AI in production, not in a demo

AI application development,built into real products.

I build products where AI does real work for real users — voice, language models and structured scoring — engineered with the fallbacks, limits and review a production system needs.

  • Voice & language models
  • Fallbacks and limits
  • Web and mobile
Smart FRCS AI on iOS: a colorectal surgery station brief with Begin and Keyword Practice options
Smart FRCS AI on iOS: a live viva with Mira asking a question while the answer is transcribed, in continuous mode
Smart FRCS AI on iOS: Alden asks a follow-up question about managing the hernia, built on what the candidate has already said

What I build

What AI can do inside your product.

Smart FRCS AI is the reference: an AI examiner that listens to a spoken answer, asks a follow-up based on it and scores it against a published scale.

01

Voice interfaces

Live speech-to-text with push-to-talk and continuous modes, and spoken responses.

02

Language-model features

Questioning, assessment and generation, with provider failover so one outage does not stop the product.

03

Structured, explainable output

Scores against defined scales, reports and transcripts users can review — not opaque answers.

Published work

Products that are live and in use.

Every link goes to the real product or its store listing.

What's included

What production AI needs around it.

The model is the smallest part. A typical AI scope also covers:

  • Provider strategyWhich models and services, with failover between providers.
  • Usage and cost controlsMetering, limits and billing so usage stays predictable.
  • Safety and interruptionRules for when the system should stop, decline or hand over.
  • Review and reportingTranscripts and reports that make the output checkable.
  • The product around itWeb and mobile apps, accounts, payments and administration.

How it works

A clear process, with you at every step.

No fixed promises before the facts are known. Timelines and cost come from the agreed scope, and you see progress at every milestone.

  1. Discovery call

    We talk through the idea, the users and the constraints. You get an honest view of whether — and how — to build it.

  2. Scope & estimate

    A written scope with milestones and an estimate based on it, so you know exactly what is being built.

  3. Design

    Flows and screens you can click through and approve before any development starts.

  4. Build in milestones

    Development in agreed stages, with working builds you can review as the work progresses.

  5. Release

    Final testing, deployment and — for apps — store listings and submission.

  6. Support & growth

    Updates, fixes and the next version, under the support arrangement we agreed.

Founder-led

You won't be passed to an account manager. You talk to the engineer who designs your product and answers for it.

Khalid AboubakrFounder & principal engineer

  • I lead the architecture, the technical decisions and the quality of what ships.
  • When a project needs more hands, I bring in senior specialists I trust — and I stay accountable for the result.
  • Healthcare and medical education are my flagship work; government, education and commercial products sit alongside them.

Questions

Before you get in touch.

Which AI providers do you work with?

Smart FRCS AI uses Anthropic models with automatic OpenAI failover, and ElevenLabs for speech. The right providers for your product depend on the task, the data and the budget.

Can AI be added to an existing product?

Often, yes. I start by finding the one task where AI saves real effort, then build it with the limits and review it needs.

Do you train a custom model, or build on existing ones?

Most products are best built on existing models, with your own content supplied at the moment of each request and the output checked against your rules. Fine-tuning or training is worth considering only when testing on real examples shows that approach falls short.

What happens to our data when it is sent to an AI provider?

That is decided in the scope: what is sent, what is removed or anonymised first, which provider terms and retention settings apply, and what must never leave your systems. If your data is regulated, tell me the requirements at the start.

Can the AI features work in Arabic?

Current models handle Arabic, but quality varies with the task and the dialect, especially in speech. I test with real Arabic input from your users before committing to an approach, rather than assuming English results carry over.

How much will it cost?

It depends on what the product has to do: features, user types, integrations and the systems behind it. After a discovery call you get a written scope and an estimate based on it — not a number guessed in advance.

Who will I actually be working with?

With me, directly. I lead the project from the first call; when specialists are needed, I bring them in and stay responsible for their work.

Start your project

Tell me about the product you want to build.

Your message comes straight to me. I'll reply personally with questions that sharpen the plan, an honest read on scope, or a clear no if I'm not the right fit.

Khalid AboubakrFounder & principal engineer

What would you like to build?
Where are you now?

Your details are used only to reply to this enquiry.