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 ↗All 12 episodes watched. Concepts pass done — code sections revisited in Phase 2.
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 alongside 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 ↗Runs alongside the end of Phase 2.
No outputs yetHow LLMs work, RAG, fine-tuning, and responsible AI. The best free conceptual deep-dive available.
github.com/microsoft/generative-ai-for-beginners ↗Runs alongside the end of Phase 2.
No outputs yetNVIDIA's free no-code intro. Short but earns an NVIDIA DLI certificate — a great first NVIDIA credential.
learn.nvidia.com ↗Runs alongside the end of Phase 2.
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 ↗Follows Phase 3.
No outputs yetAnthropic's 4D framework for designing, evaluating and iterating on prompts.
anthropic.skilljar.com ↗Follows Phase 3.
No outputs yet9-chapter hands-on notebook course. Chain-of-thought, tool use, RAG — the practical companion to AI Fluency.
github.com/anthropics/prompt-eng-interactive-tutorial ↗Follows Phase 3.
No outputs yet8+ hrs. System prompts, tool use, context windows, RAG, architecture patterns. The most important single course in this plan.
anthropic.skilljar.com ↗Follows Phase 3.
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 ↗Phase 5 begins after Phases 3 & 4 are complete.
No outputs yetLab-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 ↗Phase 5 begins after Phases 3 & 4 are complete.
No outputs yetBuild 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? Google Cloud and AWS follow after Azure.
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 ↗The final deployment phase — a long way to go yet.
No outputs yetAI workloads, ML concepts, and Azure AI services. Natural follow-on from AZ-900. Study free, exam ~£90.
learn.microsoft.com — AI-900 ↗The final deployment phase — a long way to go yet.
No outputs yetDeploy 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