Your AI Learning Journey
Track your skills, follow structured paths, and get personalized recommendations from your agent.
Profile last updated 2026-03-10
Skill Map
Proficient
- Prompt Engineering Daily practice with Claude
- Agentic Workflows Building the Intelligence Hub
- Static Site Generation Astro + Vercel pipeline
- GitHub API Automation Content publishing pipeline
- Node.js Scripting Agent development
Learning
- MCP (Model Context Protocol) Understand concept, haven't built servers yet
- Claude API Using in agent, learning patterns
- Multi-Agent Systems Phase 2D goal
Gaps
- RAG (Retrieval Augmented Generation) trending Haven't explored yet
- Fine-tuning No experience
- Vector Databases No experience
- LangChain / LlamaIndex Aware but haven't used
- Python ML Stack Focused on Node.js so far
- Model Evaluation & Benchmarks trending Consumer-level understanding
- AI Safety & Alignment trending General awareness only
- Computer Vision Haven't explored
Learning Tracks
All tracks →Model Selection & Evaluation
beginnerUnderstand model tradeoffs, read benchmarks critically, and design multi-model routing strategies.
Prompt Engineering
beginnerFrom basic prompts to advanced system prompt design — learn to communicate effectively with AI models.
Agentic Workflows
intermediateBuild AI systems that act autonomously — from single-step tools to multi-stage pipelines with decision loops.
MCP Integration
intermediateMaster the Model Context Protocol — from understanding the spec to building servers and orchestrating multi-agent systems.
RAG Systems
intermediateBuild Retrieval Augmented Generation pipelines — from understanding embeddings to building and evaluating production RAG systems.
Learning Queue
Full queue →100 new items waiting
- Agentic Workflows 15min intermediate
Read the blog post and explore the tool's approach to session analysis — note how it structures session data, then consider if a similar pattern could improve your Intelligence Hub's observability
Since you're actively building agentic workflows in Claude Code, understanding how to introspect and debug sessions will directly improve your development velocity and help you diagnose issues in the Hub pipeline.
- Python ML Stack 15min intermediate
Read for the sandboxing pattern — consider whether safe Python execution inside your Node.js agent pipelines could unblock Python ML tooling without a full stack switch
Your Python ML Stack gap has been a blocker partly because you're Node.js-first — WASM-sandboxed Python offers a bridge that lets you run Python ML code without leaving your existing infrastructure.
- Model Evaluation & Benchmarks 15min intermediate
Read the failure mode examples — note how evaluation environment design affects model behavior as context for your own agentic workflow reliability
Understanding why evaluation environments fail closes a gap in your model-quality intuition and directly applies to how you design feedback loops in your agentic systems.
- Multi-Agent Systems 15min intermediate
Read the architecture breakdown and map their agent coordination patterns against your Intelligence Hub Phase 2D design
A concrete, shipped multi-agent system at small scale gives you a reference architecture to stress-test your own Phase 2D planning before you build.
- Model Evaluation & Benchmarks 1hr intermediate
Read with focus on RAG, evaluation, and fine-tuning papers — use as a reading list to bookmark 3-5 papers that address your gap areas
Raschka's curation is unusually gap-efficient — one article surfaces the most important developments across RAG, fine-tuning, and evaluation simultaneously, three of your largest blind spots.