Belay Studio — Engineering studio
AI systems, infrastructure and web products, from one LLM integration to a team of agents that develops, tests and deploys your platform. We build it, and we stay to run it.
In production BaseadosTVvest101Kandrax RolWorld of KandraxMister DokuOsler·MD
Claude 
Anthropic 
xAI 
Grok 
Gemini 
OpenRouter 
LangGraph 
LangChain 
Langfuse 
Qdrant 
Kubernetes 
Docker 
Terraform 
Ansible 
AWS 
Google Cloud 
Cloudflare 
GitLab 
Grafana 
Python 
FastAPI 
Node.js 
TypeScript 
React 
Flutter 
PostgreSQL 
Redis 
Stripe What we do
Most teams split AI, infrastructure and product work. We do all three, so the model, the servers and the interface fit together.
From one LLM call to a team of agents that runs a platform.
Platforms that stay up, in the cloud or in your own racks.
Full-stack products, from the database to the app store.
AI agent networks
We build networks of AI agents that work as an engineering team. Each agent has one role and its own rules. The agents take tasks from your tracker, write and test the code, release it and report. A person decides at each gate.
How we build agent networksHow one change goes from the tracker to production
Manager agent
It reads the issue tracker and proposes the most important task that an agent can do.
You
One message. For a complex task you also approve the plan before any code exists.
Developer agent
Simple tasks go to a fast agent. Complex tasks go to a planning agent on a frontier model.
Release agent
One agent owns the release candidates. It checks the pipeline and reports each failure.
QA agent
It tests the change as a real user, with screenshots, and sends problems back.
You
Production gets the same build that passed staging. Then QA checks production and you get the release notes.
An agent works A person decides
The roles in a network
In production today: one network develops and releases a software platform, and one network operates a full media channel. See Kandrax Rol
Our work
Products in production and confidential systems on premise. Each one has its own page.
Live streaming & video on demand
Live and on-demand football for the clubs of the Region of Murcia, on a streaming platform that we built from the camera to the app.
Fintech SaaS · AI research agents
A portfolio and dividend tracker with AI research agents. The agents propose, and the investor approves each move.
Autonomous media channel · AI agents
A role-play channel that AI agents operate from end to end: they edit the episodes, cut the shorts, publish them and maintain the web site.
Multiplayer browser RPG
A pixel-art online RPG. Belay Studio directs and designs the game, and AI agents write the code and the architecture with our technical direction.
Browser puzzle game · Case generator
A mystery sudoku in the browser: read the clues, place the suspects and find the culprit. A new case each day.
Health AI assistant
A personal medical assistant that reads your records and answers daily health questions with your own history in mind.
Computer vision · On premise
A camera that follows the play by itself: AI detection and PID control, live and on premise.
iOS & Android app
The BaseadosTV app for iOS and Android: live matches, video on demand and in-app subscriptions.
Document chatbot · On premise
A private chatbot that answers from the documents of a company, on the servers of the company.
Technology
A tool is only a name until someone uses it well. For each one, the technology page says what we do with it, and it links to the project that proves it.
See the full technology pageAbout us
Engineers with complementary skill sets and one shared belief: technology must serve a purpose beyond itself.
Engineer with deep experience in infrastructure, automation and AI tools. He leads engineering teams, designs cloud, hybrid and on-premise systems, and keeps a strong product mindset.
Engineer driven by curiosity across hardware, frontend and Gen AI. He turns technical complexity into clear solutions, and sees technology as a means to build something meaningful.
Questions
Short answers to what clients ask first.
We are an engineering studio. We build AI systems, infrastructure and web and mobile products, and we run them in production. Typical work: an LLM integration, a chatbot on your own documents, a network of AI agents, a Kubernetes platform, or a full product from the database to the app store.
Yes. We connect your product to the model that fits the job, through a direct API (Anthropic, OpenAI, Google, xAI) or through OpenRouter. We add retrieval on your own data, guardrails, cost limits and traces, so you can see what each answer cost and why the model gave it.
It is a team of AI agents with different roles. In a software team, the agents take tasks from your tracker, write and test the code, deploy to staging and report, and a person approves each task and each production deploy. In a media team, the agents edit the recordings, publish them and maintain the web site.
Yes. We have built on-premise AI systems, for example a document chatbot that anonymizes sensitive data and a live camera tracking system. When data cannot leave your building, we use open models and local embeddings on your hardware.
Yes. We work on large, multi-repository codebases every day, with Claude Code and with our own agent networks. We write the requirements first, we approve a plan before the code, and tests decide if a change is ready.
Send us an email and tell us what you want to build or fix. An engineer reads it and answers.
Tell us what you want to build or fix. An engineer answers.
