Softellar

Generative AI Development

Generative AI Development Services, From MVP to Production

We build generative AI products on .NET and Azure, from the first MVP to the release your users run. The model is one layer, and we build the screens, data, controls and operations around it.

Discuss your AI product

We reply within 24 hours

Companies we have built software for

  • Multi Radiance Medical
  • Loma Lux Laboratories
  • WellVu
  • Commercial Capital Group
  • Grand Auto
  • HostMy
  • Land Base
  • Auto Tuning

What Goes Into an AI MVP

What three of our MVPs shipped first and what waited for later phases. Only one put the model in its first release.

Not sure your MVP needs a model? Four questions on our AI page show whether the first release needs a model, or a rule will do.

Take the fit check

AI Products We Built

An invoice recognition SaaS, a lending platform and an ETL monitoring platform, then the data and automation work around them.

United States

Invoice recognition SaaS on Azure AI

Outcomes

  • Invoice processing up to 80% faster
  • Over 60% fewer manual correction requests
  • Accurate extraction across 50+ invoice templates
  • .NET
  • React
  • Azure Cognitive Services
  • Azure Service Bus

The Model Is One Layer of the Build

Three AI products we built, drawn as the same six layers, from the model down to running it in production.

Clients on the Products We Built

An enterprise app, medical image processing and a daily operations pipeline, each quote linked to its project.

What Generative AI Work Covers

Building a product around a generative model: software that drafts, summarizes, extracts or proposes, and the screens, services, data and controls that decide what happens next. We take it from the first MVP to the release your users run, on .NET and Azure.

The goal

A first release real users work in, and a product that keeps working when the model changes.

Prompt, Ground or Train?

Three ways to put a model to work, from the least effort to the most. We start at the lowest step that does the job.

  1. Step 1, Prompt

    Prompt a hosted model behind a gateway

    For drafting and summaries from data the product already holds.

    Structured outputs make the model follow a JSON Schema

    Where we used it

    Lender summaries from a private OpenAI gateway with schema-bound outputs

  2. Step 2, Ground

    Ground it in your own data

    For answers that must come from your records and documents.

    Grounding responses in your proprietary content

    Where we used it

    Prompts built only from incident fields and slices of the dependency graph

  3. Step 3, Train

    Train it on your own samples

    For fixed document layouts that a general model misreads.

    Five examples of the same form type to get started

    Where we used it

    Models trained on each client’s invoice samples

Inside One Model Call

The path a request takes through the .NET gateways we built for the lending and ETL platforms, from the product to the model and back.

  1. 1Your product

    Called off the main path

    Loan submissions never wait on the model. In the ETL platform, the workflow decides when to call it, which contract version to use and when to skip it.

  2. 2.NET gateway

    Prompts built from an allow-list

    Only listed fields go in: incident fields, slices of the dependency graph and redacted log fragments, or hashed identifiers instead of full documents.

  3. 3.NET gateway

    Policy checked in code

    The gateway rejects payloads that run too long, contain path-like tokens or match secret patterns, before the request leaves the network.

  4. 4Azure OpenAI

    A private model in your tenant

    Azure OpenAI runs in the client’s own tenant behind private endpoints, with network rules that deny traffic to unapproved hosts.

  5. 5.NET gateway

    The answer checked against a schema

    Token limits cap the call. The answer is validated against a versioned JSON schema and parsed back into domain objects before the product sees it.

  6. 6Your product

    A fallback, then a person

    When the model fails, a circuit breaker serves static help and logs an AI unavailable event. Term changes need human approval, and code fixes arrive as normal pull requests.

Want the gateway designed before the first prompt? Software architecture covers where the model sits in your system and what it may touch.

Software architecture

Have a Prototype Already?

Tell us what it does today and who should use it next. We will say what the MVP needs around the model, and what can wait.

We reply within 24 hours and can sign an NDA first.

Have files or a long brief? Use the full form

What Ships Besides the Code

The work a security review, an investor or the on-call engineer asks about, from the lending and ETL builds.

The Team an AI Product Takes

The real teams behind three AI products, one seat per person. The highlighted seats did the model work.

Need the seats, not the whole build? Hire a dedicated team for the product, or add engineers to the team you have.

US Office, European Engineering

Headquartered in Warsaw, Poland, with a client office in New York. A European engineering team that works in your hours, with a US point of contact.

Headquarters

Warsaw, Poland

Engineering and delivery, and the main contact point for clients in Europe.

Client office

New York, United States

Kickoffs, contracts and account management for North American clients.

Shared hours with North America

Clients in Europe share the full working day with the team.

8 AM to 12 PM New York time, 2 PM to 6 PM in Warsaw.

Rankings for the AI Product Team

Independent rankings for the team behind our AI products, each next to the service it relates to.

Related reading

Read Before the First Sprint

Guides from our team on supervised and unsupervised learning, sprint zero and project estimation.

All Insights

Frequently Asked Questions

Questions founders and product teams ask before an AI MVP, and once it has to face real users.

Have a different question? Talk to our team

Building an AI Product?

Tell us the work it takes on, who uses it and the systems it touches.

We reply within 24 hours, and we can sign an NDA before you share details.

Talk to the people who will scope your project