Issues · Working Surface

Working Surfaceissues

16 issues · since 16 September 2026

One note a day, written by the morning job from the pieces it verified, and kept here as written. Each note's links have their own pages.

Issue · 3 linksThursday 1 October 2026Three pieces from the past four days place the risk of AI-assisted work at the moment a person must explain or judge what an AI agent produced. An engineering leader, a usability researcher and a summit of product leaders each argue that understanding and judgement do not grow with output and have to be checked on purpose.

LeadDev

Your error budgets don't know AI exists

Company story · roles · decisions

UX Tigers

User Vigilance Fails Twice in the AI Age: Watch Duty & Verdict Duty

How-to · agents · critique & review

Lenny's Newsletter

All of the Lenny & Friends Summit talks are now online!

Company story · roles

Issue · 3 linksWednesday 30 September 2026Dropbox, Shopify and Figma describe what changes once AI agents make building cheap. Dropbox checks agent changes like a person's, Shopify rebuilds its apps natively with one shared test suite, and Figma's product lead says choosing a direction is now the hard part.

Dropbox.Tech

Evolving our calendar assistant Reclaim to be AI-native without starting over

How-to · agents

The Pragmatic Engineer

Why has Shopify dropped React Native?

Company story · agents · decisions

Figma Blog

What it takes to build great products now

How-to · prototyping · design systems

Issue · 11 linksTuesday 29 September 2026When AI tools do more of the drafting and building, some work that people did along the way stops happening. Six pieces name parts of it, from practising a skill to writing down why a rule exists, and suggest how a team can keep doing that work. Five engineering pieces from 29 September cover teams of coding agents, architecture, a developer survey, earlier approvals and how junior engineers build judgement.

this+that

Nobody notices when a company forgets

Company story · rituals · artifacts

The Product Picnic

LLMs are just normal technology. But tech is just a normal medium.

Company story · prototyping · handoff

Nimble UX

Where do we find room to think?

Company story · collaboration · roles

Design Systems Collective

Before You Let an AI Agent Touch Your Design System, Write Down Four Rules

How-to · design systems · decisions

Nate's Newsletter

Executive Briefing: You Bought Better Tools and Your Finished Work Still Waits

Company story · collaboration · roles

Design Systems Collective

“You don’t fix the output, you fix the system” — Cristian Morales Achiardi on agentic design systems

How-to · design systems · agents

Medium

Durable Agentic Teams: Maximizing Your Software Development Workflow

How-to · agents · collaboration

Accidentally in Code

Good Architecture Is a Function of Time

How-to · decisions · design systems

Agoda Engineering & Design

Key Takeaways from Agoda’s AI Developer Report 2026

Company story · agents · roles

Medium

The Approve Button Is Not a Control

How-to · critique & review · agents

LeadDev

AI makes critical thinking harder to build

Company story · roles · rituals

Issue · 10 linksMonday 28 September 2026Five pieces from designers and engineers show which jobs people keep when AI agents do the building. They keep the design system and the first screen, the review of what agents make, the files agents read, and responsibility for the product as a whole. Five engineering pieces from 28 September cover reviewing AI-written code, agents that change live systems, agents that build agents, new AI models and tests written first.

Behind the Craft

We Built Grok Bot. Here Are Our 14 Best Bots | Peng Zheng & Lauren Tan

Company story · agents · design systems

Design Outcomes

New Patterns Are a Tax

How-to · critique & review · design systems

Design Outcomes

Good Isn't Great

How-to · critique & review · roles

Atlassian

Introducing CAFE(S): A framework for defining AI context quality

Company story · agents · artifacts

Sublime Coding

DHH's Rails World 2026 Keynote: Pencils Down, Now What

Company story · roles · decisions

Elevate

The Code Nobody Reads

Company story · critique & review · roles

LeadDev

Your agent loop is not a production system

How-to · agents · roles

Salesforce Engineering

Engineering Multi-Agent AI Teams That Build and Test Themselves

How-to · agents · critique & review

Databricks

How Databricks rolls out frontier models to 12,000 employees on Day 1

Company story · agents · decisions

BLOG@CACM

Nobody Did TDD for 25 Years. Now the Machine Requires It

How-to · agents · critique & review

Issue · 5 linksSunday 27 September 2026When AI writes part of a team's work, reviewers and users need to see what was made, by whom and from what. The pieces label sections by author, link summaries to sources, keep one document per feature, show users when a save happens, and ask for expert reviewers.

Design Outcomes

Know What to Doubt

Company story · critique & review · artifacts

The Beautiful Mess

TBM 441: AI, the Loss of Positive Friction, and What to Do About It

Company story · artifacts

Design Outcomes

Three Lattes, One Order

Company story · artifacts · handoff

SVPG

Experts Lead Experts

Company story · roles

Design Outcomes

A Working Feature Isn't the Same as a Trusted One

How-to · critique & review

Issue · 7 linksSaturday 26 September 2026Six pieces describe how teams change their work once AI agents can finish whole tasks. They show the result before the tool, take workflows apart before automating them, set checks before release and make people responsible for managing agents. One engineering piece from the same day asks whether engineers still enjoy the work once their team codes with AI.

LukeW

Skip the Tools, Make the Outcomes

Company story · artifacts

GitHub Blog

When chat is the wrong UI

How-to · agents · artifacts

Microsoft Inside Track

From the field: How agentic AI is reshaping adoption at Microsoft

Company story · agents · critique & review

Microsoft Inside Track

Driving seller adoption of Sales Agent through role-based change management at Microsoft

Company story · roles · handoff

The Pragmatic Engineer

Design Engineering with Maggie Appleton

Company story · prototyping

CIO

I stopped asking my team to use AI. I asked them to manage it

Company story · agents · roles

shubs.io

do we still enjoy software engineering in the age of AI?

Company story · roles

Issue · 5 linksFriday 25 September 2026Three pieces look at what shapes AI work before anyone chooses: the defaults a product ships, the options a team rejects, and the material an AI can reach. Each argues that these inputs should be kept in view, and one argues that each needs a named owner. Two engineering pieces from the same day look at how AI tools change an engineering manager's job and how a large embedded-software company plans to reorganise around AI agents.

UX Tigers

Default Dominance: Most Users Never Change the Setting You Ship

How-to · agents · decisions

Product Talk

Trash Can Tracking — All Things Product Podcast with Teresa Torres and Petra Wille

Company story · rituals · decisions

Nate's Newsletter

Your agent is giving you reasonable answers from half your context. A conversation with OpenAI.

Company story · agents · collaboration

Codacy

How AI Is Changing the Engineering Manager Role: More Context, More Capacity, and the New Job of Protecting Focus

Company story · roles

arXiv

Developing a Roadmap to an AI-first Organization: A Case Study in Embedded Software Development

Company story · roles · agents

Issue · 4 linksThursday 24 September 2026Four pieces from Anthropic, Stripe, Cursor and Evil Martians describe setting the rules for AI agents' work before the work starts. The rules go into automatic checks, review policies, monitoring plans and the components themselves, and people judge what falls outside them.

Anthropic

How to prepare for AI-driven code modernization projects

Company story · critique & review · artifacts

Stripe

How Stripe is designing Checkout for AI agents

How-to · agents

Cursor

Bots for the last mile: Rollouts, Security Review

Company story · agents · critique & review

Evil Martians

AI makes design system guardrails mandatory; this framework delivers them

Company story · design systems · agents

Issue · 4 linksWednesday 23 September 2026Four pieces argue that people can keep up with work made by AI agents only when it reaches them in small pieces that have already been checked. They also say that the judgment people bring has to be built first, by reading real cases and by working beside experienced colleagues.

Shopify Engineering

Helix: The internal tool powering our Shopify app's native migration

Company story · critique & review · agents

SEP

So, AI Killed Your Code Review Process. Now What?

Company story · critique & review · rituals

Lenny's Newsletter

Advanced evals: How to find (and fix) hidden AI failures in your product

How-to · critique & review · rituals

UX Collective

In the age of AI, the UX field survives on leaders who cultivate juniors

Company story · roles

Issue · 4 linksTuesday 22 September 2026Four accounts from Warp, Linear and Bolt show how software teams check work now that AI agents produce it faster than people can review it. Each company moves part of the checking into written criteria, into files the agents read, or into a review split by expertise.

Lenny's Newsletter

How I AI: Meta's Muse review + How Warp ships 2,000 PRs a month with AI factories

Company story · critique & review · roles

Linear

AI coding has made CI a bottleneck, so we reworked ours to keep up

Company story · agents · artifacts

Warp

Using LLM-as-a-judge scoring to measure your software factory

How-to · critique & review · artifacts

Bolt Labs

Design engineering at Bolt: shipping components with AI agents

Company story · design systems · handoff

Issue · 5 linksMonday 21 September 2026Five pieces look at the work left for people once AI agents build quickly. It lies in reviewing agent-built changes, answering for what is handed over, and deciding what an interface promises its users.

Design Outcomes

The Bottleneck Moved to Review

Company story · critique & review · roles

The Product Picnic

Assigning agency to AI means surrendering your own

Company story · roles · agents

GitHub Blog

Should you read the code, is RAG dead, and did Skills kill MCP?

Company story · critique & review

Design Outcomes

What the Loading State Promises

How-to · critique & review · rituals

Design Outcomes

One Chat, and It Grows

How-to · decisions · collaboration

Issue · 2 linksSunday 20 September 2026Two pieces look at the standing instructions people give AI agents before a task begins. Heavy users of one agent keep written rules, including which actions need their approval, and one engineer has his agent question him about each plan.

Nielsen Norman Group

The 3 Roles of Context for AI Agents

How-to · agents

The Pragmatic Engineer

AI Skills with Matt Pocock

Company story · agents · decisions

Issue · 3 linksSaturday 19 September 2026Three pieces show that AI now produces working prototypes, whole apps and product comparisons in minutes. Each argues that the result is worth trusting only when something is settled first or can be checked: a written problem, fixed parts, or values with a source.

UX Tigers

The 100 Most Common UX Design Methods, Ranked by Value

Company story · prototyping · decisions

Product Talk

Creating Aha! Builder: Concept to Code, No Engineers Required

Company story · prototyping · roles

UX Tigers

Comparison Tables Are Decision Machines: Design Them to Deliver a Verdict

How-to · design systems · agents

Issue · 3 linksFriday 18 September 2026Three pieces show that a person's review of an AI agent's work is only as good as the reference that person checks against. Without a reliable reference, a reviewer can add errors instead of catching them.

DataHub

What Shipping an AI Agent to 16,000 People Taught Me About Reviewing One

Company story · critique & review

DataHub

Context Engineering for AI Agents: Why the Hard Part Isn't the Context Window

How-to · agents

The Airbnb Tech Blog

Beyond the model: Engineering AI infra with scientific judgement

Company story · artifacts

Issue · 4 linksThursday 17 September 2026Four pieces show that when AI agents do the building, people's judgment moves to either end of the work. People state the problem and write checks before the build, and review the running result before it reaches production.

The Pragmatic Engineer

Inside OpenAI's agentic software factory

Company story · agents

Product Talk

4 New Evals and 16 Experiment Variants to Fix 1 Customer Complaint

How-to · critique & review

Product Talk

Delivery Isn't Free, All Things Product Podcast

Company story · collaboration

Vercel

How Delphi ships 100 times a day with its Python backend on Vercel

Company story · prototyping

Issue · 5 linksWednesday 16 September 2026Five pieces show that when AI helps produce work, a person still has to check it against a source before others rely on it. Where nobody inside the company does that checking, the users end up doing it themselves.

Nielsen Norman Group

AI Can Help Write an Article, but It Can't Stand Behind It

Company story · critique & review

Behind the Craft

Stop Building AI Agents. Start Building AI Employees

Company story · agents

Nielsen Norman Group

Test Complex Interactions Earlier with AI Prototyping

How-to · prototyping

The Product Picnic

AI hypervigilance is now an omnipresent cognitive load for your users

How-to · critique & review

The Beautiful Mess

TBM 439: Day At The Gig

Company story · collaboration

Ask