Building AI Agents for township businesses with no coding knowledge
AI does not need to be complicated to be powerful. I show how someone with no coding background can build AI agents for a township business, step by step.
Search
Writing, projects, publications, talks, and courses.
26 results for “Building with AI”
Session 6 Launch: From learning AI to building with it
Launching Season 6 with Prof Phakeng, a season focused on real case studies of people building meaningful things with AI. We reconnect with Tshepo from Lebowakgomo, who returns to share the progress of his platform STACU.
The Practical Roadmap to Building With AI Agents
A six part practical roadmap to building with AI agents: tools, retrieval, permissions, reliability and orchestration, from a site built that way.
The Practical Roadmap to Building With AI Agents, Part 1: From Chat to Agent
Most people use AI like a vending machine. I used it like a senior engineer sitting next to me, and built this whole site that way without knowing Next.js. Part one of six: what actually separates a chat window from an agent, and how to start.
The Practical Roadmap to Building With AI Agents, Part 3: Giving an Agent Knowledge
The assistant on this site answers from my actual writing. Part three of six: RAG explained without the jargon, the chunking and search settings I actually use, and three retrieval bugs where the model was fine and the information was not.
The Practical Roadmap to Building With AI Agents, Part 6: From One Agent to an Agentic System
Loops, subagents, orchestration and routing, explained without the hype, plus the economics nobody mentions. Part six of six: what this site actually runs, what it deliberately does not, and why more agents is often the wrong answer.
Session 5.13: From learning to building with AI
Exploring how to move from being a consumer of AI to a creator in an AI-native creative economy. We use South Africa as a case study, but the conversation is relevant to anyone who wants to turn AI knowledge into real opportunities.
The Practical Roadmap to Building With AI Agents, Part 5: Making Agents Reliable Enough to Ship
Generation gives you code. Feedback loops turn it into engineering. Part five of six: the failures on this site where a green build was exactly the wrong goal, and how a bug becomes a permanent check nobody has to remember.
The Practical Roadmap to Building With AI Agents, Part 2: Giving an Agent Hands
An agent that can only edit files makes you the courier between it and everything else. Tools and MCP fix that. Part two of six: what a tool actually is, what I connected, what it fixed in thirty seconds, and the permissions file I am not proud of.
The Practical Roadmap to Building With AI Agents, Part 4: Making Agents Safe Enough to Act
If your agent can use tools, what stops it doing something stupid? Part four of six: why prompt instructions are not a security control, the database rules that make bad outcomes impossible on this site, and the gaps I have not closed.
Building your personal AI Assistant to get jobs, scholarships & study opportunities
If you are still manually searching for jobs in 2026, you are already behind. Today we build a personal AI assistant that finds jobs, tracks scholarships and helps you apply properly.
Kasilam: teaching township youth to build with AI
Kasilam is a free community initiative in South African townships where young people learn to build with AI by shipping real sites for local businesses.
Session 5.7: Your AI Skill Coach - Building Agents to Accelerate Your Career
Building AI agents that act as personal skill coaches, helping you identify gaps, create learning plans, and accelerate your career development.
Session 6.2: Building AI accounting software for informal traders
A conversation with Karabo, an award-winning AI champion, professional accountant, and founder of AEGL, who used AI to build a platform for informal traders, people often overlooked, yet who form the backbone of our economies.
AI agents
Building with AI agents in practice: agentic systems, retrieval, tools, security, reliability and CI, plus public sessions for non coders.
Building a Data Science Capability From the Ground Up: A Real Life Roadmap
Two years ago I inherited a small data science team with no handover, no documentation, and production models nobody could explain. This is the conversation I wish someone had with me before I started: the challenges, the costs, the thinking behind every move, and the one belief that carried it all. Build systems that outlive the people who built them.
Session 6.3: A 20-year-old builds an AI tender system
Co-hosting with Prof Phakeng alongside Sange Zwane, a 20-year-old student entrepreneur who built an AI-powered tender system. A conversation about possibility: what happens when exposure meets talent and young Africans start building with AI.
Agent Roadmap Kit: learn AI agents by building one, free
A free, open source companion to the six part agents series: six stops that build one working assistant, runnable at no cost.
AI education: FabAcademic Unfiltered and LeparaLaMapara
Co hosting FabAcademic Unfiltered with Prof. Mamokgethi Phakeng, public technical writing, and LeparaLaMapara, a grounded assistant that cites its sources.
Session 6.5: You describe it. AI builds it. The Extern AI journey
Joining Prof Phakeng in conversation with Luncedo Simelane, a 21-year-old entrepreneur who built Extern AI, a platform that lets people create software and AI solutions without coding, with a live demonstration of how it works.
The Modern Data Scientist: A Roadmap for the Age of AI Agents
The job hasn't disappeared. The mental model has changed. Here's what the roadmap looks like for data scientists and engineers entering (or navigating) the AI agent era, with a South African lens.
Session 5.4: AI Agents for online shopping
AI is evolving fast. The next phase is AI agents that can work for you. If you want to understand the future of online shopping, business operations and decision-making then this conversation is relevant for you.
We Don't Have Rockets. We Have Towers. A Case for Building Africa's Data Centres
Google, SpaceX and others are putting computers in orbit because power and cooling on Earth have run out of room. Africa has no space programme, but it has tens of thousands of cell towers that already have power, batteries, cooling, a fence and a link to the network. This post asks whether those towers can be a data centre spread across the land, and answers with the same graph and scoring method I used to send generators to towers during load shedding.
Data science platform at a bank: telematics and MLOps
At Absa Group: architected the data engineering capability data science runs on, with Ubunye Engine at 100M+ events a day for 10+ products.
Session 5.12: Your free digital assistant
A live, practical demonstration of using AI as your digital assistant. No theory, no jargon. I show how Claude Cowork can handle your admin for you, freeing up time to focus on high-value work.
How I Learned to Build My Own Python Libraries (From Curiosity to Real Work)
creating from 1st principles