ServicesWritingAboutContactGet in touch →
ENFR

AI agents for data work

Test an AI agent on a real task, and measure what it saves.

Get in touch

The problem

Your team spends hours on a repetitive task: documenting models, writing tests, checking imports. You want to know whether an agent can take it on without lowering the quality.

What I do

  1. Together we pick a specific task and a baseline to compare against: time spent, error rate.
  2. I set up a pilot with limited permissions, on synthetic or explicitly authorised data.
  3. I put review, logging, rollback and human approval in place before anything is extended.

What you get

  • A pilot running on the chosen task.
  • A measurement of the gain against the baseline.
  • A recommendation: extend, adjust or stop.

How I know

I use coding agents every day in my own development work, and I build my tools with them.

How it starts

  1. You write to me.

    The context, what you need to decide, what’s in the way.

  2. We talk it through.

    I’ll tell you whether I can help, and with what.

  3. I send you a written proposal.

    Deliverables, timeline, price. Nothing starts until you agree.

Have a task in mind? Describe it to me.

Get in touch →