Education: The Long View — Agentic AI for Africa Innovation Challenge

← Agentic AI for Africa Innovation Challenge

Overview

In an IB classroom, a learner leaves primary school with years of documented "Approaches to Learning" — a running record of how they think, where they struggle, what they're drawn to — that a teacher and a family can use to have a real conversation about subject choices and direction. It's a genuinely good idea. It also costs more per learner than most public school systems on the continent spend in a year, so almost no child in a public school gets one.

What public school teachers have instead is a stack of quiz scores, attendance registers, and their own memory of a child across a handful of terms — spread across three or four teachers by the time a learner reaches upper primary, none of whom have time to sit down and connect the dots. A pattern that would be obvious over four years of data is invisible one term at a time. By the time it surfaces — often only at the national leaving exam — it's too late to have acted on it.

Years

How long it currently takes a strength or weakness pattern to surface for a public school learner, if it surfaces at all

~10 min

What your agent should take to update one learner's profile each time a new quiz, project, or teacher note comes in

Teacher decides

Your agent stops here and hands over a sourced profile, not a verdict on the child

One rule that is not negotiable: your agent builds a profile, it never assigns a track or a label. It surfaces a pattern — strong in spatial reasoning, struggling with reading comprehension, three terms running — for a teacher to raise with the learner and their guardian. No career or subject-path suggestion reaches a learner without that conversation happening first, and a learner's profile is never shared, scored, or ranked against classmates. Every strength or weakness claimed must cite the assignment, quiz, or observation it came from; an unsourced label on a child is worse than no label at all.

Choose one theme

Longitudinal strength tracking
Quiz and assignment results across terms and years, turned into a defensible signal — not a one-off score, a pattern held over time.
Holistic skill profiling
Attendance, participation, extracurriculars, and teacher notes folded in alongside academics, for a picture that isn't just test scores.
Early pathway guidance
Turning an aptitude pattern into plain-language subject or career-direction suggestions a teacher can open a conversation with — age-appropriate, never prescriptive.
Plain-language reporting
Turning a multi-year profile into something a non-specialist teacher, or a guardian with no education jargon, can actually read and act on.

Jargon, defined up front

MCP — Model Context Protocol: An open standard for exposing tools to an AI model. You write a small server; any agent can call its tools.
Agentic: Plans a multi-step task, calls tools, checks itself, recovers from failure. Not a chatbot.
Approaches to Learning (ATL): The IB's term for the thinking, research, and self-management skills tracked alongside academic results — the model this track is adapting, not copying.
Learner profile: A running, cited record of one learner's demonstrated strengths and struggles, built up over terms and years, not one test.
Open-weights: A model you can download and run yourself. Qwen, Llama, Gemma, Mistral, Aya.
Human in the loop: The agent pauses, and a named person approves before anything consequential.

Requirements

Projects missing any item in either list are ineligible for prizes.

What to build

Your own MCP server. Three or more different tools, and at least one that does something — updates a learner's profile, flags a pattern for review, drafts a plain-language summary. Read-only is not an agent's hands.
One MCP server you did not write. Community, official, or vendor. One line on why it beats writing it yourself.
Open-source orchestration. LangGraph, CrewAI, Pydantic AI, smolagents, Letta, Goose, n8n or equivalent. No closed no-code builders.
One full task on an open-weights model. Learner records — especially for minors, tracked over years — often cannot leave the country or the programme. Show a frontier model alongside if you like.
A logged tool call for every action, and a gate on every irreversible one — before a pathway suggestion reaches a teacher, before anything is shared with a guardian. Inputs, outputs, timestamps, and a named human approving.
New work, built during the submission period. Existing open-source libraries are fine; an existing project resubmitted is not.

What to submit

A public code repository with an OSI-approved licence and a README that gets a stranger running in one command.
A demo video under 3 minutes, uploaded to YouTube or Vimeo and publicly visible. An unedited agent run with tool calls on screen, not slides.
A text description of what it does, which sub-theme it fits, and which school and workflow it serves. Around 300 words.
ARCHITECTURE.md — one page. Agent shape, MCP servers built versus borrowed, and why.
EVALS.md — eight or more test tasks with pass and fail results, plus one failure you did not fix and what you would try next.

Three tools that work beat nine that half-work. In five days, scope is the skill we are watching for.

Prizes And Awards

Mentorship and build resources
Top 40 — selected from all submissions
Every shortlisted team gets mentor support and the other build resources described in the challenge brief.
All expenses paid
Top 10 — selected from the top 40
The top 10 teams are fully funded to attend the MCP Conference in Nairobi this November.
Amount TBC
1^st
Amount TBC
2^nd
Amount TBC
3^rd
Amount TBC
Best Women-led solution

How selection works: the top 40 submissions are shortlisted from all entries and receive mentorship and build resources; from those, the top 10 are selected and all expenses are paid for them to attend the MCP Conference in Nairobi this November. One prize per team. Judges may decline to award a prize if no submission meets the bar.

Judging criteria

Criterion	What we're checking	Points
Agentic depth and MCP craft	Does the agent genuinely plan, call tools, and recover — or is it one model call in a loop? Are the tool boundaries ones a stranger could reuse?	30
Open-source rigour	Can we clone it and run it? Is the README honest about what is unfinished?	20
Fit to the classroom	Does a named teacher do a real thing faster, across a real span of terms? Did you talk to one?	20
Evaluation and reliability	Is the test set honest rather than curated to pass? Is run-to-run variation measured or hidden?	15
Defensibility	Could this claim about a learner survive a parent asking "why"? Sourced findings, readable log, known cost per run.	10
Demo	Three clear minutes showing the agent working, including where it fails.	5
One hundred points in total.		100

Judging happens in two stages: a written review against the criteria above, shortlisting the top scores; then a 20-minute live technical review — ten minutes walking us through your code, then a new requirement added live while we watch.

Judges: panel to be announced.

Resources

There's no starter pack for this track. By this stage we're assuming you've already got MCP servers you trust and know how to stand up quickly — what data you build on is entirely your call: a synthetic learner cohort you construct yourself, an EMIS-style dataset, or records you have explicit consent to use from a school you work with. This concerns minors, so build your synthetic data to be realistically messy — inconsistent handwriting quality, gaps in attendance, results logged late — rather than clean and easy.

Questions any time in the community channel; every answer is posted publicly so no team gets a private advantage. Shortlisted teams move into a mentor-supported phase with access to better compute and, where relevant, education-data partnerships to take the prototype toward something a real school could pilot.

Rules

Eligibility: Open to developers aged 18 and over, resident anywhere in Africa. Solo entries or teams of up to three. Organisers, judges, and their immediate families may not enter.
Submission period: Opens TBC, closes TBC. Repositories are cloned at the deadline timestamp; commits after it are visible and will disqualify a submission.
Multiple submissions: One project per team. You may not enter the same project under more than one theme.
Ownership: You keep everything you build. You grant us permission to reference and demonstrate your project in community materials. Your repository must carry an OSI-approved licence to be eligible.
Data conduct: Whatever you build on is your choice — open data, your own synthetic set, or real records you have explicit consent to use. Never a real learner's records without consent — this data concerns minors and is treated accordingly — and never anyone's personal details.
AI assistance: Expected and not penalised — use whatever coding tools you normally use. The live review is where we separate directing a coding agent from accepting output you cannot explain.
Language: Submissions in English, wherever you are building from. Your agent may handle documents in any language.

Instant disqualification: A chatbot wrapper with no autonomous tool use · an MCP server that proxies a single endpoint · an agent that assigns a track or label to a learner, or shares a pathway suggestion, without a teacher raising it with the guardian first · a claim about a learner with no source · real learner data used without consent · a repository that does not run · results presented as real runs that never happened · someone else's project, undisclosed.

Schedule

Suggested build milestones — same shape for every track.

Day 1
Kickoff, team finalisation, and deep-dive into sector-specific problem statements and available open datasets.
Days 2–3
Ideation, architecture design, and initial prototyping. Milestone: "Paper Prototype" review with domain mentors.
Days 4–5
Core development, API/MCP integrations, and UX refinement. Milestone: midpoint "Stress Test" with end-user representatives.
Day 6
Final polish, documentation drafting, and open-source repository packaging.
Day 7
Final submission via the challenge portal; selection begins.

Ready to enter education?

Solo entries or teams of up to 3. You can add your repository link later.

Apply for Education

The Long View