[ AI Integration ]

AI Integration.

Wiring models into the workflows that already cost you money, with guardrails and evaluation that keep them honest.

40 articles · See the AI Integration service →

[ AI Integration ]

Your staff are already using AI you didn’t approve

Banning it drives it underground where you can’t see it. A workable policy starts by accepting it is happening.

Aug 2026·1 min read
[ AI Integration ]

When not to use AI at all

A studio that sells AI integration telling you where it doesn’t belong. Five cases where a model is the wrong component.

Aug 2026·2 min read
[ AI Integration ]

Keeping an AI feature working for three years

Nothing about it stays still: the model, your data, your business, and the prompt. Four recurring commitments that keep it honest.

Jul 2026·1 min read
[ AI Integration ]

How to buy AI from a vendor

Every product has AI in it now, which makes the label useless. Six questions that reveal what you are actually purchasing.

Jul 2026·1 min read
[ AI Integration ]

How much of your data does an AI feature actually need?

Less than the vendor implied, and less than your first architecture assumed. Scoping the corpus is the real design work.

Jul 2026·2 min read
[ AI Integration ]

Where AI fits in an e-commerce business

Product data, support volume and returns are the three places it pays. Recommendation engines are further down the list than you’d think.

Jul 2026·1 min read
[ AI Integration ]

How to switch off an AI feature

Not every feature works. Removing one cleanly is a skill, and doing it badly is how a team decides never to try again.

Jul 2026·1 min read
[ AI Integration ]

When your AI feature has to explain itself

A customer disputes a decision, or a regulator asks how it was made. Explainability is an architecture choice made long before the question.

Jul 2026·1 min read
[ AI Integration ]

Where AI fits in a professional services firm

When you sell expertise by the hour, automation threatens the billing model. Where it helps anyway, and where it genuinely doesn’t.

Jun 2026·1 min read
[ AI Integration ]

How to decide which AI feature to build next

Everyone has a list. Ranking it by excitement produces a portfolio of demos. Four axes that produce a portfolio of returns.

Jun 2026·1 min read
[ AI Integration ]

Guardrails for when the model is confidently wrong

Fluent, plausible, and incorrect is the default failure mode. Designing for it is an engineering problem, not a prompting one.

Jun 2026·2 min read
[ AI Integration ]

Adding AI to an existing product without a rebuild

You don’t need a new architecture. You need one seam where a model can be inserted and its output checked.

Jun 2026·1 min read
[ AI Integration ]

Using AI for accessibility work, carefully

It can produce alt text, captions and plain-language versions at a scale nobody was going to fund. It can also produce confident nonsense for the people who most depend on accuracy.

Jun 2026·1 min read
[ AI Integration ]

Why your AI feature got slower and more expensive after launch

Nothing broke. The context grew, the retries stacked up, and the prompt accumulated instructions nobody removed.

Jun 2026·1 min read
[ AI Integration ]

What QA looks like for an AI feature

You can’t assert an exact output, so the usual test suite doesn’t apply. What replaces it, and what stays the same.

Jun 2026·1 min read
[ AI Integration ]

Build your AI feature in-house or hire someone?

The build is the small part. What decides it is who maintains the thing eighteen months from now.

May 2026·1 min read
[ AI Integration ]

Where AI actually belongs in your product

Bolting a chatbot onto a homepage isn’t AI strategy. The wins come from wiring models into the workflows that already cost you money.

May 2026·2 min read
[ AI Integration ]

Building on someone else’s model

Your feature depends on a system you don’t control, that changes without asking. Four ways to hold that dependency safely.

May 2026·1 min read
[ AI Integration ]

Permissions: what your AI feature is allowed to see

Retrieval ignores your access rules unless you build them into it. The question to ask in week one, not week twenty.

May 2026·1 min read
[ AI Integration ]

How to explain an AI project to a board

They are not asking how it works. They are asking what it costs, what it risks, and how you will know if it failed.

May 2026·1 min read
[ AI Integration ]

Extracting data from documents, reliably

Invoices, forms and contracts arriving as PDFs is one of the most common real problems AI solves. The trick is knowing when it’s wrong.

May 2026·1 min read
[ AI Integration ]

Building an AI assistant for your own team first

The lowest-risk deployment in your company answers your own staff. It also builds everything a customer-facing one would need.

Apr 2026·1 min read
[ AI Integration ]

What to do with the data your AI feature generates

Every interaction produces a record of what was asked, what was answered, and what a human did next. Most teams throw it away.

Apr 2026·1 min read
[ AI Integration ]

What happens to your AI feature under load

Model calls are slow, rate-limited and metered. A traffic spike behaves very differently to one hitting ordinary code.

Apr 2026·1 min read
[ AI Integration ]

How to run an AI proof of concept in two weeks

Long enough to learn something real, short enough that cancelling isn’t a defeat. The shape that avoids permanent pilot purgatory.

Apr 2026·1 min read
[ AI Integration ]

Translating your content with AI

Good enough to make translation affordable, not good enough to publish unreviewed. Where the line falls, by content type.

Apr 2026·1 min read
[ AI Integration ]

Handling personal data in an AI feature

Customers type things you never asked for. Four decisions to make before that becomes a problem you can’t unwind.

Mar 2026·1 min read
[ AI Integration ]

Should this run in real time or overnight?

Real-time is the default assumption and often the expensive one. Much AI work is genuinely happier in a batch at 2am.

Mar 2026·1 min read
[ AI Integration ]

Your prompts belong in the repository

A prompt is the specification of how your feature behaves. Keeping it in a dashboard where anyone can edit it untracked is a strange choice.

Mar 2026·1 min read
[ AI Integration ]

The three places AI belongs in a support workflow

Everyone puts the bot at the front door. The higher-return positions are further back, where customers never see it.

Mar 2026·2 min read
[ AI Integration ]

Choosing a model for a feature, not for a benchmark

Public leaderboards measure something other than your workflow. Four questions that pick the right model for the job in front of you.

Feb 2026·1 min read
[ AI Integration ]

Chatbot, copilot, agent: what the words actually mean

Vendors use them interchangeably, which makes buying hard. The distinctions that change what you get and what it costs.

Feb 2026·1 min read
[ AI Integration ]

The AI feature that should have been a form

Conversation is a slow interface for structured input. Sometimes the sophisticated answer is four fields and a button.

Feb 2026·1 min read
[ AI Integration ]

Should this be an agent or a workflow?

Agents are the exciting answer and usually the wrong one. The distinction that decides it is how much of the path you already know.

Feb 2026·1 min read
[ AI Integration ]

Write the evaluation before you build the AI feature

If you can’t describe what a good answer looks like, you can’t ship the feature — you can only demo it.

Jan 2026·2 min read
[ AI Integration ]

Do you actually need to fine-tune a model?

Almost certainly not yet. Three cheaper things solve the problem you think fine-tuning solves, and they’re reversible.

Jan 2026·1 min read
[ AI Integration ]

Meeting transcription: what to do with all that text

Recording every meeting is easy now. Most companies accumulate thousands of transcripts nobody reads and call it knowledge management.

Jan 2026·1 min read
[ AI Integration ]

The AI pilot that never ships

It demos well, everyone is pleased, and eleven months later it is still a pilot. The reasons are organisational, not technical.

Jan 2026·1 min read
[ AI Integration ]

Designing the interface for when the AI fails

Most AI interfaces are designed for the successful case. The failure states are where users decide whether to trust it again.

Jan 2026·1 min read
[ AI Integration ]

The questions to ask before any AI project

Eight questions that take an hour to answer and predict, more reliably than anything else, whether the project will ship.

Jan 2026·1 min read