AI
AI Agents
We build AI agents that carry out work inside the limits you set.
The situation
Repetitive knowledge work eats human time. Reading the same email, filling the same form and opening the same record repeat every day.
Our approach
We run the agent on your rules. You decide which tasks it completes alone and which ones need your approval.
What we do
- Task definition and boundary setting
- Connecting to your existing systems
- Human approval steps
- A record of every action taken
- Cost and usage monitoring
Technologies we use
- Backend
- Node.js · Express · PHP · Payload CMSNode.js speaks the same language as the frontend in most projects; we use PHP where only shared hosting is available.
- Database
- PostgreSQL · Supabase · SQLite · MySQL · Prisma · DrizzlePostgreSQL for multi-user, relational work; SQLite for small, single-site setups.
- Servers & hosting
- Linux (Ubuntu) · Nginx · PM2 / systemd · Let's EncryptA dedicated Linux server is enough for most projects and keeps costs predictable; server access is handed to you.
- AI
- Claude API · Gemini APIWe pick the model by the sensitivity and cost of the task, and state in writing where your data goes.
How we work
- 01
Discover
A map of the current state and a prioritised list of needs.
- 02
Define
A scope document, success criteria and a schedule.
- 03
Design
A clickable interface prototype and the design system.
- 04
Develop
Working builds delivered at regular intervals.
- 05
Test
Test scenarios, a closed bug list and an acceptance test signed off by you.
- 06
Deploy
The live system, technical documentation and a hand-over session.
- 07
Grow
A usage report and a prioritised improvement plan.
Common questions
Can an incorrect action by the agent be undone?
It can. Every action is recorded and a rollback step is defined. For critical actions we make approval mandatory.
Other services in this area
Let's talk about this
A short call to get clear on what you need. We will tell you plainly which approach fits.
Start your project