Skip to content
Platform / AI Tools

AI Tools Handle the Repetitive Work, Brilliantly

AI in the build, with a person on the end of it. AI tools are best for the repetitive work in a business: answering, sorting, summarising and drafting, with a person approving what matters.

Platform Claude & LLMs
Front End Next.js
Best For Chatbots & Automation
01 / Best for

Where AI Tools fits best.

01

Support Chatbots

Answers from your own documents, with a hand-off to a person when unsure.

02

Document Processing

Invoices, forms and contracts read and turned into data.

03

Email & Ticket Triage

Messages sorted, tagged and drafted for a person to send.

04

Staff ask questions and get answers from company documents.

05

Content Drafting

First drafts of descriptions, replies and reports to edit, not publish blind.

06

AI Agents In Workflows

Multi-step tasks run with n8n and approved at the right points.

02 / What we build with

The tools, named.

01

Claude Code

Anthropic’s terminal agent, for repo-wide changes run on a branch and reviewed like any other pull request.

02

Claude Design

Anthropic’s design tool, for putting a first visual on the table in minutes instead of days.

03

OpenAI Codex

A second coding agent, for the tasks that suit a different model better.

04

Gemini CLI and Cursor

Google’s models at the command line, and the editor where the smaller edits happen.

03 / Honestly

Why this, and when not.

Why we use them

Language models handle reading, sorting and drafting that used to need a person for every item, at a fraction of the cost. Grounded in your own data, they answer specific questions, and a person approving key steps keeps quality high.

05 / Questions

AI Tools, answered.

What are AI tools used for in a business?
Answering customer questions, processing documents, triaging email, searching internal knowledge and drafting content, with people approving key steps.
Which AI model do you use?
The one that fits the task: Claude, GPT or Gemini, chosen on accuracy, cost and data rules, and switchable later.
Is our data safe with AI?
We use business API terms where data is not used for training, keep sensitive data out of prompts where possible and log what the system does.
Will AI replace our team?
No. It removes repetitive work so your team handles the cases that need judgement.
How accurate is an AI chatbot?
Grounded in your documents and tested on real questions, it answers most routine questions well, and hands off to a person when unsure.
When should you not use AI?
For decisions that must be right every time, use fixed rules. For simple, fixed tasks, standard automation is cheaper.

Building with AI?

A 30–60 minute call with the engineer who would lead the build. You leave with a scope sketch either way.