The learning plan — AI agent specialist
Six phases, built from scratch. Each resource has its own portfolio page tracking outputs and progress. Status boxes update as work progresses.
✦ plan designed by Claude (Anthropic) · I'll build this myself one dayA brilliant free introduction to the world of AI agents — the perfect starting point before a single line of code is written. Skip every code section entirely — Python comes in Phase 2.
Covers agent design patterns, AutoGen, Semantic Kernel, RAG, multi-agent systems, and tool use. Watch everything, note everything, skip all code snippets.
learn.microsoft.com/shows/ai-agents-for-beginners ↗Portfolio page will appear once work begins on this module.
No outputs yetEverything in this plan runs on Python. Get solid here before moving on — it pays back every hour you invest. The Anthropic notebooks layer in naturally from week 3.
15 real projects built in-browser. The most structured free Python cert available — project-based from day one. Primary Python course.
freecodecamp.org/learn/python-v9 ↗Labs underway. Project #001 — Agent Eligibility Checker — live and signed off.
View outputs →Jupyter notebooks covering the Claude SDK, API keys, streaming, and multimodal prompts. Start alongside Python in week 3.
github.com/anthropics/courses ↗Begins week 3 of the Python course.
No outputs yetReturn to the 12 Microsoft episodes once Python makes sense. Work through the Semantic Kernel and AutoGen code sections skipped in Phase 1.
github.com/microsoft/ai-agents-for-beginners ↗Follows completion of the Python cert.
No outputs yetBuild the conceptual foundation across multiple big players before going deep. Deliberately non-technical — understanding the landscape before building in it.
Three-course path: Intro to Gen AI, Intro to LLMs, and Responsible AI. Free skill badges via GEAR programme.
skills.google/paths/118 ↗How LLMs work, RAG, fine-tuning, and responsible AI. The best free conceptual deep-dive available.
github.com/microsoft/generative-ai-for-beginners ↗NVIDIA's free no-code intro. Short (~2 hrs) but earns an NVIDIA DLI certificate — a great first NVIDIA credential.
learn.nvidia.com ↗Portfolio pages will appear per provider once work begins.
No outputs yetLearn to talk to LLMs properly and start building with the Claude API. Anthropic takes centre stage here as a focused thread.
Core features, capabilities, and limits. Sets the vocabulary for everything in the Academy that follows.
anthropic.skilljar.com ↗Anthropic's 4D framework for designing, evaluating and iterating on prompts.
anthropic.skilljar.com ↗9-chapter hands-on notebook course. Chain-of-thought, tool use, RAG — the practical companion to AI Fluency.
github.com/anthropics/prompt-eng-interactive-tutorial ↗8+ hrs. System prompts, tool use, context windows, RAG, architecture patterns. The most important single course in this plan.
anthropic.skilljar.com ↗Follows Phase 3. Portfolio page will appear once work begins.
No outputs yetFrom "I understand AI" to "I can build agents". Microsoft on frameworks, Google on cloud-native agents, NVIDIA on production RAG systems.
12 lessons with code: agent design patterns, tool use, RAG, multi-agent systems, AutoGen, Semantic Kernel, and Azure AI Foundry.
microsoft.github.io/ai-agents-for-beginners ↗Lab-assessed credential. Scenario-based assessment proving you can build agents in Copilot Studio. Free to earn.
learn.microsoft.com/credentials ↗Phase 5 begins after Phases 3 & 4 are complete.
No outputs yetMulti-agent systems, Agent Development Kit (ADK), MCP integration, and enterprise deployment on Google Cloud.
skills.google/paths/3273 ↗Phase 5 begins after Phases 3 & 4 are complete.
No outputs yetNVIDIA's flagship agent course. Dialog management, document reasoning, state management, deploying agentic systems at scale.
courses.nvidia.com ↗Build MCP servers and clients in Python. The three primitives that let any AI agent talk to the outside world.
anthropic.skilljar.com ↗Phase 5 begins after Phases 3 & 4 are complete.
No outputs yetWhere do your agents live? Lead with Azure — AZ-900 is the most recognised entry cloud credential globally. Google Cloud and AWS bolt on after.
Cloud concepts, Azure services, and pricing models. Study free, exam ~£90. The most widely recognised entry-level cloud cert globally.
learn.microsoft.com — AZ-900 ↗AI workloads, ML concepts, and Azure AI services. Natural follow-on from AZ-900. Study free, exam ~£90.
learn.microsoft.com — AI-900 ↗Deploy Claude via AWS Bedrock — RAG pipelines, tool use, batch processing, and production patterns in the AWS ecosystem.
anthropic.skilljar.com ↗The final deployment phase — a long way to go yet.
No outputs yetDeploy Claude via Google Vertex AI. Pairs with the Agentic AI path from Phase 5.
anthropic.skilljar.com ↗Follows Azure in Phase 6.
No outputs yetAmazon's free foundational cloud course. The other major entry-level cloud credential alongside AZ-900.
aws.amazon.com/training ↗Follows Azure in Phase 6.
No outputs yet