get_call_ai_notes
ChatGPTGet AI-generated Q&A notes for one or more interviews (up to 20). Returns condensed question-answer pairs automatically extracted from the interview transcript. Each note contains the interviewer's question and the candidate's answer, with timestamps. Each returned call also includes the associated scheduled_interview_id (when present) so guide-coverage workflows can join AI notes to get_interview_guide results without re-querying search. Use this instead of get_transcripts when you want to understand what was discussed without consuming a large context window. AI notes are much smaller than full transcripts but capture the key content. If the organization has data redaction enabled, notes for calls that contain redacted transcript content are omitted for users who cannot view redactions. Accepts up to 20 call_ids at once, so you can batch-fetch notes for multiple interviews from a single search result page. The call_ids can be obtained from search results. Use this tool when: Analyzing interview quality or candidate responses; Comparing answers across multiple interviews for the same position; Summarizing what was covered in an interview; Evaluating interviewer question quality. Each note's question field is AI-generated from the transcript and may paraphrase what was said — use judgment to semantically match notes to topics (e.g. interview guide cues) rather than relying on exact keyword overlap alone.
get_candidate_summary
ChatGPTGet the most recent completed candidate summary notes for a candidate. Returns ordered summary notes with topic, subtopic, and text.
get_coaching_report
ChatGPTGet the calling user's most recent BrightHire AI coaching report as raw markdown. Coaching reports summarize trends and feedback across the user's recent interviews. Takes no arguments — the user is inferred from the MCP session, and only their own report is returned. Returns the report as a single markdown text block. If the user has no coaching report yet, the tool returns an error indicating the report was not found.
get_interview_context
ChatGPTGet interview prep context for a scheduled interview. Returns scheduled start time, candidate and position metadata, action URLs, interview guide, and candidate summary.
get_interview_guide
ChatGPTGet interview guides for one or more scheduled interviews (up to 20). Returns a list of guides, each with the guide name and an ordered list of questions/cues to help the interviewer prepare. Accepts up to 20 scheduled_interview_ids at once so you can batch-fetch guides for a full page of search results. For large batches, pass fields: ['cue'] to omit long description text and shrink the response dramatically.
get_interview_summary
ChatGPTGet a post-interview summary for a single interview by interview_id. Returns candidate name, position title, user-created interviewer notes (text notes, cues, comments), emoji reactions (thumbs up/down, star, flag) with counts, and action links (interview_url, share_url, ats_scorecard_url). Use this to build a recap of what the interviewer captured during the call. For AI-generated Q&A notes derived from the transcript, use get_call_ai_notes instead.
get_job_description
ChatGPTGet one or more job descriptions. Pass position_id for a single role or position_ids (1-50 UUIDs) to batch-fetch JDs for multiple positions in one call. Use this to understand role requirements, key skills, qualifications, and responsibilities. position_ids can be found in search results (each interview is associated with a position). This is especially useful for: Understanding what skills and competencies to evaluate when analyzing interviews; Comparing candidate responses against the actual job requirements. On success returns {job_descriptions: [{position_id, title, ats_job_posting_id, ats_job_posting_updated_at, description}]}. Positions you can't view, that don't exist, or that have no ATS JD attached are silently omitted from the response — diff the input set against the returned position_ids if you need to know which were dropped. If every requested position would be dropped, the tool returns an error result instead of an empty payload, so you don't need to special-case an empty list — just stop and surface the error to the user.
get_scheduled_interviews
ChatGPTGet upcoming scheduled interviews. Returns metadata for each scheduled interview including candidate name, position title, interviewers, and scheduled start/end times. By default returns interviews scheduled from now through the next 7 days. Use from_date and to_date to customize the time range (accept either a Unix timestamp in seconds OR an ISO 8601 date/datetime string; naive values are treated as UTC). Set current_user_only: true (default) to only return interviews where you are a scheduled interviewer. Set current_user_only: false to see all scheduled interviews you have access to in your organization. The scheduled_interview_id in results can be used with get_interview_context to get full interview prep details including the interview guide and candidate summary.
get_scorecards
ChatGPTGet Greenhouse ATS scorecards for one or more interviews (up to 20). Returns the interviewer's overall recommendation from their ATS scorecard, along with scorecard attributes and questions. Each scorecard belongs to one interviewer for one interview. You can query either by explicit call_ids, or by candidate_id + position_id. First use search to find interviews by candidate name, interviewer, date, or position, then pass the call_ids here. For candidate-position workflows, pass candidate_id and position_id to fetch calls for that pair. Use this tool when: Comparing interviewer assessments across interviews for a candidate; Understanding how an interviewer rated a candidate; Aggregating scores across a hiring panel for a position. This is the source for formal ATS scorecard data and recommendations — not a substitute for get_interviewer_signal_quality, which measures behavioral patterns from AI notes.
get_transcripts
ChatGPTGet full verbatim transcript segments and user-created call notes for one or more interviews (up to 20 call_ids per request). Large payload — prefer get_call_ai_notes for condensed Q&A. Pass call_id values from search results. If the organization has data redaction enabled, segment text may contain Redacted tokens in place of detected PII / EEOC content; users with permission to view redactions receive the original unredacted text.
search
ChatGPTSearch BrightHire interviews using structured filters (optional interview name, department, location, outcome, stage, type, position, interviewer, candidate, date range, etc.). Returns metadata for each matching interview (call_id, candidate_id, candidate name, position, interviewers, date, duration, stage, outcome). Set my: true to restrict results to interviews where the authenticated user was an interviewer. Set my: false (default) to search across all interviews the user has access to in their organization. For full verbatim transcripts and user-created notes, call get_transcripts with call_id values from search results (large payload — batch appropriately). For condensed Q&A, use get_call_ai_notes instead. Use page (0-indexed) to paginate through results. Each page returns up to limit results. If a page returns fewer than limit results, it is the last page. Optional min_date / max_date bound interview start time (accept either a Unix timestamp in seconds OR an ISO 8601 date/datetime string; naive values are treated as UTC). When both are omitted, no date filter is applied. The call_id field in search results can be used with get_call_ai_notes to retrieve AI-generated Q&A notes, with get_scorecards to retrieve interviewer scores and feedback, or with get_job_description (via the position_id) to understand what the role requires.
get_call_ai_notes
Claudeget_candidate_summary
Claudeget_coaching_report
Claudeget_interview_context
Claudeget_interview_guide
Claudeget_interview_summary
Claudeget_job_description
Claudeget_scheduled_interviews
Claudeget_scorecards
Claudeget_transcripts
Claudesearch
Claude
