Everyone below gets one compact line, so the channel stays readable even during a busy hiring push.

Does it reject or move candidates automatically?

No. It only reads from Workable and posts to Slack. Nothing is changed in your pipeline, no candidate is disqualified, and no email is sent. Every hiring decision stays with your team.

What happens if someone applies without a resume?

It works with whatever the application actually contains and says plainly what was missing, rather than inventing experience the candidate never claimed. A thin application usually shows up as a lower score with the gap called out.

How do we improve the quality of the scoring?

Candidates are scored against the job description and requirements stored in Workable, so a clear, specific job post produces a much sharper verdict than a vague one. Tightening your requirements list is the fastest way to improve results.

Related templates

Build a credential rotation checklist when someone leaves

When someone leaves, we check which shared passwords they used in their final months and post a ranked rotation list to your security channel.

+1

Agentic Task

Weekly Amazon S3 bucket security audit posted to Slack

Every Monday, check every S3 bucket for public exposure, missing encryption and weak backup settings, then get the risks ranked in Slack.

Agentic Task

Log Agorapulse social conversations to HubSpot contacts

Twice every weekday, the conversations from your social inbox land on the right HubSpot contact timelines, with a Slack recap for sales.

Agentic Task

Clean up HubSpot contacts from your Amazon SES suppression list

Every morning, find the addresses that hard bounced or filed a spam complaint, update the matching HubSpot contacts, and post a short Slack recap.

Agentic Task

Draft polite follow-ups for emails that never got a reply

Every weekday at 4pm, spot the threads that went quiet, stage a ready-to-send nudge in your mailbox, and get a ranked Slack recap.

Agentic Task

Replay failed SQS messages when a bug fix is merged

When you merge a fix in GitHub, this agent checks the matching dead-letter queue, replays the failed messages, and reports back on the pull request and in Slack.