Applied AI Africa · A griot's tale of machines
A3-SERE
Systems, Edge & Real-World Engineering
Every great story begins with a constraint — ours has four. Here you learn to build AI that survives a $30 phone, a signal that comes and goes, four languages in one sentence, and a budget that barely whispers. Not a course of slides. A journey through the fire, proven by what you ship.
- Target device
- $30–80 Android phone
- Network
- 2G/3G, often none
- Languages
- Swahili · Luganda · Yoruba · Pidgin
- Budget
- $5–15 / month, all in
Prologue · The laws of the land
The four non-negotiable pillars
Before a single line is written, the griot states the rules. Every decision in this program is judged against these four constraints.
Chapter One · The instrument
Most courses track what you’ve read.
This one works out what you know.
The Compass is a learner model over a 37-skill prerequisite graph. You shouldn’t take that on faith — the whole engine runs in your browser, so use it right now. No account. Answer one question and watch it revise skills it never asked you about.
Three questions. Watch it reason.
This is the real engine on the real item bank — 88 calibrated items across 37 skills. No account, no server, nothing sent anywhere. Answer one question and watch it change its mind about skills it never asked you about.
Chapter Two · The four commitments
Why it can be trusted with that answer
An assessment that grades you and won’t explain itself is asking for trust it hasn’t earned. Four commitments, each one checkable.
It diagnoses causes, not symptoms
Your retrieval work is failing. Most systems tell you to re-read the retrieval chapter. The Compass walks the prerequisite graph, finds that you never demonstrated embeddings, and points there instead — naming every downstream skill that unblocks when you fix it.
It refuses to flatter you
Finishing a page is capped at 58% mastery, and a skill it has never measured is capped lower still. Reading is not knowing. Nothing on the Compass goes up because you scrolled to the bottom of something.
It shows its work
Every number opens into the evidence that produced it — prior, each answer, decay since, the inference used. Download the whole learner model as JSON. Disagree with it if you can find the step where it went wrong.
It obeys its own four pillars
The entire engine is arithmetic that runs in your browser. No model download, no API, no tokens — it works offline on a $40 phone at $0.00 per 1,000 recommendations. A tool that taught these constraints while ignoring them would be refuting itself.
Chapter Three · Choose your path
Where the road forks
Wherever you stand today, start here.
Chapter Four · The library
The tale in three volumes
Everything is organized so the right chapter finds you at the right moment.
Chapter Five · The road
The zero-to-master path
The certificate is earned only when you ship a working, publicly reachable system — a rite of passage, not a completion badge.
Chapter Six · The contrast
What makes this tale different
Most platforms optimize for the notebook. A3-SERE optimizes for the field.
| Typical platform | A3-SERE |
|---|---|
| Clean English datasets | Corrupted, multi-currency, code-switched reality |
| Cloud GPU assumed | CPU-first, $30 phone assumed |
| Accuracy in a notebook | Latency, memory, and cost on a live system |
| Copy-paste that may not run | Every example verified |
| English-only | Multilingual by law |
Epilogue · The proof
Measure what matters
Success is not a notebook accuracy number. It is a live system a real user can reach on WhatsApp or USSD, that runs within the memory budget of a mid-range phone, and remains useful when the network drops. That is how the tale ends — and where yours begins.