AI education: FabAcademic Unfiltered and LeparaLaMapara
Making practical AI knowledge easier to reach
Most people meeting AI for the first time get either hype or a research paper. This is the work of explaining what is actually true about building with it, in public.
- What it is
- Programme of work
- Role
- Co-host, writer and builder of the assistant
- Period
- 2026 to present
- Status
- Active
- Topics
- AI education
- Retrieval augmented generation
The problem
Public conversation about AI splits into hype and inaccessible research, and very little of it explains what building with these systems actually involves, what it costs, and where it fails.
Why it mattered
Practical AI adoption is limited less by access to models than by access to plain explanation and technical mentorship, and that gap is widest for people furthest from the industry.
The context
A public AI leadership and technical education effort, run alongside the day job rather than instead of it, aimed at practical adoption, mentorship and industry-wide literacy.
What I did
I co-host FabAcademic Unfiltered alongside Prof. Mamokgethi Phakeng, delivering strategic AI insight to a global audience. I publish technical leadership writing that distils distributed systems, MLOps, AI governance and enterprise ML architecture into something readable. I also built LeparaLaMapara, my retrieval-grounded AI assistant, which answers only from this site’s own content and cites its sources, so the material can be interrogated rather than only read.
What changed
A large audience gets an accurate account of what building with AI involves, from someone doing it in production rather than describing it from outside.
Who benefited
Practitioners, students and people considering the field, and the technical audience reading the writing each month.
What remained
A body of public technical writing, a recorded conversation series, and a grounded assistant that cites its sources.
Technical context
Retrieval-augmented generation over Supabase pgvector, Gemini embeddings and chat models, source citations, serverless deployment.
Related work
- Shares retrieval augmented generation, ai educationAgent Roadmap Kit: learn AI agents by building one, freeA free, open source companion to the six part agents series: six stops that build one working assistant, runnable at no cost.
- Shares ai educationKasilam: teaching township youth to build with AIKasilam is a free community initiative in South African townships where young people learn to build with AI by shipping real sites for local businesses.
- Shares ai educationStudent success analytics and recommendations at WitsAnalytics and a clustering based recommendation system for student success at Wits, with over R2 million a year in subsidy impact attributed to it.