Understand how software really works.

1. 01

   AI Engineering

   8 of 9 published

   Build real applications with LLMs, agents and tools.

   • LLM Application Evaluation
   • Loop Engineering
   • AI Models
2. 02

   System Design

   3 of 3 published

   Design systems that are fast, scalable and reliable.

   • Introduction
3. 03

   More on the way

   Languages, frameworks and more, taught the same way.

1. 01 · Watch

   

   A short animated explainer, narrated, with Vora as your guide: diagrams move, data flows, code runs.

2. 02 · Read

   A polite prompt is not a guardrail

   This is the third lesson in Loop Engineering, after the agent loop and tool calling, but it stands on its own. You need one idea: an agent is a model that can call tools, like looking up an order or sending a refund, in a loop until the job is done.

   A written deep dive at your own pace, with code that has been run before it was published.

3. 03 · Practice

   Bob's prompt says never refund over £30, yet a test message gets a £180 refund. What fixes it?

   • AWrite the prompt rule in capitals and repeat it twice
   • BA code check on the amount before issue_refund runs
   • CA bigger model that follows instructions more closely

   A short quiz that explains every answer, right or wrong.

See the whole lesson: AI Agent Guardrails: Limits That Keep an Agent Safe

• 7:40

  AI Engineering· Beginner · 6 min read

  AI Agent Guardrails: Limits That Keep an Agent Safe

  Asking the model nicely in the prompt is not a guardrail. A guardrail is a check your code runs around the model, and it can say no whatever the message says.

  Oct 25, 2026

• 7:29

  AI Engineering· Beginner · 6 min read

  The Agent Loop: How an LLM Plans, Acts and Knows When to Stop

  An agent is a model inside a loop: it reads the goal and the history, picks the next tool, sees the result, and repeats. Loop engineering is designing that loop on purpose, including how it stops.

  Oct 24, 2026

• 7:04

  AI Engineering· Beginner · 6 min read

  Tool Calling: How an Agent Picks and Uses a Tool

  The model never runs a tool. It writes a call, a tool name plus arguments, and your code checks it, runs it and hands back the result. Here is one round trip, start to finish, at a small cinema.

  Oct 24, 2026

• 8:02

  AI Engineering· Intermediate · 7 min read

  Jev Explained: A Decision Model vs an LLM

  An LLM writes an answer word by word. A decision model like Jev picks one answer from your list and says how sure it is, so software can act on every event. Here's how, and what's still unproven.

  Oct 24, 2026

• 7:12

  AI Engineering· Beginner · 6 min read

  LLM Eval Methods: Code Checks, Human Review and LLM-as-Judge

  An eval method is the procedure that turns one output into a verdict. See code, a judge model and a person each judge the same five customer emails, and learn when each one is the right tool.

  Oct 23, 2026

• 6:55

  System Design· Intermediate · 5 min read

  Back-of-the-Envelope Estimation for System Design

  A few lines of rough maths tell you how big a problem is before you design for it. Follow an exam results website from 21 requests a second to 1,500 at 8:00 am, and see what each number decides.

  Oct 23, 2026