Evaluate and Respond to a Candidate No
Analyze interview feedback against your hiring data, decide whether a save attempt is warranted, and draft a Slack message that moves the conversation forward.
Overview
When an interviewer gives a No and something does not add up -- the concern feels thin, was never actually probed in the interview, or contradicts feedback from the rest of the loop -- recruiters typically spend 10-20 minutes manually reviewing the scorecard, re-reading transcripts, and carefully drafting a Slack message that challenges the feedback without dismissing the interviewer. This MCP template automates that entire synthesis: analyzing the data, walking through a structured decision framework, and producing a draft response calibrated for tone and specificity.
How it works
Connect your Ashby, Google Docs, and Slack accounts. When an interviewer submits a No at Job Fit or later, give the AI the candidate name, role, and the stated concern. It pulls the full scorecard and application history from Ashby, reads the relevant hiring rubric from Google Docs, and scans your Slack hiring channel for additional context. It then walks through five structured questions to determine whether a save attempt is warranted -- and either recommends closing with rationale or drafts a Slack message designed to move the conversation forward in a direct, non-template voice. If you have interview transcript excerpts, paste them in and they will be factored into the analysis.
Who this is for
Built for recruiters who trust their read on a candidate and want a structured way to push back on thin or inconsistent feedback -- without coming across as dismissive. Especially useful at Job Fit stage or later, when the cost of getting the conversation wrong is highest.
Suggested prompt
I just got a No from an interviewer on [candidate name] for [role]. The stated concern was [concern]. Help me evaluate whether a save attempt makes sense.
Frequently asked questions
What decision framework does the template use?
The template walks through five structured questions to determine whether a save attempt is warranted: whether the stated concern was actually probed in the interview, whether it contradicts other data points from the loop, whether the hiring rubric supports the objection, how the candidate compares to others you have seen for the role, and whether the concern reflects a genuine disqualifier or an interviewer preference. Based on the answers, it recommends saving or closing -- with rationale.
What data does the template pull from Ashby?
It retrieves the candidate scorecard, feedback from all interviewers, current application stage, and interview loop history. This gives the AI the full picture of what has been assessed and what has been skipped -- which is often the most important part of the analysis.
How does the Slack message avoid sounding like an AI wrote it?
The template is built to produce a direct, recruiter-native voice -- citing specific data points, naming the gap in the interview process, and framing the request as a collaborative conversation rather than a formal challenge. It avoids hedging language and template-sounding phrases.
What if I have a BrightHire transcript to include?
You can paste relevant transcript excerpts directly into the conversation when running the template. The AI will factor them into the analysis alongside the Ashby scorecard and hiring rubric -- strengthening the case if the transcript shows the concern was underexplored or never directly addressed.