EN TR
Get a quote
View all services
Web software

One app carries the brochure pages and the request queue.

System architecture

The pieces and their boundaries are settled before code.

Enterprise & commercial software

Several institutions, one system, records kept apart.

Mobile app

One codebase, both stores: iOS and Android.

Software consulting

We take a running system over and improve it.

AI consulting

AI only where the problem actually calls for it.

Get a quote
EN TR

AI Consulting · Esenyurt

AI Consulting for Esenyurt businesses

A business growing in Esenyurt does not have to draw a plan first. A wall into the shop next door is opened, a mezzanine goes into a corner, and the layout ends up accumulated rather than designed. Records go the same way, except the bill is higher, because every new field means altering a table. In Secretum, the product we are building right now, we chose not to carry that bill. The character record sits in MongoDB as a document: when a capability arrives the structure gives, and we do not rebuild the schema.

Get a quote Tell us about your project

AI Consulting — Esenyurt

Esenyurt leans on small businesses, multi-branch operations and private education, where the same name can occupy a few buildings. If every point wants its own field added, the list of what they need does not stay fixed. The evidence behind this page is Secretum, and its status is written as it is: our own product, under construction right now. We have nothing to show for a course chain's enrolment system, nor for warehousing or wholesale export, because no work of that kind exists in the portfolio. What carries across is a single decision: holding the record as a document. Under it sit MongoDB, Redis, Laravel and Node.js, with Vue 3 and React Native (Expo) on the client side.

  • Because the record is held as a document, adding a field needs no schema migration; the structure gives as things are added.
  • One point carrying an extra field on the same record does not force a second table or a second installation into existence.
  • We do not recommend it everywhere: where fields are fixed and relations are tight we stay on MySQL, and most of our portfolio sits there.

Why Algoriel

  • The image does the reading

    Vipkurum reads optical form marks with OpenCV from the image of the sheet, not through the optics of a reader appliance.

  • Cropping apart from judgement

    Image processing decides where a question begins and ends; the language model only binds the answer to it. The two jobs never mix.

  • Model output lands in a record

    Vipkurum writes the answer key into the cropped question's own record instead of keeping it as a separate document.

  • A person has the last word

    At Tahlil.com the model drafts the reading and a doctor approves what reaches the patient; an unapproved reading never appears on screen.

What we build

AI Consulting

  • Where no model is needed

    Marks on an answer sheet are read from the form image itself; the threshold that decides whether a bubble counts as filled sits in the code, and no language model runs in that step.

  • Splitting the job in two

    Computer vision sets the question boundaries; a language model then ties each answer in the key to its question. Cropping accuracy never rests on a model's interpretation.

  • Removing the hardware step

    Marking stops depending on a reader device; when the form layout changes, we adjust the reading service in software instead of ordering new hardware or device-specific forms.

  • Turning existing material into a pool

    A booklet page is split into individual questions, the answer key is written onto each question's own record, and the questions already on hand become the pattern for new ones.

  • Tying the output to a person

    At Tahlil.com AI prepares the first reading, a specialist physician writes and approves the interpretation, and responsibility for the text that reaches the patient stays with the physician who signed it.

  • Queueing the generation

    In Secretum text and images come out of two separate generation paths; image generation is not instant, so that work goes onto a queue, and the finished file is stored once instead of being regenerated in the feed. Secretum is the product we are building now.

Work like this

AI Consulting · Case study

Secretum — under construction: the record is a document and the structure gives

Secretum is our own product and still under construction; we do not describe it as finished work. We are building a platform where AI characters live in a feed, and we hold the character record in MongoDB as a document. As a character gains new capabilities the document structure gives, so no addition forces us to rebuild the schema. Text is produced by the Anthropic API and images by Flux API with Replicate; the service layer is Laravel with Node.js, and the clients are Vue 3 and React Native (Expo). The scope is a social feed product, not enrolment.

Read the case study →

Working with Esenyurt teams, remotely

We have no office, so work for this city runs remotely and we do not offer on-site support. What was done, and why it was done that way, stays in writing. The project pages mark which builds came out of a partnership.

  • The first release ships as a working piece; extras follow later.
  • Every client we know of is in Turkey.
  • Decisions stay in writing; progress shows in working screens.

Frequently asked

  • Our points do not need the same things. Does that mean a separate system for each?

    It does not. When the record is held as a document, one point's extra field lives inside that record rather than in a second table or a second installation. That is how we hold the character record in Secretum, because its set of fields keeps opening up over time.

  • Is a document record the right choice everywhere?

    No, and we say so plainly. Where fields are fixed and relations are tight we stay with Laravel and MySQL, which is where most of our portfolio sits. We reach for a document record where the set of fields keeps widening as the work goes on.

  • Can we buy Secretum?

    No, we are building it right now. What this page describes is not a product but a decision about the shape of a record. We do not present it as a finished delivery.

  • Would you not need to visit our institution and look around?

    We keep no office, work fully remotely, and do not offer on-site support. The work is writing down which piece of information belongs in which record. As the number of points grows, that written separation earns more than another screen does.

AI Consulting in other cities

The other cities where we publish this service are below, grouped by province.

Other services for this location

Let us look at which step needs a model and which one needs computer vision.

Get a quote or open the service