AI engineering · mapped from public work
Map what
you’ve built.
AI-Atlas reads your public GitHub projects and maps the AI capabilities your work actually demonstrates — judged on what you built, not on what you imported.
Live Atlas coverage
What AI-Atlas does with your repositories
- 01
Discover
Find the public repositories your GitHub account owns and remove obvious noise such as forks and empty projects.
- 02
Understand
Read the code and project structure to identify what you actually built, not merely which libraries you imported.
- 03
Map
Place demonstrated work across six AI domains, giving deeper projects more influence than repeated shallow ones.
- 04
Explain
Turn the result into a profile that shows the shape of your public AI portfolio and where its evidence came from.
Six domains of evidence
Each domain is scored on its own, from evidence in the code you published.
01. Machine Learning
Model architectures, training loops, optimisation, classical and deep learning method work — the mathematics and mechanics of learning systems.
02. Computer Vision
Image and video understanding: classification, detection, segmentation, generative vision, multimodal perception and vision architectures.
03. Data Science
Data acquisition, cleaning, feature engineering, statistics, analysis, experimentation and visualisation that supports decisions or models.
04. NLP & LLMs
Language modelling, transformer architectures, tokenisation, fine-tuning, retrieval augmented generation, evaluation and inference of LLMs.
05. AI Agents
Tool-using and autonomous systems: planning, orchestration, memory, multi-agent coordination, function calling and agent evaluation.
06. MLOps
Getting models into and keeping them in production: serving, pipelines, experiment tracking, reproducibility, monitoring and infrastructure.
Evidence, not buzzwords.
A score should reflect what the work can prove.
AI-Atlas reads implementation, weighs depth and ownership, then keeps each conclusion connected to the source evidence that supports it.
implementation, not labels
depth over repetition
claims back to files
src/attention.pyCore implementationtrain.pyTraining behaviourexperiments/results.mdEvaluation evidence