Working Surfacetopics

The ideas that keep coming up

13 topics gather the links that return to the same question. Pick one to see what it means and every piece filed under it.

Topic · 46 links · since 16 September 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.

Salesforce Engineering
How AI Slashed 600-Test-Failure Triage From Days to 90 Minutes
Shireen Nagdive and Riya Suri · 17 November 2026
A Salesforce engineering team cut triage of over 600 failing tests from days to 90 minutes, with code doing routine steps and engineers approving the AI's conclusions.
Company story · agents · decisions
18 Nov 2026
InfoQ
Doing The Right Thing: Accountability In The Age Of AI Coding Summary
Shane Hastie with Hugo Venturini · 13 November 2026
Hugo Venturini, a former Meta engineering manager, told the news site InfoQ that whoever directs an AI tool answers for its code, and teams may choose which changes need review.
Company story · critique & review · roles
15 Nov 2026
Dev Interrupted
All the code review is a stage
Andrew Zigler · 12 November 2026
Engineering leaders told Andrew Zigler of Dev Interrupted that AI-written pull requests have outgrown careful review, so they now sort changes by risk before deciding who reads them.
Company story · critique & review · roles
14 Nov 2026
Sentry Blog
We have a Slopware Factory
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.
Company story · agents · critique & review
13 Nov 2026
Salesforce Engineering
Scaling AI Engineering Automation Without Sacrificing Reliability
Salesforce Engineering with Fereydoon Vafaei · 9 November 2026
Salesforce's Agentforce engineers let AI agents fix and test their own reasoning engine, but a person must approve every merge and every release to production.
Company story · agents · critique & review
10 Nov 2026
Forbes Technology Council
Agentic AI Is Shipping Code. Who Owns The Risk?
Andrea Scaduto · 5 November 2026
Andrea Scaduto, chief executive of the security training company SecureFlag, argues that the developer who approves an AI agent's change owns it, so the approval cannot be a formality.
Company story · agents · critique & review
10 Nov 2026
Warp
Addressing the code review bottleneck
Ben Holmes · 5 November 2026
A Warp engineer has AI agents review and test their own code changes and score each pull request's risk, so people know which parts need their attention.
How-to · critique & review · agents
8 Nov 2026
Microsoft Inside Track
Beyond translation: How we’re making Microsoft Copilot work better in Japanese
Kevin Kotani · 5 November 2026
Microsoft gave Copilot's Japanese-language problems one reporting route with named owners and had native speakers test early; daily use in Japan then peaked at 93%.
How-to · localisation · collaboration
6 Nov 2026
A.Team
Agentic engineering for teams: What changes when every engineer runs agents
A.Team · 28 October 2026
A.Team, which supplies engineering teams, advises that an AI agent's pull request needs an approver other than the engineer who asked for it, because review breaks first.
How-to · critique & review · agents
3 Nov 2026
Engineering at Meta
Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale
Sreeja Thummala, Sophie Zeng, Mark Harman, Weini Liu and Eric Liu · 29 October 2026
Meta's JiTTests use AI models to write tests that catch bugs in risky code changes before they are merged, and contact engineers only about the strongest findings.
Company story · critique & review · agents
1 Nov 2026
Accidentally in Code
Escaping the No-Code Platform by Building a Software Factory
Cate Huston · 27 October 2026
Cate Huston rebuilt the hiring marketplace Twill in four months with one engineer and AI coding agents, spending about a third of output on checks against whole classes of bugs.
Company story · agents · critique & review
28 Oct 2026
Design Systems Collective
Humans, humans everywhere. Notes from Converge 2026
Cassie Groos · 25 October 2026
At Converge 2026, design system speakers proposed firm automatic checks for AI agents and named human owners for decisions, according to attendee Cassie Groos.
How-to · design systems · decisions
26 Oct 2026
InfoQ
Move Fast, Don’t Break Trust: Shipping Constantly with Humans and Beyond
Suhail Patel · 23 October 2026
Monzo, a British digital bank, lets engineers and AI agents ship safely by keeping one service template, strict automated checks and a human code owner on every change.
Company story · critique & review · agents
25 Oct 2026
Vercel
How Vercel Agent accesses production safely
Tom Dale · 23 October 2026
Vercel's AI agent for fixing broken deployments investigates with read-only access, then asks a person to approve one plan, avoiding the reflexive clicking that step-by-step prompts cause.
How-to · agents · decisions
24 Oct 2026
Thoughtworks
How Sensible Harness can help teams create an AI-first delivery environment
Vitória Regina Ragazzon Toebe, Amy Pellegrini and María José Lalama · 22 October 2026
A Thoughtworks team built Sensible Harness to run software delivery with three AI agents whose limits the tool enforces, and a person approves each plan before code is written.
Company story · agents · critique & review
23 Oct 2026
LeadDev
Engineers lose 17+ days a year to AI rework
Michael Hill · 20 October 2026
A vendor survey reported by LeadDev finds engineers lose at least 17 working days a year fixing AI-assisted code, while outside code reaches production unreviewed.
Company story · critique & review · decisions
21 Oct 2026
seangoedecke.com
What requirements don't you have?
Sean Goedecke · 19 October 2026
Sean Goedecke, a software engineer and writer on system design, says that about half the large AI-generated changes he reviews add a requirement nobody asked for.
How-to · critique & review · agents
20 Oct 2026
Auth0 Blog
Agentic Development: Time to Shift the Focus
Riccardo Cocetta · 16 October 2026
Riccardo Cocetta, VP of Engineering at Auth0, says the step from idea to pull request is solved, so the hard work is choosing what to build and validating the result.
Company story · decisions · critique & review
20 Oct 2026
Irrational Exuberance
Speeding up code review with small-change
Will Larson · 17 October 2026
Imprint lets the build decide which small pull requests an AI skill can approve, so engineers spend review time on the larger and riskier changes.
Company story · critique & review · agents
18 Oct 2026
claude.dev Blog
How the Claude Code team does code review
Addy Osmani, Morgan Westlee Lunt and Qing Wang · 15 October 2026
The Claude Code team at Anthropic sets how many people approve each change from what the change touches, and doubled its merged changes while reverts fell.
Company story · critique & review · agents
18 Oct 2026
LeadDev
The reality of being a forward deployed engineer (FDE)
Manas Verma · 14 October 2026
Manas Verma, an AI forward-deployed engineer, found that an AI assistant invented column names while mapping a legacy database, and a product expert checked the mapping.
Company story · roles · critique & review
17 Oct 2026
Dev Interrupted
Your agents should ask the factory first
Andrew Zigler · 16 October 2026
Andrew Zigler of LinearB, an engineering-metrics company, proposes that each AI coding agent check how long the team's pull requests wait for review before starting new work.
Company story · agents · critique & review
17 Oct 2026
The Pragmatic Engineer
Uber's AI infra, from the inside
Gergely Orosz with Uday Kiran Medisetty · 14 October 2026
Uber's engineers still review every pull request, but an AI review and a risk score come first, and Uber now tags pull requests by type instead of counting them.
Company story · critique & review · rituals
16 Oct 2026
Accidentally in Code
Attempting to reverse engineer code review
Cate Huston · 13 October 2026
Cate Huston, an engineering leader, used Claude to mine 4,176 code review comments and found that review missed most problems and enforced rules the team never agreed.
Company story · critique & review · decisions
14 Oct 2026
Vercel
How Rillet ships 3× faster with AI agents on Vercel
Susan Aziz · 9 October 2026
At Rillet, an accounting software company, AI agents turn customer requests into pull requests, and one engineer, Anthony Liang, reviews and merges every change.
Company story · agents · critique & review
11 Oct 2026
SoluteLabs
The Agentic Harness: How We Rebuilt Our SDLC for AI-Augmented Product Engineering
Prakash Donga · 8 October 2026
Prakash Donga of SoluteLabs describes a four-phase process for AI-written code, with a human check after each phase and a second AI agent that reviews before a person does.
Company story · agents · critique & review
9 Oct 2026
The GitHub Blog
Building Git infrastructure for agent-scale development
Brian Celenza · 6 October 2026
Brian Celenza of GitHub explains why the volume of commits from AI agents forced a rebuild of GitHub's storage, and why required reviews must survive the change.
Company story · agents · critique & review
8 Oct 2026
JetBrains Research
Our Framework for Reviewing AI-Generated Code
Katie Fraser, Agnia Sergeyuk and Ilya Zakharov · 6 October 2026
JetBrains researchers propose that tools for reviewing agent-written code should show an overview, rank files by risk and only then open code, based on workshops with 17 practitioners.
How-to · critique & review · agents
7 Oct 2026
Salesforce Engineering
How Deterministic Controls Turn AI Output Into Reliable Prompt Templates
Vaibhav Raizada, Kumar Kasimala and Ashish Gite · 30 September 2026
Salesforce engineers let an AI agent draft prompt templates for administrators but gave it no power to save, publish or run them, so a person approves every change.
How-to · agents · critique & review
2 Oct 2026
UX Tigers
User Vigilance Fails Twice in the AI Age: Watch Duty & Verdict Duty
Jakob Nielsen · 29 September 2026
Jakob Nielsen, a usability researcher, argues that people approving an AI agent's actions stop paying attention, and that products should ask less often and offer undo.
How-to · agents · critique & review
1 Oct 2026
Dropbox.Tech
Evolving our calendar assistant Reclaim to be AI-native without starting over
Greg Unrein, Josh Jensen and Christopher Wildman · 29 September 2026
Dropbox's engineers sent every AI agent change in Reclaim, their calendar assistant, through the same checks of scheduling rules that people's changes pass, and let users preview it first.
How-to · agents
30 Sep 2026
Agoda Engineering & Design
Key Takeaways from Agoda’s AI Developer Report 2026
Agoda Engineering · 29 September 2026
Agoda, the online travel company, surveyed developers in Southeast Asia and India: 53 percent use AI agents widely, and 79 percent require a person to approve production deployments.
Company story · agents · roles
29 Sep 2026
Medium
The Approve Button Is Not a Control
Rama Lingamgunta · 29 September 2026
Rama Lingamgunta, who builds AI agent platforms, replaced a single Approve button with three earlier approvals after a reviewer passed a 1,400-line agent change in under two minutes.
How-to · critique & review · agents
29 Sep 2026
Design Outcomes
Good Isn't Great
Leonardo De La Rocha · 26 September 2026
A designer fixed a billing problem for clinicians in an afternoon with an AI coding agent, and his design lead used the review to take it from good to great.
How-to · critique & review · roles
28 Sep 2026
Elevate
The Code Nobody Reads
Addy Osmani · 28 September 2026
Addy Osmani withdraws his advice to read every line of AI-written code and proposes automated review of every change, human review matched to risk, and a person approving every merge.
Company story · critique & review · roles
28 Sep 2026
Microsoft Inside Track
From the field: How agentic AI is reshaping adoption at Microsoft
Poly Palaiogeorgou · 24 September 2026
Microsoft reports that staff in its Europe South region now take up AI agents without being pushed, and that the hard part has moved to governing them.
Company story · agents · critique & review
26 Sep 2026
Cursor
Bots for the last mile: Rollouts, Security Review
Rustam Lalkaka · 23 September 2026
Cursor launched two AI bots for the work after a code change is proposed: one plans and watches the release, and one reviews every change for security flaws.
Company story · agents · critique & review
24 Sep 2026
Lenny's Newsletter
How I AI: Meta's Muse review + How Warp ships 2,000 PRs a month with AI factories
Lenny Rachitsky · 21 September 2026
Warp, which makes tools for software teams, lets the person who asked its AI agent for a code change review that change, instead of waiting for a separate reviewer.
Company story · critique & review · roles
22 Sep 2026
Bolt Labs
Design engineering at Bolt: shipping components with AI agents
Burak Özdemir · 17 September 2026
At Bolt, designers now build interface components with AI agents directly in the library that ships, and engineers review those components instead of rebuilding them.
Company story · design systems · handoff
22 Sep 2026
Design Outcomes
The Bottleneck Moved to Review
Leonardo De La Rocha · 19 September 2026
When designers at Leonardo De La Rocha's company began making code changes with AI agents, the review broke down, so he set out who reviews them and to what standard.
Company story · critique & review · roles
21 Sep 2026
The Product Picnic
Assigning agency to AI means surrendering your own
Pavel Samsonov · 20 September 2026
Pavel Samsonov argues that treating an AI model as a colleague lets people hand over work nobody has checked, and that whoever hands it over stays responsible for it.
Company story · roles · agents
21 Sep 2026
GitHub Blog
Should you read the code, is RAG dead, and did Skills kill MCP?
GPS (@madebygps) · 18 September 2026
A GitHub developer advocate argues that people must still review code written by AI, with effort matched to the risk, until they can explain and own the result.
Company story · critique & review
21 Sep 2026
DataHub
What Shipping an AI Agent to 16,000 People Taught Me About Reviewing One
Ananya Das · 17 September 2026
Ananya Das, an intern at DataHub, tested a support agent before its release and found that an unchecked human review had made the agent look worse than it was.
Company story · critique & review
18 Sep 2026
The Pragmatic Engineer
Inside OpenAI's agentic software factory
Gergely Orosz · 15 September 2026
Gergely Orosz describes how OpenAI builds software with its coding agent Codex: people define the problem, agents write and review the code, and high-risk changes can require a person's review.
Company story · agents
17 Sep 2026
Vercel
How Delphi ships 100 times a day with its Python backend on Vercel
Susan Aziz and Kevin Sundstrom · 15 September 2026
Delphi, a company with ten engineers, ships to production over 100 times a day and first sees its AI agents' work on live preview links, according to Vercel.
Company story · prototyping
17 Sep 2026
Nielsen Norman Group
AI Can Help Write an Article, but It Can't Stand Behind It
Raluca Budiu · 11 September 2026
Raluca Budiu, an editor at Nielsen Norman Group, explains that the firm uses AI to write and critique articles, but only a human expert decides whether it publishes them.
Company story · critique & review
16 Sep 2026