Ai Hr Management Toolkit

Parse a resume file (PDF, DOCX, TXT, MD) or URL and extract text with algorithmic pre-analysis including keyword extraction, metrics detection, section identification, and experience estimation.

Unified resume analysis tool. Select which analysis aspects to run via the "aspects" parameter: - "keywords" — TF-IDF keyword extraction with NER overlay and skill categorization - "entities" — Named Entity Recognition (12 types with confidence and disambiguation) - "skills" — Categorized skill extraction with proficiency estimation (13 categories) - "experience" — Structured work history with timeline, achievements, and career progression - "patterns" — Date ranges, metrics, seniority detection, and section analysis - "similarity" — Job description matching with fit tier, gap analysis (requires jobDescription) - "all" — Full comprehensive analysis combining all aspects (default) Accepts raw text or a file (base64-encoded PDF/DOCX/TXT/MD or URL). 100% algorithmic — no AI calls needed.

Parse multiple resume files at once and run the full algorithmic pipeline on each. Returns raw text, pipeline analysis, keywords, entities, and confidence scores for each file. The LLM client should interpret and structure the results.

Assess a resume against recruiter-defined criteria. Supports 8 criteria axes: Education, Experience, Skills, Certifications, Knowledge Stack, Competitions, Thresholds, and Job Qualification. Returns per-axis scores, weighted overall score, and a pass/review/reject decision.

Run the full 5-node atomic deconstruction pipeline (Ingestion → Sanitization → Tokenization → Classification → Serialization) on resume text. Returns stage-by-stage metrics, confidence scores, entity classification with disambiguation, data quality assessment, and assumption audit. Use this to understand HOW the parser processes a resume and WHERE confidence is low.

Unified candidate management for the ATS pipeline. Actions: CRUD: add, update, delete, move, bulk_move, list Analytics: rank (sort by fit), filter (by criteria), recommend_stage (suggest moves), compare (side-by-side), summarize (overview stats) Pass the current candidates record and an action. Returns updated state and/or analysis results.

Manage job postings in the ATS. Actions: create (new job posting), update (edit fields), delete, list (with optional status/department filter), search (by keyword in title/description), close, reopen. Pass current jobs record and an action.

Manage offers in the ATS. Actions: create (validate & structure), update_status (draft→pending-approval→approved→sent→accepted/declined), delete (remove offer), list (all offers with optional filters), compare (side-by-side offer comparison), validate (check for issues). Returns structured offer data.

Manage candidate notes in the ATS. Actions: add (create note on candidate), update (edit note content), list (get all notes for a candidate), delete (remove a note), search (find notes by keyword across one or all candidates), bulk_add (add notes to multiple candidates). Pass the current candidates record.

Full CRUD for interviews. Actions: create (validate & schedule with conflict detection), update (reschedule/modify), delete (permanent removal), list (filter by candidateId/jobId/status), get (single interview by id). Pass existing interviews record for conflict checks.

Manage interview feedback in the ATS. Actions: submit (add feedback to completed interview), get (retrieve feedback for an interview), update (modify existing feedback), delete (remove an interview), list_pending (interviews awaiting feedback), list_completed (interviews with feedback, optionally filtered by candidate), analyze (aggregate feedback for a candidate across all interviews), summary (hiring signal summary for a job or all jobs).

Unified ATS analytics. Select report type: - "dashboard" — Hiring health report: key metrics, stage distribution, offer stats, velocity, insights - "pipeline" — Funnel analysis: conversion rates, avg days-in-stage, bottleneck detection - "full" — Both reports combined

Generate a full set of realistic demo data for the ATS (Applicant Tracking System). Returns a complete ATSState with sample jobs, candidates at various pipeline stages, scheduled interviews, and offers. Useful for testing, demonstrations, or populating an empty ATS instance.

Global search across the ATS. Actions: search (keyword search across candidates, jobs, interviews, offers — scoped optionally), filter_candidates (structured filter by stage/job/tags/score), get_entity (retrieve a single entity by type+id). Pass the full ATS state.

Enterprise compliance toolkit: audit trail queries, EEO/EEOC diversity reporting, GDPR data export & erasure (right to be forgotten), data retention policy checks. Actions: query_audit, eeo_report, eeo_record, gdpr_export, gdpr_erase, retention_check, update_settings, get_settings.

Manage passive candidate talent pools (CRM). Create pools, add/remove candidates, search across pools, get pool analytics. Actions: create, update, delete, list, get, add_candidates, remove_candidates, search, analytics.

Structured interview scorecards — create evaluation templates with weighted criteria, fill scorecards per candidate/evaluator, update templates and entries, aggregate scores to rank candidates, ensure consistent hiring decisions. Actions: create_template, list_templates, get_template, update_template, delete_template, fill, get_entry, update_entry, get_candidate_scores, aggregate, delete_entry.

Post-hire onboarding checklist management. Create checklists with categorized tasks (paperwork, IT setup, training, orientation, compliance), track per-task progress, find overdue items, manage assignees. Actions: create, list, get, update_task, add_task, remove_task, progress, delete, overdue.

Candidate communication management — create email templates with {{variable}} interpolation, preview and send messages, log inbound/outbound communications, search history, and get communication stats. Actions: create_template, list_templates, get_template, update_template, delete_template, preview, send, log, get_history, search_history, stats.

Monitor parsing quality, detect drift when resume formats change, submit human corrections, and view learned error patterns. Use 'check_drift' to see if parsing quality has degraded. Use 'submit_correction' to feed back human corrections that improve pattern detection. Use 'calibrate_baseline' after confirming parsing quality is good to set the reference point.

Export parsed resume results to a specified format (JSON, CSV, or Markdown). Accepts an array of structured resume results and returns formatted output.

Send parsed resume results via email using SMTP. Requires SMTP configuration (host, port, user, pass) and recipient email. Sends an HTML summary of all results.