Building the products healthcare, education and the AI ecosystem needs.

Six products, all working today. Every number on this page is a real one.

Six products, three places 01 / 6 · Healthcare
HealthcarePilot next 01

Voxtar

Voice as a vital sign. A patient records five short tasks a day in their own language, and Voxtar measures tremor, breathiness and timing against that person’s own baseline — then flags the drift.

Best oral presentation — West African College of Physicians, July 2026, University of Ibadan, before a panel of consultants. The numbers
HealthcareIn design 02

AuraHealth

Voice triage on the queue, with escrowed payment, so an emergency admission is not held up at a cashier’s desk. Designed, not yet built — the page says so.

The numbers
EducationLaunched 03

Coursified

The missing proof layer for YouTube. The best teaching is already free — what is missing is evidence you can do the work at the end of it.

Graded labs, not a quiz: code that passes hidden tests, a model that reconciles, a deck that survives checks. The numbers
EducationLive 04

Hypatia

Learning by domain isomorphism. Bring what you already know, and it maps that structure onto what you want to learn — then teaches you exactly where the mapping breaks.

The numbers
EducationRunning, with users 05

MB3 Prepbot

A daily drill bot for MB BS Part III. Telegram quiz polls each morning, marked automatically, with a leaderboard at close of play — because solo spaced repetition is a solved problem that almost nobody sustains alone.

155 students · 71,377 limbs marked at 75.47% · ₦47,900 from 25 payers. The numbers
AIApache 2.0 06

Vectorless

Document retrieval with no chunking, no embeddings and no vector database. A PDF has no headings — only glyphs with a size and a position — so Vectorless rebuilds the structure from the page geometry and navigates to the exact section, tables included.

On FinanceBench: all evidence found, and the section it points at went from 183 pages to 6. The numbers
How we work

We do not guess what matters in a system. We measure it, then publish what the measurement said — including the parts that went against us.

02The numbers we have FinanceBench, 21 filings, cold cache. From our own evaluation docs.

What we can prove today.

Our headline number today is a benchmark, not an install count.

Vectorless — generative extraction replaced by a batched judge
MeasureBeforeAfter
Evidence-page coverage0.8001.000
Cost per document$0.017–0.095$0.0003–0.0015
Time per document103–840 s12–143 s
Generative calls per document10
Median span holding a gold page183 pages36 pages

When adoption is the number worth showing, it will be the one here.

03What we do Three fields we work in, and the layer all three stand on.

Three fields. One layer underneath.

01

Healthcare. Voxtar leads, with an IRB application at UCH for a post-thyroidectomy voice cohort as the current priority. Cervical screening, oncology pharmacology and HIV-resistance genomics run behind it. Every clinical product plugs into one shared record core instead of rebuilding it.

02

Research. Systematic reviews, mechanistic modelling, and checking that a model found real signal rather than a shortcut in the data. Nothing ships from this pillar — it is the standard the other two are held to, applied whether the output is a manuscript or a product.

03

Education. A cohort of 176 came through three evenings in August. Coursified turns open video into graded courses, Hypatia teaches a new field through one you already know, and MB3 Prepbot drills a medical finals syllabus every morning.

04The layer we own Written for our own products, then released on their own.

Three libraries. Ours, and open.

01

Vectorless — Apache 2.0. Document retrieval with no chunking, no embeddings and no vector database. It rebuilds a document’s structure from the geometry of the page and navigates to the exact section — tables included.

02

llmgate — Apache 2.0. One Go client over Anthropic, OpenAI and Gemini, with routing, fallback and cost tracking on top. LiteLLM, for Go.

03

pdfgrab — MIT. A Go port of pdfplumber: positioned words, font sizes, bounding boxes and table detection. It is what lets Vectorless read a page at all.

Every product above runs on these three. Nothing rebuilds them — which is how six products are the work of one person.

05Training The education arm — and what the last room actually did.

We teach what we build. Then we publish the register.

176 signed up in a fortnight, from one announcement
3 of 3 evenings ran past their scheduled finish
6 in 10 still in the room when the clock said stop
See the programme
06Who is behind it One pair of hands, so far.
Halleluyah Oludele
Halleluyah Oludele · Ibadan, Nigeria

A final-year medical student, building what the ward kept needing.

Every product here started as a job I was already doing — clerking, revising for finals, hunting one paper at one in the morning. I build in the open and publish what the measurement said — including the runs that went against me.

6products built
3libraries released open
1storal presentation, WACP
About the founder

Capital to finish these and take them to market.

Most of this is built, by one person. What is missing is not engineering — it is runway, and the second pair of hands that sells.

Start a conversation
The argument
Every product runs on the same layer, and we own the layer. One compounding asset with several front doors.
Open to
A studio partner, clinical pilots, infrastructure design partners.
Based in
Lagos · Ibadan, Nigeria