Recruitment Assistant Agent

Agent Description:

The Recruitment Assistant Agent is designed to automate the initial stages of candidate screening by transforming unstructured CVs into actionable intelligence. It enables HR teams to objectively evaluate large volumes of applicants by extracting key professional attributes, identifying skill gaps, and calculating holistic "fit" scores based on weighted organizational requirements.

Purpose and Components
  • Purpose: This template streamlines the recruitment funnel by parsing various document formats (PDF, DOCX, Text), validating the clarity and completeness of extracted data, and directly routing candidate profiles for skill evaluation while forwarding confidence scores and noting any missing information. The agent eliminates manual data entry and reduces screening bias by providing a standardized, multi-dimensional scoring rubric for every candidate.

    The agent improves talent acquisition efficiency by:

    • Extracting and normalizing core CV fields (Skills, Experience, Education) with associated confidence scoring.

    • Holistically evaluating CV quality to flag low-detail or unstructured submissions.

    • Automatically comparing candidate skill sets against specific job descriptions using semantic similarity.

    • Computing weighted fit scores across four pillars: Skills, Experience, Profile Consistency, and Engagement.

    • Categorizing candidates into clear labels (Excellent, Moderate, or Low Fit) with detailed justifications.

  • Components:

    • CV Extractor: Converts unstructured resumes into structured JSON, assigns a confidenceScore based on data completeness, and notes any missing or unclear information for downstream consideration.

    • Skill Evaluator:Receives candidate profiles directly from the CV Extractor regardless of confidence score. Performs a deep-dive comparison between applicant skills and the target job description to compute a match score while factoring in any flagged data gaps.

    • Final Scorer: The aggregation engine that calculates a weighted candidate profile and produces the final fit summary, taking into account the extracted data, confidence scores, and evaluations.

Supported Capabilities

  • Multi-format CV parsing (PDF/DOCX/Text)

  • Holistic confidence scoring (0.0–1.0) based on section completeness

  • Data normalization (Name, Skills, Experience, Education)

  • Semantic skill similarity analysis and keyword matching

  • Missing vs. Strong skill identification

  • Weighted scoring logic: 40% Skills, 30% Experience, 20% Consistency, 10% Engagement

  • Direct candidate handoff with confidence score forwarding and missing data tagging.

  • Automated candidate labeling (Excellent, Moderate, Low Fit)

LLM Used

Sub-Agents

1. CV Extractor

  • Role:CV Extractor

  • Scope:Converts unstructured CVs into structured JSON with confidence scoring.

  • Description:Extracts name, skills, experience, and education. It evaluates the CV's clarity holistically to assign a confidence score, passing the extracted data and confidenceScore forward while noting any missing or unclear information.

  • LLM Used: Default (Inherits from parent agent).

2. Profile Evaluator

  • Role:Profile Evaluator

  • Scope:Manages workflow execution and handoff to technical evaluation nodes.

  • Description:Acts as the logic controller. Always hands off the candidate profile directly to the Skill Evaluator, regardless of confidence score.

  • LLM Used: Default (Inherits from parent agent).

3. Skill Evaluator

  • Role:Skill Evaluator

  • Scope:Evaluate candidate skills and experience against specific job requirements.

  • Description:Uses keyword similarity and embeddings to identify missing vs. strong skills. Evaluates candidate profile data alongside any noted missing or unclear information forwarded from the CV Extractor, computing a match score (0–1).

  • LLM Used: Default (Inherits from parent agent).

4. Final Scorer

  • Role:Final Scorer

  • Scope:Generate a holistic, weighted evaluation of the candidate.

  • Description:Aggregates all data to compute a final weighted score (Skills, Experience, Consistency, Engagement). Considers all extracted data, confidence scores, and notes to produce a summary labeling the candidate as an Excellent, Moderate, or Low Fit.

  • LLM Used: Default (Inherits from parent agent).

Agent Workflow Behavior Summary

  1. Input: A CV file is uploaded to the CV Extractor.

  2. Validation: The Extractor identifies fields like "Python" and "5 years experience." t computes a confidenceScore and flags any missing or unclear details.

  3. Routing: The Profile Evaluator passes the candidate profile directly to the Skill Evaluator, regardless of confidence score, along with all extracted data and notes.

  4. Scoring: The Skill Evaluator and Final Scorer receive the skill match and experience relevance to calculate the final percentage while taking noted data gaps into account.

  5. Final Output: A comprehensive candidate report with a fit label and justification.

Sample Questions:

  • Screen the attached CV for the Senior DevOps Engineer role.

  • Evaluate candidate John Doe's profile against our mandatory skill list for Project Managers.