Knowledge Base
Search
-
Day 2 - What Is an AI Agent? Definitions, Workflows vs Agents Explained
Three definitions of an AI agent, and the workflows-vs-agents split from Anthropic, with real-world examples of each.
5 -
Day 4 - Start the Digital Twin: Read a PDF and Master System Prompts
Starts the Digital Twin lab: prepare linkedin.pdf and summary.txt in lowercase, read the PDF with pypdf, and refresh system prompts, conversation hist...
5 -
Day 4 - How Tool Calling Works: The Truth Behind AI Agent Autonomy
Explains what tools really are: function calling is your code acting on tokens the LLM generates, shown with an airline price prompt, a move-north pro...
5 -
Day 4 - The Agent Landscape: Frameworks, Runtimes, Tools and Builders
Maps the agent landscape into builders, products, runtimes and frameworks, explains what agent frameworks abstract (orchestration, tool calling and MC...
5 -
Day 3 - LLM as a Judge: Rank Multiple LLMs with an Orchestration Flow
Rank nine LLM answers with a judge model: anonymise the competitors, prompt for a JSON ranking, use Grok as the non-contestant judge, and map results...
5 -
Day 3 - Install Ollama and Run Local LLMs: Llama, GPT-OSS and Gemma
Installing Ollama, picking models by size (the Llama 3.2 vs 3.3 trap, the '-cloud' naming gotcha), the ollama ls/serve/pull/rm commands, and calling l...
5 -
Day 3 - Call 8 LLMs with the OpenAI-Compatible API: GPT, Claude, Gemini
How the OpenAI-compatible endpoint lets one client shape call OpenAI, Anthropic, Google, DeepSeek, Groq, OpenRouter and even local Ollama models — and...
5 -
Day 3 - Set Up Multiple LLM API Keys and Generate a Question to Ask
Setting up optional extra API keys (OpenRouter is the one to pick), verifying each key's shape, and the trick of having an LLM generate its own challe...
5 -
Day 3 - LLM Providers Compared: OpenAI, Claude, Gemini, Ollama, Groq
A quick map of the LLM landscape before the labs start: OpenAI, Anthropic and Google's small/medium/large model families, DeepSeek, the Groq/Grok mix-...
5 -
Day 2 - Agentic AI Risks, Guardrails, Evals and Traps to Avoid
The two traps that catch almost everyone building their first AI agent — leading with the solution before the problem, and anthropomorphizing an agent...
5 -
Day 2 - Agentic AI Design Patterns: Chaining, Routing, Orchestrator
Anthropic’s five workflow design patterns — prompt chaining, routing, parallelization, orchestrator-worker, evaluator-optimizer — and the open-ended a...
5 -
Registering a Microsoft Entra App for n8n to Reach Microsoft 365 and Teams
Register an app in Microsoft Entra ID, grant the right Microsoft Graph permissions, and connect it to n8n - both delegated OAuth2 and app-only service...
10 -
Registering for Google Gemini and Creating Your API Key
Create a Gemini authorization key in Google AI Studio, store it as GEMINI_API_KEY, and call Gemini three ways - raw REST with x-goog-api-key, the goog...
10 -
Registering for OpenRouter and Creating Your API Key
Sign up for OpenRouter, add credits, create a spend-capped API key, and call hundreds of models from Anthropic, OpenAI, Google and others through one...
10 -
Registering for ChatGPT and Creating Your API Key
Set up an OpenAI platform account, add credits, create an sk-proj- API key, wire it into a .env file, and run the course notebook 1_foundations/1_lab1...
10 -
Registering for Claude and Creating Your API Key
Create an Anthropic account, tour the Claude developer console at platform.claude.com, mint and safely store your first API key, and verify it with a...
10 -
Day 1 - Your First OpenAI API Call and Chaining LLM Calls in Python
Week 1, Day 1. The messages format, your first chat completion call, reading the response - then chaining two calls so the model writes the next promp...
10 -
Day 1 - Set Up Your OpenAI API Key and .env File for the First Lab
Week 1, Day 1. Step 4 of setup: why the API is not ChatGPT, creating the account and organization, the $5 minimum top-up, an organization-level API ke...
10 -
Day 1 - Windows Setup: Install Cursor, Git, Clone the Repo and Run UV
Week 1, Day 1. The Windows path through setup: four PC-specific gotchas that cause most failures (script permissions, antivirus, the 260-character pat...
10 -
Day 1 - Environment Setup Overview: UV, API Keys, Costs and GitHub Repo
Week 1, Day 1. What you set up before the real work starts: uv for the Python environment, a .env file of API keys, and the GitHub repo that holds the...
10