deerwork-ai
Featured
deer-workflow
An open-source Dynamic Workflow runtime that combines deterministic TypeScript orchestration with replaceable Agent runtimes.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It offers a comprehensive, phased learning path covering both foundational theory and advanced topics (e.g., Flash Attention, agent systems, model evaluation) with clear daily guidance and built-in revision.
Who it is for
- Self-taught developers new to AI/ML
- College students seeking a structured AI study plan
- Software engineers transitioning into AI engineering
- Tech leads looking for a team upskilling resource
Use cases
- Personal structured learning over 100 days
- Internal training or bootcamp for developer teams
- Brush-up on modern AI topics like RAG and inference optimization
- Interview preparation for AI/ML engineering roles
Strengths
- Covers a wide range from regression to computer‑use agents
- Each day links to a dedicated, self‑contained blog post
- Includes revision days to reinforce learning
- Public sharing commitment (#100DaysOfAI) boosts consistency
Considerations
- Relies entirely on external blog posts; no code or interactive exercises provided
- All content comes from a single source (Outcome School), creating potential bias
- No community discussions or Q&A built into the repository
README quick start
100 Days of AI
Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.
Prepared and maintained by the Founder of Outcome School: Amit Shekhar
How to take the challenge
The rules are simple:
- Learn one concept every day. Each day maps to one blog - read it, understand it, and take your time with the examples.
- Spend 30 to 60 minutes a day. That is all it takes.
- Write a short note every day in your own words. Teaching yourself on paper is the fastest way to make a concept stick.
- Share your progress publicly on X or LinkedIn with the hashtag #100DaysOfAI. Public commitment keeps you consistent.
- If you miss a day, do not restart. Continue from where you left off. Consistency beats perfection.
- Revision days have no new reading. Use them to revise, rewrite your notes, and let the concepts settle.
Before Day 1
Before starting the challenge, watch this video to get the big picture of AI Engineering - it will help you see where every day of this challenge fits.
Let's get started: AI Engineering Explained: LLM, RAG, MCP, Agent, Fine-Tuning, Quantization
Phase 1: Machine Learning Foundations (Days 1-10)
Everything in AI stands on machine learning. In this phase, we will learn what machine learning is and build the vocabulary we will use for the next 90 days.
| Day | Topic | Resource |
|---|---|---|
| 1 | Machine Learning | What is Machine Learning? |
| 2 | Supervised vs Unsupervised Learning | Supervised vs Unsupervised Learning |
| 3 | Regression | Linear Regression vs Logistic Regression |
| 4 | Feature Engineering | Feature Engineering for Machine Learning |
| 5 | Loss Functions | What Are L1 and L2 Loss Functions? |
| 6 | Regularization | Regularization In Machine Learning |
| 7 | Bias in Neural Networks | [What is Bias In Artificial Neural Network?](https://outcomeschool.com/blog/ |
Description
Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.
Related repositories
Similar projects matched by category, topics, and programming language.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
S40911120
Featured
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.