A frontend contract that became an AI product line
Edvantage (edvantage.me), a government-backed education company in the Middle East
I was contracted to build the frontend for a government-backed education company's website in the Middle East. Working inside the product, the more valuable opportunity was obvious: their mock test product could do more than mark answers. I built an AI tutor that speaks the languages their learners already speak and teaches English in the learner's own language, rather than assuming English to teach English. That turned a defined frontend piece into a long-term engagement — I now work directly with the CEO and the team on where AI belongs across the business, and the capability has given them something concrete to show in investor and grant conversations.
- How the engagement started
- Frontend briefHow the engagement started
- Tutor teaches English in the learner's first language
- MultilingualTutor teaches English in the learner's first language
- Direct with the CEO on the AI roadmap
- OngoingDirect with the CEO on the AI roadmap
The problem
The brief was a frontend. Building it meant living inside the product, and the mock test experience made the ceiling clear: it could tell a learner whether an answer was right, but not why, and not in a language the learner was comfortable being taught in.
Their learners arrive with English as the subject, not the medium. A tutor that explains English in English helps the learners who least need help.
What I built
An AI tutor attached to the mock test product that responds in the learner's own language while teaching English — explaining why an answer was wrong in terms the learner already understands.
The work then widened from one feature to the question the CEO actually had: which parts of this business should use AI, in what order, and what has to be true before each one ships.
What changed
A scoped frontend contract became a continuing engagement working directly with the CEO and the team.
The company has a working AI capability to point at rather than an intention, which has made investor and grant conversations easier to have. I make no claim about the outcome of those conversations — that is theirs to report.
Multilingual LLM tutoring · Assessment product · Frontend · AI roadmap
Related
Written at a public-safe level: client names, internal project names and proprietary business logic are held back by agreement.
Last reviewed