Working Surfaceissue · 13 Nov
Issue · 11 links
Issue

Friday
13 November 2026

Eleven accounts show teams deciding how far AI agents may act alone, from Sentry's quick-look merges to Shopify's watched attacking agent and Zalando's design system prototypes. Across them, freedom for the agent follows limits on what it can reach, automated checks and a named person who answers for it.

01

Sentry Blog

We have a Slopware Factory

David Cramer · 12 Nov

David Cramer, a co-founder of Sentry, says the company's Slack-based AI agent has more code changes to its name than any person, often merged after a brief look.

Company story · agents · critique & review · Human approval

02

Ubie Tech Blog (Zenn)

Beyond the software factory: Ubie's in-house cloud agent platform for making all company work AI-native

Yuku Kotani · 12 Nov

Ubie, a Japanese health-technology company, lets AI agents work without approvals by limiting each shared agent's access to what everyone in the conversation may see.

Company story · agents · collaboration · Agent ownership

03

Shopify Engineering

Cyber Chaos Monkey: Staying ahead of security threats with AI agents

Dan Scofield · 12 Nov

Shopify built AI agents that attack its own live systems to find security flaws, with a second AI agent on a different AI model ready to stop them.

How-to · agents · critique & review · Agent ownership

04

Pinterest Engineering Blog

How Pinterest Improved Analytics Agent Compliance with Loop Engineering

Skyler Zheng, Chris Moradi, Lu Liu, Aman Gairola and Michael Chau · 12 Nov

Pinterest engineers stopped hand-editing their data agent's instructions and built an automated loop that keeps only changes passing paired tests drawn from real chats.

How-to · agents · critique & review · Evals before the build

05

UX Collective

In-system design: from code to Figma and back. Prototyping in your real design system

Christine Vallaure · 11 Nov

Designer Christine Vallaure moves prototypes between code and Figma with an AI agent by naming components identically on both sides and asking for a note of anything invented.

How-to · design systems · prototyping · Agent context files

06

Retool

Do your AI agents need an org chart?

Kelsey McKeon · 10 Nov

Retool's survey of 300 technology leaders found half worry about AI agents making decisions with no clear owner, and recommends naming an owner and scope before launch.

Company story · agents · roles · Agent ownership

07

UX Collective

AI Prototyping inside your design system. A hands-on guide for design & product teams.

Christine Vallaure · 10 Nov

Designer Christine Vallaure found that AI builders connected to a design system rebuild lookalike components, and says agents need a generated component list they must query.

How-to · design systems · prototyping · Agent context files

08

Into Design Systems + AI

How Zalando built its own AI prototyping environment on top of its design system

Into Design Systems · 9 Nov

Zalando's design system team built its own AI prototyping tool, the ZDS Capsule, after Figma Make stayed off brand, then learned its prototypes could slow implementation.

Company story · design systems · prototyping · After the prototype

09

Headway

Your Design System MCP Shouldn't Be Costing You Tokens

Tim Gremore · 10 Nov

Tim Gremore of the agency Headway says a design system's AI costs depend on how often its context loads; in an Atlassian test, a smaller file cost more.

How-to · design systems · agents · Agent context files

10

Inside Atlassian

3 lessons from rebuilding Atlassian’s product development lifecycle for people and agents

Avani Prabhakar · 10 Nov

Atlassian is redesigning how its nearly 10,000 research and development staff build products with AI agents, aiming people at decisions and keeping shared specifications the agents work from.

Company story · agents · roles · Changing roles

11

LeadDev

3 agentic AI questions engineering leaders must answer

Jennifer Riggins · 10 Nov

Journalist Jennifer Riggins asked developer-experience researchers how to measure AI agents' effect on engineering teams; they point to wellbeing, enforced accountability and the cost of checking agents' work.

Company story · agents · critique & review · Agent ownership

Swipe for 02 to 11
13 Nov
The note

As AI agents take on more real work, the teams that give them the most freedom first limit what the agents can reach. They also add a second check that does not depend on a person's quick glance, and design system teams and Atlassian apply the same idea to prototypes and plans.

David Cramer, a co-founder of Sentry, which makes error-monitoring software for developers, wrote about Junior, the company's internal AI agent that takes requests in Slack (13 Nov · 01). Cramer says the agent's name is on more code changes than any other single contributor at Sentry. In his example, he asked it in one Slack message to remove a failed experiment and gave no further detail. He glanced at its pull request, approved it himself and let the agent merge it, at a cost of \$1.32 and about five minutes of his time. He admits the change may have missed some references, which shows how thin the human check becomes once an agent handles routine changes.

Yuku Kotani, chief technology officer of Ubie, a Japanese health-technology company, described in Japanese the platform Ubie built so AI agents can work across the whole company (13 Nov · 02). The problem was sharing: an agent called in a shared Slack channel reads with the requester's access, so it could show management information to partners in that channel. Ubie split its agents into two kinds. Personal agents use one person's access and cannot be shared, while team agents run under service accounts limited to what everyone in the conversation may see. Because the agents' workspaces hold no credentials, they may make reversible changes without asking, and a nightly agent proposes improvements to the agents themselves.

Dan Scofield, writing on Shopify's engineering blog, described AI agents that attack Shopify's own live systems to find security flaws before outside attackers do (13 Nov · 03). Shopify, which runs online stores for merchants, says its bug bounty reports have risen almost 300% since 2024 as AI models made finding flaws cheaper. A second AI agent, running on a different AI model, reads everything the attacking agent does and stops it if it breaks the agreed rules. If that second agent fails, the run ends, and Shopify reports tens of thousands of runs with no outages caused by the testing.

Five Pinterest engineers, data scientists and managers, including software engineer Skyler Zheng, described how they made the company's data-analysis AI agent follow its required steps (13 Nov · 04). Rewriting its instructions by hand was trial and error, and one sensible rule made it refuse a question it could answer. The team built paired tests from real chats, one set where a rule applies and one where it does not. An automated loop now keeps only changes that fix failures without breaking anything else. Because 10.3% of cases changed result between identical runs, they judge changes case by case, not by the total score.

Christine Vallaure, a designer who teaches design and code through her learning platform moonlearning, described how she moves a prototype between code and Figma with an AI agent (13 Nov · 05). Her one condition is that every component has the same name and properties on both sides, so the agent looks parts up instead of guessing. She asks the agent to leave a note listing what it built by hand and where the two sides differ, and she reads that note before the screens. The round trip caught a 21-pixel spacing fault in the code that no automated check had found.

Kelsey McKeon of Retool, a company that sells software for building internal tools and AI agents, reported its survey of 300 technology leaders (13 Nov · 06). Half of the leaders with agents in production named agents making decisions with no clear owner as a top concern. Thirteen percent said an agent had taken an unintended action in a production system in the past year. Retool recommends a named owner and a defined scope for every agent before launch, and its figures come from a vendor with an interest in the answer.

Christine Vallaure (13 Nov · 07) also wrote a guide in UX Collective on why AI builders connected to a design system still hand developers a lookalike. When she tested Claude Design on her own code, every button property and token came back right, but its helpers, styles and types were replaced. Her remedy is a list, generated from the code, of every component, property and allowed value. The agent must query it through an MCP server, a standard connection that lets an agent ask a tool what exists. Prototypes stay on a design branch that is never merged, and accepted ideas are rebuilt and checked before they reach the product.

Zalando's design system team built its own AI prototyping tool, the ZDS Capsule, after Figma Make kept producing screens that were off brand. Dana Baddad and Gonzalo Vásquez Correa (13 Nov · 08) described it at a meetup in Berlin, in notes published by the newsletter Into Design Systems. The team rewrote its guidelines as small markdown files and made its skills run scripts at critical steps, because the agents' choices varied from run to run. More than 20 designers have contributed, but an engineer found the AI-written motion specs for one feature hard to follow. The team judged that implementation could take two or three times as long.

Tim Gremore (13 Nov · 09), development lead at the agency Headway, wrote about what a design system costs when AI agents read it. A DESIGN.md file, the usual written rules for an agent, is read in full on every turn. In a test Atlassian published, an 80 KB file used almost twice the tokens of a larger MCP server fetched in slices. Headway runs its own MCP servers as local packages that answer narrow questions, such as which properties a component takes.

Avani Prabhakar (13 Nov · 10), Atlassian's Chief People and AI Enablement Officer, described how the company is reworking product development for nearly 10,000 research and development staff. Its own survey found that 26% of developers now say AI saves them more than ten hours a week, down from 68% a year earlier. Agents now prepare fixes for 52% of security vulnerabilities, so engineers start from a proposed fix and decide whether it is safe to ship. Decisions are kept in shared specifications that become the tasks agents carry out. More than 50 product managers and designers shipped over 100 engineering-approved changes in three months.

Jennifer Riggins (13 Nov · 11), writing for LeadDev, asked developer-experience researchers how engineering organisations should measure AI agents, with no DORA survey of software delivery this year. Their answers stress developers' wellbeing and the cost of checking agents' work, which a McKinsey report put at 60% of agentic AI spending. Although 87% of organisations claim AI governance policies, fewer than a quarter have put controls in place. Charlotte Fleming of Octopus Deploy argues that the rules must run as gates in the deployment pipeline.

What they add up to

Ubie and Shopify let their agents act with little supervision only after limiting what the agents could reach and adding a check that does not tire. Pinterest built the same kind of check for an agent's behaviour. Vallaure, Zalando and Headway built theirs for design systems, as a list of real components or a script the agent must run. Atlassian applies the idea to the whole process, keeping decisions in specifications the agents work from and people at the points that need judgement. The inference here is that where those limits are missing, as in Cramer's account, one person's glance is the only check. Retool's survey and the researchers LeadDev asked suggest many organisations are in that position.

The case against

Most of these accounts come from the teams that built the systems, and only Pinterest reports careful measurements. Atlassian's figures come from its own pilots, and Headway's cost comparison rests on one Atlassian test of one screen. Zalando's experience also shows that a faster prototype can make implementation slower. Sentry's light review may be the more honest picture of most teams, and for low-risk changes it may be good enough.

Receipts
Sentry Blog
We have a Slopware FactoryCompany story · 13 Nov 2026
David Cramer · 12 November 2026

David Cramer, a co-founder of Sentry, says the company's Slack-based AI agent has more code changes to its name than any person, often merged after a brief look.

Ubie Tech Blog (Zenn)
Beyond the software factory: Ubie's in-house cloud agent platform for making all company work AI-nativeCompany story · 13 Nov 2026
Yuku Kotani · 12 November 2026

Ubie, a Japanese health-technology company, lets AI agents work without approvals by limiting each shared agent's access to what everyone in the conversation may see.

Shopify Engineering
Cyber Chaos Monkey: Staying ahead of security threats with AI agentsHow-to · 13 Nov 2026
Dan Scofield · 12 November 2026

Shopify built AI agents that attack its own live systems to find security flaws, with a second AI agent on a different AI model ready to stop them.

Pinterest Engineering Blog
How Pinterest Improved Analytics Agent Compliance with Loop EngineeringHow-to · 13 Nov 2026
Skyler Zheng, Chris Moradi, Lu Liu, Aman Gairola and Michael Chau · 12 November 2026

Pinterest engineers stopped hand-editing their data agent's instructions and built an automated loop that keeps only changes passing paired tests drawn from real chats.

UX Collective
In-system design: from code to Figma and back. Prototyping in your real design systemHow-to · 13 Nov 2026
Christine Vallaure · 11 November 2026

Designer Christine Vallaure moves prototypes between code and Figma with an AI agent by naming components identically on both sides and asking for a note of anything invented.

Retool
Do your AI agents need an org chart?Company story · 13 Nov 2026
Kelsey McKeon · 10 November 2026

Retool's survey of 300 technology leaders found half worry about AI agents making decisions with no clear owner, and recommends naming an owner and scope before launch.

UX Collective
AI Prototyping inside your design system. A hands-on guide for design & product teams.How-to · 13 Nov 2026
Christine Vallaure · 10 November 2026

Designer Christine Vallaure found that AI builders connected to a design system rebuild lookalike components, and says agents need a generated component list they must query.

Into Design Systems + AI
How Zalando built its own AI prototyping environment on top of its design systemCompany story · 13 Nov 2026
Into Design Systems · 9 November 2026

Zalando's design system team built its own AI prototyping tool, the ZDS Capsule, after Figma Make stayed off brand, then learned its prototypes could slow implementation.

Headway
Your Design System MCP Shouldn't Be Costing You TokensHow-to · 13 Nov 2026
Tim Gremore · 10 November 2026

Tim Gremore of the agency Headway says a design system's AI costs depend on how often its context loads; in an Atlassian test, a smaller file cost more.

Inside Atlassian
3 lessons from rebuilding Atlassian’s product development lifecycle for people and agentsCompany story · 13 Nov 2026
Avani Prabhakar · 10 November 2026

Atlassian is redesigning how its nearly 10,000 research and development staff build products with AI agents, aiming people at decisions and keeping shared specifications the agents work from.

LeadDev
3 agentic AI questions engineering leaders must answerCompany story · 13 Nov 2026
Jennifer Riggins · 10 November 2026

Journalist Jennifer Riggins asked developer-experience researchers how to measure AI agents' effect on engineering teams; they point to wellbeing, enforced accountability and the cost of checking agents' work.