Hades Studio
Menu

AI and LLM App Development

AI features that work on your data and hold up in production

We add LLM-powered features to real products: search and question answering over your documents, assistants that take actions in your systems, and automation of repetitive text-heavy work.

A demo is easy to build and a reliable feature is not. We set up evaluation on your own data early, so that every change to a prompt or a model is measured before it reaches users.

What we deliver

RAG and knowledge search

Question answering over your documents, tickets and databases, with citations back to the source.

AI agents and tool use

Assistants that call your APIs to look up records, draft replies, file tickets and complete multi-step tasks.

Document and data processing

Extraction, classification and summarization pipelines for contracts, invoices, emails and support logs.

Evaluation and cost control

Test sets built from your data, quality tracking, prompt caching and model routing to keep spend predictable.

Technology we use

  • Claude API
  • OpenAI API
  • Python
  • TypeScript
  • LangGraph
  • pgvector
  • PostgreSQL
  • FastAPI
  • Next.js

A good fit if

  • You have a product and want to add an AI feature that users will rely on
  • Your team spends hours on text-heavy work that follows a repeatable pattern
  • You built a prototype and it is not accurate enough to release

How a project runs

  1. Step 1

    Project brief

    You send us a description of the problem, the users and the constraints. We reply in writing with questions within one working day.

  2. Step 2

    Written estimate

    Within a few working days you receive a scope, a timeline and a price broken down by feature.

  3. Step 3

    Weekly increments

    We build in one-week cycles. Each ends with a recorded demo and a version you can open and test yourself.

  4. Step 4

    Launch and handover

    We deploy to your accounts, document the system and either stay on for maintenance or hand over to your team.

Related work

In-house product, in development

TransSub: a cross-platform media player with AI subtitles

An in-house product in development: a Flutter media player for six platforms that generates subtitles with AI and keeps long-running jobs alive across screens and restarts.

  • Flutter
  • Node.js
  • AI subtitles

Frequently asked questions

Do we need to fine-tune a model?

Usually not. Most products get better results from retrieval over their own data combined with a well-designed prompt. We consider fine-tuning only when evaluation shows that retrieval and prompting have reached their limit.

Is our data used to train the model?

We use API providers whose commercial terms state that API data is not used for training by default, and we confirm the current terms with you before the project starts. For stricter requirements we can deploy through your own cloud account.

How do you deal with hallucinations?

We ground answers in retrieved sources, show citations, instruct the model to say when it does not know, and measure accuracy on a test set built from your data. No approach removes errors entirely, so we also design the interface to make answers easy to verify.

How much will the model usage cost us each month?

We estimate it from your expected volume before building, then reduce it with caching, smaller models for simple steps and batching where latency allows. You get a dashboard showing spend per feature.

Can you integrate AI into our existing product?

Yes. Most of our AI work is adding features to an existing web or mobile product through its current backend and authentication.

Keep reading

Service

Custom Web App Development

SaaS products, customer portals, dashboards and internal tools built with React, Next.js and Node.js.

Service

Mobile App Development

Cross-platform and native apps for iOS and Android, including the backend and the store submission.

Have a project in mind?

Tell us what you are building. We reply within one working day with next steps.