Working Surfaceplaybook

Plays for product managers working with AI agents

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

103 plays from 98 links

Changing roles

How the jobs of product managers, designers, engineers and their managers change when AI agents do more of the building.

23 plays · Topic pageClearest first, as Jev scored them
CHECKED BY JEV · WORKING SURFACE ·22 NOV2026
Product

Have a person review every customer email an AI agent drafts before it is sent.

LukeW · Crazy Agent Scale: Companies All-in on AI · 21 Nov 2026
Product

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.

AI PM Playbook (Uditi Sharma on Substack) · Where does a PM's prototype stop? · 15 Oct 2026
Product

Before opening a prototyping tool, write down the one question the prototype answers and the result that would change the plan.

AI PM Playbook (Uditi Sharma on Substack) · Where does a PM's prototype stop? · 15 Oct 2026
Product

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.

Lenny's Newsletter · Inside PM at Anthropic: Who Makes It, and Who Doesn’t · 1 Nov 2026
Product

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.

Behind the Craft · Gemini 4 Changed How Google Builds Products | Jaclyn Konzelmann · 2 Nov 2026
Product

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.

Nate's Newsletter · Executive Briefing: You Bought Better Tools and Your Finished Work Still Waits · 29 Sep 2026
Product

Agree with a partner team how success will be measured before agreeing on the architecture of a shared AI model.

Spotify Engineering · AI Product Management at Spotify: A View From Three Angles · 10 Nov 2026
Product

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.

UX Collective · The people using AI should set its strategy · 31 Oct 2026
Product

Replace annual product goals with a short list of assumptions about the next three to six months and a plan rewritten each month.

Lenny's Newsletter · Inside PM at Anthropic: Who Makes It, and Who Doesn’t · 1 Nov 2026
Product

End each research run, prototype test and metrics review with a decision written in a log kept beside the code.

Product Map · AI product management in the agentic era: PMs build now · 20 Nov 2026
Product

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.

Spotify Engineering · AI Product Management at Spotify: A View From Three Angles · 10 Nov 2026
Product

Write one discovery brief with five fields: user problem, evidence, assumptions, business outcome and open questions, each question with a named owner.

Product Management Society · How AI changed the product manager and product designer dynamic in 2026 · 23 Oct 2026
Product

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.

Lenny's Newsletter · All of the Lenny & Friends Summit talks are now online! · 1 Oct 2026
Product

Measure AI adoption by whether finished work reaches users faster, counting the time colleagues spend checking and fixing AI output.

Nielsen Norman Group · AI in UX: Work Is Faster, But Practitioners Have Mixed Feelings · 24 Oct 2026
Product

Put a prototype in front of three users, then open the specification with a list of what to keep and what to cut.

Product Map · AI product management in the agentic era: PMs build now · 20 Nov 2026
Product

Keep reusable agent instructions in one shared repository so that product managers adapt an existing one instead of building a duplicate.

Microsoft Inside Track · Boosting product manager productivity at Microsoft with AI · 9 Oct 2026
Product

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.

Microsoft Inside Track · Boosting product manager productivity at Microsoft with AI · 9 Oct 2026
Product

Keep engineers responsible for deciding what is released to production, even when product managers or designers build features with AI agents.

The Pragmatic Engineer · The state of the tech industry in 2026 · 8 Oct 2026
Product

When a new feature ships, check that the product's AI agent knows when to use it, and treat a gap as a defect.

Lenny's Newsletter · The end of feature discovery as we know it. · 9 Nov 2026
Product

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.

Silicon Valley Product Group · AI and the Future of the Product Role · 7 Nov 2026
Product

Record decisions about what to build and how in a shared specification that becomes the tasks AI agents carry out and update.

Inside Atlassian · 3 lessons from rebuilding Atlassian’s product development lifecycle for people and agents · 13 Nov 2026
Product

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.

The Pragmatic Engineer · The Pulse: new trend of building “internal vibe-coding apps” at tech companies · 19 Oct 2026
Product

Expect each product manager to defend every statement in their own documents, using AI as a thought partner rather than the writer.

Behind the Craft · Gemini 4 Changed How Google Builds Products | Jaclyn Konzelmann · 2 Nov 2026

After the prototype

AI makes a working prototype quick, so the effort moves to choosing a direction and getting from prototype to production with a reliable product.

19 plays · Topic pageClearest first, as Jev scored them
WORKING SURFACECHECKEDBY JEV · 22 NOV 2026
Product

Show stakeholders proposed versions of a feature as clickable prototypes kept side by side, instead of describing each version in a document.

Figma Blog · 6 ways teams are experimenting with code layers · 25 Oct 2026
Product

Release a new feature to half of new users and keep the other half unchanged as a comparison group.

Muzli Blog · AI didn’t kill the design process. It made being dirt cheap. The new workflow, the tools, and what you should do today. · 7 Oct 2026
Product

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.

Thoughtworks Insights · Cheaper code won't kill software development, but it’s already reshaping it · 20 Oct 2026
Product

Ship a new AI feature switched off by default as an experiment, and measure who turns it on and keeps it on.

UX Collective · Nobody asked for the sparkle button · 26 Oct 2026
Product

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.

Thursday Thoughts on AI · What I Look For in an AI PM - Part 4: The Prototype Isn’t Enough Anymore · 20 Nov 2026
Product

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.

UX Collective · Buy vs. build is now also a UX decision, especially in enterprise · 24 Oct 2026
Product

Before anyone builds a prototype, write down the decision it is meant to help the team make.

Top 1% Builder with Ravi · PRD or Prototype: Which should start with when it comes to building products with AI? · 18 Oct 2026
Product

Before a product experiment ships to users, write down the number of users it needs and the date the team will read the result.

Muzli Blog · AI didn’t kill the design process. It made being dirt cheap. The new workflow, the tools, and what you should do today. · 7 Oct 2026
Product

Show the working prototype to stakeholders before the production build, so that engineering and marketing partners can commit early.

Inside Track (Microsoft) · Rebuilding our Microsoft Foundry Labs site with a three-people build team and AI · 4 Oct 2026
Product

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.

The Product Picnic · LLMs are just normal technology. But tech is just a normal medium. · 29 Sep 2026
Product

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.

SVPG · Experimentation, AI and the Product Model · 22 Oct 2026
Product

Before launch, decide formally whether each prototype the team has built is worth the customer's attention, and set the rest aside.

Top 1% Builder with Ravi · PRD or Prototype: Which should start with when it comes to building products with AI? · 18 Oct 2026
Product

Before deploying a change built from a customer call, ask whether it is worth doing and whether it is what the customer meant.

The Beautiful Mess · TBM 450: The Loss of Positive Friction · 9 Nov 2026
Product

Require every proposed AI feature to fill in a one-page brief naming who asked, what it does, and its AI cost per seat.

UX Collective · Nobody asked for the sparkle button · 26 Oct 2026
Product

Revise the written specification and the working prototype against each other, so that a change in one is checked in the other.

Inside Track (Microsoft) · Rebuilding our Microsoft Foundry Labs site with a three-people build team and AI · 4 Oct 2026
Product

End each stage of a project with working software that the team must inspect, not with a plan.

Thoughtworks · Quality is speed: Where engineering discipline moves in the AI era · 8 Oct 2026
Product

Name who may approve and who may revert a change made with an AI agent, and set technical permissions to match.

Postdigitalist · Is agentic design living up to the expectations? · 14 Nov 2026
Product

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.

Irrational Exuberance · The Explorer Pattern for product invention and development. · 22 Nov 2026
Product

Have product teams run their own experiments, with experimentation specialists embedded to coach them instead of running tests on request.

SVPG · Experimentation, AI and the Product Model · 22 Oct 2026

Agent context files

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.

13 plays · Topic pageClearest first, as Jev scored them
CHECKEDJEV22 NOV 2026
Product

When asking a colleague for context, say which decision it is for and what is already known.

The Beautiful Mess · TBM 452: Contexting vs. Context · 19 Nov 2026
Product

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.

martinfowler.com · Generated Glossary · 16 Nov 2026
Product

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.

The Beautiful Mess · TBM 452: Contexting vs. Context · 19 Nov 2026
Product

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.

Lenny's Newsletter · How I AI: Grok vs. Dot vs. Muse vs. Duet: which one crushes the competition? + How Figma’s PMs actually use AI every day · 3 Nov 2026
Product

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.

Evil Martians · AI makes design system guardrails mandatory; this framework delivers them · 24 Sep 2026
Product

Write down the actions the AI agent must never take, such as renaming a customer's existing feature flags.

PostHog · WTF is context engineering? (with real examples) · 10 Oct 2026
Product

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.

Qiita · How development started to flow after separating the Claude that writes prompts from the Claude that implements · 8 Nov 2026
Product

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.

Lenny's Newsletter · How I AI: Grok vs. Dot vs. Muse vs. Duet: which one crushes the competition? + How Figma’s PMs actually use AI every day · 3 Nov 2026
Product

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.

Behind the Craft · We Built Grok Bot. Here Are Our 14 Best Bots | Peng Zheng & Lauren Tan · 28 Sep 2026
Product

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.

Nielsen Norman Group · Context Libraries: How AI Power Users Manage Context Engineering · 11 Oct 2026
Product

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.

Nielsen Norman Group · The New Big Ball of Mud: Why Agentic AI Systems Turn Fragile · 3 Oct 2026
Product

Before a manager calls a colleague resistant to AI, list which documents, drives and team systems that colleague's AI assistant can actually open.

Nate's Newsletter · Your agent is giving you reasonable answers from half your context. A conversation with OpenAI. · 25 Sep 2026

Decision records

A written record of what was decided and why, kept with the work so that someone who did not build it can review it.

12 plays · Topic pageClearest first, as Jev scored them
CHECKED BY JEV · CHECKED BY JEV ·22.11.26
Product

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.

Product Talk · Trash Can Tracking — All Things Product Podcast with Teresa Torres and Petra Wille · 25 Sep 2026
Product

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.

The Beautiful Mess · TBM 439: Day At The Gig · 16 Sep 2026
ProductDesign

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.

Design Outcomes · Three Lattes, One Order · 27 Sep 2026
Product

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.

Thoughtworks · Don’t ask AI to write the user story yet · 23 Oct 2026
ProductDesign

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.

Design Outcomes · Know What to Doubt · 27 Sep 2026
Product

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.

AWS Machine Learning Blog · Accelerating product development with AI-driven lifecycle management (AI-PDLC) in AWS Quick · 17 Nov 2026
Product

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.

this+that · Nobody notices when a company forgets · 29 Sep 2026
Product

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.

The Socratic Leadership · The Roadmap Is a Lie · 18 Oct 2026
Product

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.

The Beautiful Mess · TBM 441: AI, the Loss of Positive Friction, and What to Do About It · 27 Sep 2026
Product

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.

Thoughtworks · Don’t ask AI to write the user story yet · 23 Oct 2026
Product

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.

The Socratic Leadership · The Roadmap Is a Lie · 18 Oct 2026
Product

Trace every acceptance criterion in a specification back to the customer problem and priority score it came from.

AWS Machine Learning Blog · Accelerating product development with AI-driven lifecycle management (AI-PDLC) in AWS Quick · 17 Nov 2026

Agent ownership

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.

9 plays · Topic pageClearest first, as Jev scored them
CHECKEDJEV22 NOV 2026
Product

Require an AI agent that classifies documents to give a written reason for each decision that a person can check against the source.

Microsoft Inside Track · Scaling AI responsibly at Microsoft: Lessons from our Customer Zero journey · 24 Oct 2026
Product

Write down what the first version of an AI feature will not do before deciding what it will do.

Bootcamp · We wanted voice AI in our payments app. Here’s what we cut. · 1 Nov 2026
Product

Name the person accountable for each AI agent's behaviour, and write down what the agent may do without supervision.

Thoughtworks · Why executive judgment decides who wins with AI · 17 Oct 2026
Product

Assign every AI agent a named owner and a defined scope before launch, and update both when people or processes change.

Retool · Do your AI agents need an org chart? · 13 Nov 2026
Product

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.

Sublime Coding · DHH's Rails World 2026 Keynote: Pencils Down, Now What · 28 Sep 2026
Product

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.

Atlassian blog · How two companies made agentic AI the core of modern enterprise workflows · 17 Nov 2026
Product

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.

Thoughtworks · Why executive judgment decides who wins with AI · 17 Oct 2026
Product

Write down, for each AI agent, what it may recommend, decide and carry out, and when authority returns to a person.

Thoughtworks · Leadership in the age of AI agents · 10 Oct 2026

Human approval

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.

8 plays · Topic pageClearest first, as Jev scored them
CHECKEDJ22 NOV 2026
Product

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.

Microsoft Inside Track · Beyond translation: How we’re making Microsoft Copilot work better in Japanese · 6 Nov 2026
Product

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.

Auth0 Blog · Agentic Development: Time to Shift the Focus · 20 Oct 2026
Product

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.

The Product Picnic · Assigning agency to AI means surrendering your own · 21 Sep 2026
Product

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.

Microsoft Inside Track · Beyond translation: How we’re making Microsoft Copilot work better in Japanese · 6 Nov 2026
Product

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.

Microsoft Inside Track · From the field: How agentic AI is reshaping adoption at Microsoft · 26 Sep 2026
Product

Count each quarter how many changes from product and design reached production, instead of counting prototypes or lines of code.

AutonomyAI · The bottleneck moved: what 131 product and engineering teams told us · 20 Nov 2026
Product

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.

DataHub · What Shipping an AI Agent to 16,000 People Taught Me About Reviewing One · 18 Sep 2026

Evals before the build

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.

5 plays · Topic pageClearest first, as Jev scored them
22 NOV2026CHECKED BY JEV
Product

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.

Microsoft Inside Track · Deploying AI with employee councils: An IT playbook from Microsoft · 30 Oct 2026
ProductEngineering

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

From 3 articles · Anthropic, GitHub Next, PikdShow all 3Hide
Anthropic · in Anthropic · 24 Sep 2026The automatic checks are agreed with the people who approve changes, and tests are added until those engineers would merge on the results alone.
GitHub Next · in The Pragmatic Engineer · 26 Sep 2026The spec for a prototype lists how the agent will verify each part of its work.
Pikd · in BLOG@CACM · 28 Sep 2026The tests that define a correct result are written first, the agent works until they pass, and people review the tests instead of the code.
Product

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.

Microsoft Inside Track · Deploying AI with employee councils: An IT playbook from Microsoft · 30 Oct 2026
Product

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.

Lenny's Newsletter · Advanced evals: How to find (and fix) hidden AI failures in your product · 23 Sep 2026

Ground truth for review

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.

3 plays · Topic pageClearest first, as Jev scored them
CHECKED22.11.26JEV

Interfaces for agents

Product pages and data designed so that an AI agent, not only a person, can use them.

2 plays · Topic pageClearest first, as Jev scored them
CHECKEDJEV22.11.26

Understanding the work

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

1 play · Topic page
CHECKED BY JEV · WORKING SURFACE ·22 NOV2026

Work cut to size

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

1 play · Topic page
WORKING SURFACECHECKEDBY JEV · 22 NOV 2026

Other plays

Plays from links that are not filed under a topic.

7 playsClearest first, as Jev scored them
CHECKEDJEV22 NOV 2026
Product

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.

Smashing Magazine · Is Your Organization Messing Up AI Adoption? · 18 Oct 2026
Product

Ask users what they expect before they first use an AI feature, then compare that with what they report afterwards.

UX Tigers · User Satisfaction Depends on Delivered Quality Relative to Expectations · 2 Oct 2026
Product

Collect 90 days of requests that customers sent to analysts and use them as the list of questions a chat feature should answer.

UX Collective · Where to Draw the Line Before AI Reaches Professional Users · 24 Oct 2026
Product

Ask the people already using AI tools to show colleagues in similar roles what works for them, before training the rest of the team.

Smashing Magazine · Is Your Organization Messing Up AI Adoption? · 18 Oct 2026
Product

Add the question of whether users understand and trust a feature to every product review, beside the question of whether it works.

Design Outcomes · A Working Feature Isn't the Same as a Trusted One · 27 Sep 2026
ProductDesign

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.

LukeW · Skip the Tools, Make the Outcomes · 26 Sep 2026
Product

Keep untested product ideas off dated roadmaps until product discovery has shown that they solve the customer's problem.

Silicon Valley Product Group · Predictability vs Outcomes · 18 Oct 2026