NEOPOLIS AKADEMY
Agent capable of processing and classifying 1,000 CVs
Intermediate practical exercise to process and classify CVs at scale (e.g. 1,000). Shows ingestion pipeline (PDF/text), extraction with OpenAI, n8n automation and structured storage (Notion, Sheets) with human review checkpoints.
View this course on Akademy ↗Enrolment and practical details are available on Neopolis Akademy.

What you will explore
CV ingestion pipeline (PDF, DOC, text) and format normalization.
Metadata extraction and scoring using OpenAI for initial sorting.
Automation of routing, categorization and recording into Notion/Google Sheets.
Manual review steps to verify classifications and refine rules.
STEP BY STEP
Course programme
01Agent capable of processing and classifying 1,000 CVs
Build an automated agent to ingest, read and classify 1,000 CVs. The practical session covers environment setup, orchestration with n8n, PDF processing into a Notion database and progressive construction with security checkpoints.
Goal: design a pipeline that collects PDF CVs and converts them into structured Notion records.
Preparation: configure n8n, set up API access and organise PDF inputs before processing.
Progressive build: text extraction, field normalisation, classification and updating records in Notion.
Security checkpoint: verify access controls, personal data handling and data integrity checks before full automation.
Explore this module on Akademy ↗Programme source: Neopolis Akademy. Original course page