Aidena

— AI STACK RECOMMENDATION

AI Talent Acquisition & Resume Screening System

Automated resume parsing, candidate ranking, and screening pipeline using LLMs and document processing. Scales from hundreds to thousands of applications with cost-efficient inference and vector-based semantic matching.

Stays alive for 365 days after the last visit.

Other

AI Talent Acquisition & Resume Screening System

Automated resume parsing, candidate ranking, and screening pipeline using LLMs and document processing. Scales from hundreds to thousands of applications with cost-efficient inference and vector-based semantic matching.

high confidence

Core Stack ℹ︎

Claude Sonnet 4

Primary

Balanced LLM for resume analysis, candidate ranking, and structured extraction with low hallucination. Cost-effective for high-volume screening at $0.003/1K tokens.

$50-200/month

AWS Textract

Primary

Extracts text, tables, and form fields from PDFs and scanned resumes at scale. Handles diverse resume formats reliably for $1.50 per 1K pages processed.

$30-100/month

Chroma

Primary

Open-source vector database for semantic candidate matching against job descriptions. Enables similarity search and ranking without external dependencies.

$0/month

Complete the Stack ℹ︎

CrewAI

Alternative

Multi-agent orchestration for coordinating resume parsing, skill extraction, and ranking workflows. Manages complex screening logic with role-based agents.

$0/month

Dify

Alternative

Visual workflow builder for non-technical HR teams to configure screening rules, prompts, and ranking criteria without code changes.

$0-50/month

DeepEval

Alternative

Evaluate screening quality and ranking accuracy with built-in metrics. Ensures consistent candidate evaluation across batches.

$0/month

Getting started

  1. 1Set up AWS Textract to extract text from uploaded resumes (PDF/DOCX).
  2. 2Use Claude Sonnet to parse extracted text into structured JSON (skills, experience, education, certifications).
  3. 3Generate embeddings for candidate profiles and job descriptions using Cohere Embed or OpenAI.
  4. 4Store embeddings in Chroma for semantic similarity matching.
  5. 5Use CrewAI agents: one for resume parsing, one for skill matching, one for ranking against job criteria.
  6. 6Implement scoring logic combining semantic match + explicit criteria (years of experience, required skills).
  7. 7Deploy via Dify for HR team to configure screening rules and view ranked candidates.
  8. 8Use DeepEval to test ranking consistency on sample datasets.
Copy link to clipboard

What are you building?

Build your own AI stack →