Engineering/Applied AI

AI in the product without the hype: where an assistant really helps the user

Putting a chat on every screen is not an AI strategy. A way to decide where AI creates real value in the product, how to design the experience and which privacy safeguards belong in from day one.

Murilo Anzini 4 min read

Lately the question has shifted from "should we use AI?" to "where do we put the chat?". And that's where a lot of products go wrong: they treat AI as a feature to show off, when it should be a means for the user to get something done that used to be hard.

Start with the job, not the model

The useful question is the same as for any feature: what job is the user trying to get done, and where do they get stuck? AI comes in when it removes a blocker that other solutions don't handle well.

The patterns where I see AI creating real value:

PatternThe user gets stuck because...AI helps to...
Blank pageThey don't know where to startGenerate a first draft to edit
Specialist knowledgeThey don't master the methodGuide step by step, explaining along the way
VolumeThere's too much information to readSummarize and highlight what matters
Translating intentThey know what they want, not how to ask the systemTurn natural language into action

A concrete example: a store owner who "never managed to put together a cash flow" doesn't need a generic chat. They need an assistant that talks about the context of their business and, at the end, leaves the categories and projections created in the system, not just explained in the conversation. The difference between "the AI explained it to me" and "the AI helped me do it" is the difference between curiosity and value.

A good sign that AI is in the right place: the result of the interaction becomes data in the product (a saved draft, a goal created, a report generated), instead of dying in the chat history.

Designing the experience

A few experience decisions that make a difference:

Draft, not decision

The AI proposes, the person decides. Everything the AI generates shows up as an editable draft, with the final action always in the user's hands. That lowers the cost of mistakes (which will happen) and keeps responsibility where it belongs.

Context is everything

A generic model with the right context beats a better model without it. The value of an in-product assistant is precisely knowing who the user is, what the business is, what has already been done. But context is also a responsibility: only what's needed goes in.

Your own method

What sets your product's assistant apart from any chat is the method it follows: the questions it asks, the order, the criteria. That method is product knowledge and should be written, tested and versioned like any other part of the system.

Fail gracefully

The model will get things wrong, be slow or go down. The experience has to plan for that: honest loading states, clear messages and a manual path that's always available.

Privacy by design

AI in the product means sending user data to a model. That calls for explicit decisions, ideally public ones:

  • What the assistant receives and what it never receives. Sensitive data that isn't needed for the task stays out;
  • Vendors that don't train on the data and don't keep it longer than necessary;
  • Defined retention: how long the history and logs are kept;
  • Transparency in the privacy policy, in plain language;
  • Tests with fictional data during development, never with real conversations without authorization.
If you sell to companies, the question "where does the data my team types into the AI go?" will come up in the negotiation. Having the answer written down beforehand is a competitive advantage.

Engineering: keep it simple

On the technical side, the temptation is to build a complex architecture right away. What's usually enough at first:

  • A service layer that isolates the model vendor (switching vendors can't require touching the whole product);
  • Prompts and methods versioned in the repository, with regression tests using fictional conversations;
  • Tools (tool use) so the model acts on the system in a controlled way: create the draft, fetch the context, never free access;
  • Usage and cost logging per account, to understand the value and the margin.

How to tell it worked

The metric isn't "messages sent to the assistant". It's the same as always: did the user get the job done? A few questions for the dashboard:

  • How many interactions end in a completed action in the product?
  • Do people who use the assistant activate faster or retain better?
  • How much of what the AI generates is accepted, edited or discarded?

Summary

AI in the product is a product decision before it's a technical one. Find the user's real blocker, design the AI as the one who proposes (not the one who decides), turn the result into something concrete in the system, treat privacy as part of the feature and measure by the job done. Without the hype, AI becomes what it should be: a way for your product to be more useful.

#ai#llm#product#privacy#ux

Murilo Anzini

Hands-on writing on engineering, product, data and marketing for people who want to understand, and build, the whole journey of a product.

About me

Free ebook

Criando infoprodutos de valor

The method I use to bring product, marketing and sales together when creating digital products: the way startups test hypotheses, understand needs and build what the market wants to buy.

  • Understand the customer and set the initial hypotheses
  • Build and test a lean MVP
  • Measure progress and validate with data
  • Know when and how to pivot
Download for freePDF · 23 pages · in Portuguese · no sign-up