Technology
Proven tools, chosen for each problem.
We work across leading model providers and a modern, widely supported engineering stack. The list below reflects what we build with — it does not imply partnership or certification with any vendor.
Stack
Grouped by function
AI & models
- OpenAI
- Anthropic Claude
- Google Gemini
- Open-weight models
- LangChain / LangGraph
- Embeddings
- Speech-to-text & TTS
Retrieval & data
- PostgreSQL
- pgvector
- Supabase
- MongoDB
- Vector databases
- SQL
Engineering
- TypeScript
- React
- Next.js
- Node.js
- Python
- FastAPI
- TensorFlow / PyTorch
Infrastructure
- Vercel
- AWS
- Docker
- Managed cloud services
- CI/CD
Integrations
- REST & GraphQL APIs
- Webhooks
- CRMs
- Help desks
- Email & calendar
- WhatsApp & SMS
- n8n / Make
How we choose
Selection criteria
Fit for the task
Models and tools are chosen per step by quality, latency, and cost — not brand loyalty.
Your data requirements
Hosting, data retention, and residency requirements narrow the options before anything else.
Maintainability
We prefer well-supported, widely understood tools your team or a future team can maintain.
Portability
Abstraction layers where practical, so a model or vendor can be swapped without a rewrite.
Next step
Bring us the process your team is tired of doing manually.
A strategy call is a working conversation about one workflow: what it involves today, what could be automated, and what a first build would look like.
What happens next
- 1Tell us about one workflow
- 2We review it before replying
- 3A working session, then a first-build proposal