What product managers and product owners can try, taken from what the teams in these articles did once AI agents took on more of the building. Jev, an AI model from TypeSafe, checks that each one makes sense without its article. How the check works

How the jobs of product managers, designers, engineers and their managers change when AI agents do more of the building.
Have a person review every customer email an AI agent drafts before it is sent.
Before building an interface for an AI feature, test the prompt it will use on about 20 real user inputs in a chat tool and read every answer.
Before opening a prototyping tool, write down the one question the prototype answers and the result that would change the plan.
Tell each new product manager to read the last two months of the team's public channels, then bring a written view to the team instead of asking for a catch-up.
Before engineers start building a new product, have the product manager decide whether the product should exist at all, and stop the work if the answer is no.
Before pausing work done with AI agents, share its files, write down the next step and list open questions, so a colleague can continue it without the person who started.
Agree with a partner team how success will be measured before agreeing on the architecture of a shared AI model.
Test every candidate AI tool against ten real tasks with answers the team trusts, scoring errors caught, edits needed, hours saved and token cost, before signing a contract.
Replace annual product goals with a short list of assumptions about the next three to six months and a plan rewritten each month.
End each research run, prototype test and metrics review with a decision written in a log kept beside the code.
Test an AI feature with examples taken from real use, have an AI model tuned to that feature grade its answers, and keep running these tests after launch.
Write one discovery brief with five fields: user problem, evidence, assumptions, business outcome and open questions, each question with a named owner.
Have product leaders record, for each product, whether its product managers and designers may deploy their own changes to production, rather than one rule for all teams.
Measure AI adoption by whether finished work reaches users faster, counting the time colleagues spend checking and fixing AI output.
Put a prototype in front of three users, then open the specification with a list of what to keep and what to cut.
Keep reusable agent instructions in one shared repository so that product managers adapt an existing one instead of building a duplicate.
Before an AI agent drafts a report from planning data, have a second AI agent check each item against written rules and tell its owner what to fix.
Keep engineers responsible for deciding what is released to production, even when product managers or designers build features with AI agents.
When a new feature ships, check that the product's AI agent knows when to use it, and treat a gap as a defect.
When testing a product built on AI models, make the product manager decide whether each answer is good enough, judged by its value to customers and its business risk.
Record decisions about what to build and how in a shared specification that becomes the tasks AI agents carry out and update.
Once the company has an internal tool that lets staff build apps from company data, have every new employee build a simple app with it during onboarding.
Expect each product manager to defend every statement in their own documents, using AI as a thought partner rather than the writer.

AI makes a working prototype quick, so the effort moves to choosing a direction and getting from prototype to production with a reliable product.
Show stakeholders proposed versions of a feature as clickable prototypes kept side by side, instead of describing each version in a document.
Release a new feature to half of new users and keep the other half unchanged as a comparison group.
Keep a written list of the features the team has built but not yet checked with real users, and track it alongside the technical debt backlog.
Ship a new AI feature switched off by default as an experiment, and measure who turns it on and keeps it on.
When reviewing a prototype, ask its maker who it is for, what they left out and why a user would come back in week three.
Before an internal tool built with AI ships, name the person who maintains it and set aside 30 per cent of its build cost every year for upkeep.
Before anyone builds a prototype, write down the decision it is meant to help the team make.
Before a product experiment ships to users, write down the number of users it needs and the date the team will read the result.
Show the working prototype to stakeholders before the production build, so that engineering and marketing partners can commit early.
Write down the business rules a piece of software must follow before prototyping it with AI, and give developers those rules along with the prototype.
When building an AI feature, score its outputs against a fixed set of test cases during development, and keep A/B tests on live users for proving that the feature adds value.
Before launch, decide formally whether each prototype the team has built is worth the customer's attention, and set the rest aside.
Before deploying a change built from a customer call, ask whether it is worth doing and whether it is what the customer meant.
Require every proposed AI feature to fill in a one-page brief naming who asked, what it does, and its AI cost per seat.
Revise the written specification and the working prototype against each other, so that a change in one is checked in the other.
End each stage of a project with working software that the team must inspect, not with a plan.
Name who may approve and who may revert a change made with an AI agent, and set technical permissions to match.
Name a sponsor for any exploratory project expected to run longer than about three weeks, and post its progress in a public project and channel.
Have product teams run their own experiments, with experimentation specialists embedded to coach them instead of running tests on request.

The files an AI agent reads before it works, such as AGENTS.md, CLAUDE.md, design-system rules and other written instructions, and the person or team who keeps them current.
When asking a colleague for context, say which decision it is for and what is already known.
Keep a separate glossary for each part of the business in version control, with entries for terms agents must not use, such as internal names kept out of customer screens.
Pair with a colleague on one real problem to see how they judge it, instead of asking them to explain their reasoning in the abstract.
Before a team's bug-testing session, give an AI agent that can operate a web browser a test account and a written board of scenarios, and have it record what it finds on that board.
Make one person responsible for the design system, separate from whoever builds screens, and have that person review every gap or exception the builders record.
Write down the actions the AI agent must never take, such as renaming a customer's existing feature flags.
Define the design system's colours, type, spacing and components in one source before AI agents build screens, and point every agent's instruction file at that source.




Have the AI agent record unclear business rules as open questions in its completion report instead of deciding them, and take that list to the client.
Store the AI skills and instruction file that a product team's managers use in one shared Git repository, and have it check that each manager's copy is the latest version.
Give an AI agent one new kind of task at a time, such as testing its own work before merging, and add the next only once it handles that reliably.
Schedule a regular review in which an AI agent compares recent meeting notes with the instruction files it reads, and a person approves each suggested update.
Set a recurring date to read in full the instruction file that an AI agent loads before every task, and move instructions that serve only one task into separate files.
Before a manager calls a colleague resistant to AI, list which documents, drives and team systems that colleague's AI assistant can actually open.

A written record of what was decided and why, kept with the work so that someone who did not build it can review it.
Keep a visible list on the team's planning board of each customer problem the team chose not to solve and each solution it rejected.
Name one person to keep the maps and documents that explain the product current, and to mark the out-of-date ones, so newcomers know which to trust.
Replace a feature's requirements document and design brief with one table that has a row for each thing the product lets someone do. Link a click-through prototype under each row, and have a designer record a video walkthrough at the top.
Ask the AI assistant to sort requirement notes into confirmed, assumed and unknown items, with a source line for each confirmed item, before it drafts any user story.
Put a short human-written brief at the top of every ticket or specification handed to an agent, and label each section as written by a person or generated by the agent.
Require a person to approve each stage of agent-drafted product work, from the list of customer problems to the final specification, before the next stage starts.
List the tasks AI agents now do, have their former owners test whether they can still do them unaided, and schedule practice without AI for skills that are slipping.
Before engineers estimate a roadmap item, write down the customer behaviour behind it, the belief it rests on and the result that would stop the work.
Link every synthesised finding and ticket to the transcript or feedback it came from, and stop work on any item that cannot be traced to its source.
Write each business rule stakeholders agree, such as what counts as a duplicate, into a decision record with its owner and source, and have AI draft acceptance criteria only from it.
On the roadmap, draw untested bets in a different style from contracts and regulatory deadlines, each with a funding window and a stopping condition instead of a delivery date.
Trace every acceptance criterion in a specification back to the customer problem and priority score it came from.

A person or team answers for what an AI agent does, and decides its instructions, its default settings and when it must hand a decision to a person.
Require an AI agent that classifies documents to give a written reason for each decision that a person can check against the source.
Write down what the first version of an AI feature will not do before deciding what it will do.
Name the person accountable for each AI agent's behaviour, and write down what the agent may do without supervision.
Assign every AI agent a named owner and a defined scope before launch, and update both when people or processes change.
Make one person responsible for how an AI-built product fits together as a whole, and have that person check that each new change fits.
Give every instruction file that an AI agent works from a named owner who keeps it current.



Have an AI agent break an approved project document into user stories with acceptance criteria written for coding agents, and keep them in the team's work-tracking tool.
The first time a person decides an unusual case for an AI agent, have that person write the decision down as a rule the agent follows the next time.
Write down, for each AI agent, what it may recommend, decide and carry out, and when authority returns to a person.

A person other than the one who built a piece of AI-assisted work checks it and approves it before it reaches customers, often called keeping a human in the loop.
Before releasing an AI assistant in a new language, have employees who are native speakers of it test a preview and report errors such as misread names or the wrong level of politeness.
Write down which actions an AI agent may take alone, such as opening a pull request, and which wait for a person, such as merging or deploying to production.







Before a feature is built, write down the customer value it adds, the problem it solves, how it fits the product and how it fits the financial strategy.
Ask whoever hands over work that AI helped produce to confirm they have checked all of it, and treat any error in it as their error.
Route every language-quality report through one shared channel where field staff, product owners and language experts agree priorities and name one owner for each issue.
Publish the list of checks an agent must pass before release at the start of a project, so that builders plan for them from the first day.
Count each quarter how many changes from product and design reached production, instead of counting prototypes or lines of code.
Before a person reviews an AI agent's answers, give that person a verified reference to check them against, and re-check any corrections the reviewer makes.

Before an AI feature is built, the team writes down what a good output looks like, so that the result can be tested against it.
Before a team automates a workflow with AI, list each step as it runs today, mark the steps where work gets stuck or effort is wasted, and fix those steps first.
Have the AI agent ask its questions or show its plan before it builds anything.




Before an AI agent starts building, agree with the people who approve its changes which automatic tests every change must pass.



Record how long a workflow takes and how many people it needs before an AI project starts, so the result can be compared against that baseline.
Have a person read 10 real user sessions with an AI feature and note what went wrong, then 100, before anyone writes a measure of its quality.

A set of correct answers or expected results, prepared by someone other than the builder, that a reviewer uses to check work made with AI.
Write down the problem a feature solves before building it, and judge the result against that statement.


When a survey uses AI-generated respondents, treat its answers as hypotheses only, and put the same question to real people before deciding anything that depends on rare answers or differences between groups.
When an AI agent analyses data, save the steps it followed in a tool the whole team can use, so that anyone can repeat the analysis and check the answer.

Product pages and data designed so that an AI agent, not only a person, can use them.
Record each AI agent's calls to the product and replay sessions call by call, as the team does for human users.
In a product built on an AI model, list the checks added only to work around an older AI model's mistakes, and remove those the current one no longer needs.

A team checks on purpose that its people can still explain work that AI agents produced.

Before an AI agent starts, the work is split into pieces small enough for a person to review one at a time.

Plays from links that are not filed under a topic.
Ask staff which tasks they do with personal AI accounts, and use that list as the case for which AI tools the company approves next.
Ask users what they expect before they first use an AI feature, then compare that with what they report afterwards.
Collect 90 days of requests that customers sent to analysts and use them as the list of questions a chat feature should answer.
Ask the people already using AI tools to show colleagues in similar roles what works for them, before training the rest of the team.
Add the question of whether users understand and trust a feature to every product review, beside the question of whether it works.
Design an AI feature to hand users the finished result first, such as a personalised report, and offer the underlying tool and controls as a second step.
Keep untested product ideas off dated roadmaps until product discovery has shown that they solve the customer's problem.
Hello, I'm Wevy. Ask how product, design and engineering teams work with AI agents. The answer comes only from the 315 links on this site.
Claude picks the links and writes the answer from them only. Answers can be wrong. Do not type personal information: questions go to Anthropic. How Ask works · Privacy
I send the week's answers from real teams in one email, every Monday.
You get one email to confirm, then one every Monday. Your address goes to Resend once you confirm it. Privacy