Learning in public · started from zero

Going from total technophobe
to AI agent specialist — in public.

I couldn't code. I didn't know what an API was. Tech jargon made my eyes glaze over. I'm documenting every step of learning to build with AI — the confusion, the breakthroughs, the certifications, and the things I build along the way. If you're starting from nothing, you're in the right place.

See the full plan ↓ Follow the journey
6 phases
14 certifications
6 things built & published
0 prior coding experience
🙋
Who this is

A complete beginner. No CS degree, no coding background, no technical contacts. Just curiosity, stubbornness, and a structured plan.

🗺️
What the plan is

A 6-phase roadmap built with Microsoft, Google, NVIDIA, Anthropic, AWS, and freeCodeCamp — designed specifically to go from zero to AI agent specialist.

📢
Why in public

Learning out loud keeps you accountable and helps others who are on the same road. Every milestone gets a post. Nothing gets hidden.

The learning plan — AI agent specialist

Six phases, built from scratch. Microsoft · Google · NVIDIA · Anthropic · AWS · freeCodeCamp — direct from the big players. Certifications marked throughout.

✦ plan designed by Claude (Anthropic) · I'll build this myself one day
Cert key:
cert — freefree cert included
cert — paid examfree study, paid exam
no certno cert but core content
Phase 1 Microsoft AI Agents for Beginners — concepts only ~2 weeks · no coding required

A brilliant free introduction to the world of AI agents — and the perfect starting point before a single line of code is written. Work through all 12 episodes with Obsidian open, taking notes in your own words. Skip every code section entirely — you don't have Python yet and that's completely fine. The goal here is building your mental map: what agents are, how they think, what problems they solve. You'll return to the code sections after Phase 2 once Python is under your belt, and they'll make complete sense at that point.

AI Agents for Beginners — 12 episodes (concepts pass)Microsoft

Covers agent design patterns, AutoGen, Semantic Kernel, RAG, multi-agent systems, and tool use. Watch everything, note everything, skip all code snippets. A second pass for the code comes later in Phase 4.

learn.microsoft.com/shows/ai-agents-for-beginners ↗
no certconcepts onlyskip code sectionsObsidian notes
Learn in public brief #1 — trigger: all 12 episodes watched "12 things I learned about AI agents from Microsoft" — one concrete insight per lesson in plain English. No code, no jargon. First post on the Coding Newbie site.
Phase 2 Python foundations ~4–5 weeks

Everything in this plan runs on Python. Get solid here before moving on — it pays back every hour you invest. The Anthropic GitHub notebooks layer in naturally from week 3 onwards. Once complete, return to the Microsoft Phase 1 code sections — they'll make perfect sense now.

Scientific Computing with Python (v9)freeCodeCamp

15 real projects built in-browser. The most structured free Python cert available — project-based from day one. Your primary Python course.

freecodecamp.org/learn/python-v9 ↗
cert — freeprimary~40 hrs
Anthropic GitHub courses — API fundamentals notebooksAnthropic

Jupyter notebooks covering the Claude SDK, API keys, streaming, and multimodal prompts. Start these in week 3 alongside Python — they reinforce each other perfectly.

github.com/anthropics/courses ↗
no certstart week 3notebooks
AI Agents for Beginners — code sections revisitMicrosoft

Return to the 12 Microsoft episodes now that Python makes sense. Work through the Semantic Kernel and AutoGen code sections you skipped in Phase 1 — a completely different experience with Python under your belt.

github.com/microsoft/ai-agents-for-beginners ↗
no certcode sections onlyfork & run the repo
Learn in public brief #2 — trigger: fCC Python cert earned Build and publish a small Python tool that does something genuinely useful to you. First cert goes on the portfolio page.
Phase 3 AI fundamentals — Google, Microsoft & NVIDIA ~3–4 weeks · runs alongside end of Phase 2

Build the conceptual foundation across multiple big players before going deep. These courses are deliberately non-technical or lightly technical — they're about understanding the landscape.

Introduction to Generative AI learning pathGoogle Cloud

Three-course path: Intro to Gen AI, Intro to LLMs, and Responsible AI. Free on Google Cloud Skills Boost — earns skill badges. Join the GEAR programme for 35 free monthly credits.

skills.google/paths/118 ↗
cert — freeskill badgesGEAR programme
Generative AI for Beginners (21 lessons)Microsoft

Microsoft's open-source GitHub course covering how LLMs work, RAG, fine-tuning, and responsible AI. Python code examples throughout. The best free conceptual deep-dive available.

github.com/microsoft/generative-ai-for-beginners ↗
no certcore reading21 lessons
Generative AI Explained (no-code intro)NVIDIA DLI

NVIDIA's free, no-code intro to generative AI — how it works, use cases, and limitations. Short (~2 hrs) but earns an NVIDIA DLI certificate. A great first NVIDIA credential.

learn.nvidia.com ↗
cert — freeNVIDIA DLI~2 hrs
Learn in public brief #3 — trigger: Phase 3 complete An illustrated explainer: "How generative AI actually works" — written for a complete beginner. Pulls together what you've learned from Google, Microsoft, and NVIDIA into one coherent post.
Phase 4 Prompt engineering & the Claude API — Anthropic ~3–4 weeks

Now you know how LLMs work, learn to talk to them properly and start building with the Claude API. Anthropic takes centre stage here as a focused thread — not the whole plan.

Claude 101Anthropic Academy

Core features, capabilities, and limits. Do this first — sets the vocabulary for everything in the Academy that follows.

anthropic.skilljar.com ↗
cert — freestart here
AI Fluency: Framework & FoundationsAnthropic Academy

Anthropic's 4D framework for designing, evaluating and iterating on prompts. Foundational for everything that follows in the developer track.

anthropic.skilljar.com ↗
cert — freeprompt engineering
Prompt Engineering Interactive TutorialAnthropic

9-chapter hands-on notebook course direct from Anthropic. Covers basic to advanced: chain-of-thought, tool use, RAG. The practical companion to AI Fluency above.

github.com/anthropics/prompt-eng-interactive-tutorial ↗
no certhands-onnotebooks
Building with the Claude APIAnthropic Academy

8+ hrs. System prompts, tool use, context windows, RAG, architecture patterns. The most important single Anthropic course in this plan — this is how you build real AI products.

anthropic.skilljar.com ↗
cert — freecore8+ hrsPython
Learn in public brief #4 — trigger: Claude API course done Build and publish something that calls Claude — a real tool, not a demo. Could be a writing assistant, a data parser, anything genuinely useful. Your first AI product on the site.
Phase 5 Building AI agents — Microsoft, Google & NVIDIA ~6–8 weeks · the engineering core

This is where you go from "I understand AI" to "I can build agents". Three major players, three complementary perspectives — Microsoft on frameworks, Google on cloud-native agents, NVIDIA on production RAG systems.

Microsoft — agent frameworks & Copilot Studio
AI Agents for Beginners (full GitHub course)Microsoft

12 lessons with code: agent design patterns, tool use, RAG, multi-agent systems, AutoGen, Semantic Kernel, and Azure AI Foundry. Works with free GitHub Models.

microsoft.github.io/ai-agents-for-beginners ↗
no certcorePythonrun the code
Applied Skills: Create agents in Copilot StudioMicrosoft Learn

Microsoft's lab-assessed credential. Scenario-based assessment proving you can build agents in Copilot Studio. Free to earn — highly relevant for enterprise and freelance client work.

learn.microsoft.com/credentials ↗
cert — freelab-assessedenterprise value
Google — cloud-native agent development
Agentic AI on Google Cloud learning pathGoogle Cloud

Multi-agent systems, Agent Development Kit (ADK), MCP integration, and enterprise deployment on Google Cloud. Hands-on labs in real GCP environments via GEAR programme credits.

skills.google/paths/3273 ↗
cert — freeskill badgeADKMCP
NVIDIA — RAG agents & production LLM systems
Building RAG Agents with LLMsNVIDIA DLI

NVIDIA's flagship agent course. Covers dialog management, document reasoning, state management, and deploying agentic systems at scale. Earns a DLI certificate on assessment completion.

courses.nvidia.com ↗
cert — freeNVIDIA DLIRAGproduction
Intro to Model Context Protocol (MCP)Anthropic Academy

Build MCP servers and clients in Python. Tools, resources, and prompts — the three primitives that let any AI agent talk to the outside world.

anthropic.skilljar.com ↗
cert — freeMCPPython SDK
Learn in public brief #5 — trigger: Phase 5 complete Build and publish an MCP server that connects Claude to a real data source or tool. Your most impressive portfolio piece yet.
Phase 6 Cloud deployment — Azure (lead), Google Cloud & AWS ~5–7 weeks · Azure first, others as bolt-ons

Where do your agents live? Lead with Azure — Microsoft's free learning paths are the strongest and AZ-900 is the most recognised entry cloud credential. Google Cloud and AWS bolt on after.

Azure — lead provider
Azure Fundamentals (AZ-900) learning pathMicrosoft Learn

Free study path covering cloud concepts, Azure services, and pricing models. The most widely recognised entry-level cloud cert globally. Study is free; exam is ~£90.

learn.microsoft.com — AZ-900 ↗
cert — paid exam ~£90study freeglobally recognised
Azure AI Fundamentals (AI-900) learning pathMicrosoft Learn

Covers AI workloads, ML concepts, and Azure AI services. Natural follow-on from AZ-900 and directly relevant to deploying agents. Study free, paid exam ~£90.

learn.microsoft.com — AI-900 ↗
cert — paid exam ~£90AI on Azureagent deployment
Claude with Amazon BedrockAnthropic Academy

Deploy Claude via AWS Bedrock — RAG pipelines, tool use, batch processing, and production patterns in the AWS ecosystem. Directly from Anthropic, free cert included.

anthropic.skilljar.com ↗
cert — freeAWSproduction
Google Cloud — bolt-on
Claude with Google Cloud Vertex AIAnthropic Academy

Deploy Claude via Google Vertex AI — the full Claude API on GCP. Pairs with the Agentic AI path from Phase 4 to give you a complete GCP agent picture.

anthropic.skilljar.com ↗
cert — freeGoogle CloudVertex AI
AWS — bolt-on
AWS Cloud Practitioner EssentialsAWS

Amazon's free foundational cloud course. AWS is dominant in enterprise client work — add this after Azure. The Cloud Practitioner cert is the other major entry-level cloud credential alongside AZ-900.

aws.amazon.com/training ↗
cert — paid examstudy freeenterprise / client work
Learn in public brief #6 — trigger: first agent deployed to cloud A live agent, accessible via a URL, running on Azure or AWS Bedrock. The first thing you can actually send to a potential client.