AI features with a human in control.
AI can write, sort and answer for you, but it should not change anything on its own. I build features where the model suggests and a person decides.
What works well
- Drafting and summarisingFirst drafts and summaries that a person edits and approves.
- Classification and triageSorting requests, tickets or content so people see the important ones first.
- Search and answersFinding and explaining things in your own content.
- Internal toolsSmall tools that remove repetitive work from a team.
What to avoid
- Models that change production systems with nobody approving
- A chatbot with no defined scope or knowledge boundary
- Sending sensitive data to a service without a plan for it
- Features that cannot be switched off if they misbehave
The approval-gate pattern
For any AI feature that can change something real, the model proposes, a person approves, and the system verifies the result. The model has no direct write path. This is the pattern ZoneSteward uses, where every change is approved on the server and checked against the live system afterward.
Cost and data handling
AI features have running costs and data implications, and both should be decided up front. I scope usage costs, choose which model fits each task, decide what data leaves your systems, and make sure there is a way to monitor and limit all of it.
A fixed-scope AI audit
If you are not sure where AI would help, I can run a short audit. I look at your processes and site, identify a few candidate features, describe how each would work with a person in control, and estimate effort and risk. You leave with a plan whether or not we build it together.
Related
Which models do you use?
Mostly Claude through its API, and I pick the model per task. The right choice depends on quality needed, speed, cost and data requirements.
Will it make things up?
Models can be wrong. That is why the design puts a person in the approval step for anything consequential, and why outputs are checked against real data where possible.
Can you add AI to my existing WordPress site?
Yes, as a plugin or a connected service, with the same approval pattern and clear limits on what it may do.
What happens to my data?
We decide it together before building: what is sent, to which provider, under what terms, and what is stored. Nothing is sent that you have not agreed to.