Skip to main content
LinkGro
LinkGro Technologies

Software, AI, and Products That Ship

We design and build web platforms, mobile apps, and AI systems — and we run our own products, so we ship under the same constraints our clients do.

AI engineering

AI that does work, not demos

Language models become useful when they are wired into real data and real workflows. That wiring is the engineering.

AI agents & assistants

Task-scoped agents with tool access, guardrails, and a human in the loop wherever the cost of being wrong is high.

RAG & knowledge systems

Retrieval over your own documents and data, with citations, so answers can be checked rather than trusted.

Workflow automation

Queues, schedulers, and event pipelines that move work between systems without anyone copying fields by hand.

LLM integration

Model selection, prompt and context design, caching, evaluation, and cost control on the hot paths.

How we work

Pick the shape that fits the problem

Fixed scope when the requirements are known, a dedicated team when they are still moving.

Fixed-scope project

A defined deliverable at a defined price. Best when requirements are settled and the surface is well understood.

  • Milestone billing
  • Written acceptance criteria
  • Fixed timeline

Dedicated team

Engineers embedded with yours, working your board and your standards. Best for ongoing product work.

  • Monthly rolling
  • Your tooling and process
  • Scale up or down

Consulting & audit

A read on architecture, security, or performance, delivered as findings you can act on without us.

  • Fixed engagement
  • Written report
  • No lock-in

Why us

What working with us is actually like

Each of these has cost us work at some point. We would rather lose it up front than halfway through.

You own the code from the first commit

It lives in your repository, or is transferred at handover. No licence retained, no escrow, no dependency on us to keep running.

We will tell you not to build it

If the thing you asked for is not the thing that solves the problem, that goes in the discovery report — even when the smaller scope is worth less to us.

Estimates carry their assumptions

A number without the assumptions behind it is a guess with a decimal point. Ours name what would change them.

No offshore relay

The people in the kickoff are the people writing the code. Nothing is passed to a team you have not met.

Stack

What we build with

Chosen for maintainability over novelty. Almost everything here runs in our own production, not just our clients’.

Frontend

  • Next.js
  • React
  • TypeScript
  • Tailwind CSS
  • Radix UI
  • shadcn/ui
  • Framer Motion
  • TanStack Query
  • Zustand

Backend

  • NestJS
  • Node.js
  • Express
  • REST
  • WebSockets
  • Socket.IO
  • OpenAPI
  • Zod
  • Passport
  • Python
  • FastAPI

Mobile

  • React Native
  • Expo
  • PWA
  • Push notifications
  • Deep linking
  • Offline sync

Data & storage

  • MongoDB
  • PostgreSQL
  • Mongoose
  • Redis
  • BullMQ
  • Vector search
  • S3

AI & ML

  • Claude
  • OpenAI
  • RAG pipelines
  • Embeddings
  • Evaluations
  • Prompt versioning
  • Model routing
  • Guardrails

Cloud & DevOps

  • AWS
  • Docker
  • Terraform
  • GitHub Actions
  • Sentry
  • CI/CD
  • Nginx
  • Cloudflare

Industries

Where we have built

Domain shapes the constraints more than the stack does.

Questions

What clients ask first

If your question is not here, it is probably worth a call rather than a paragraph.

From a single well-defined release through to a multi-quarter platform build. If a project is too small to justify our involvement we will say so rather than pad it.

Still have a question? Talk to the team

Tell us what you are building.

A short call is usually enough to say whether we are the right team, and what it would take.

  • No obligation
  • You own the code
  • Written scope before work