# Addy Osmani Addy Osmani is an engineering and evangelism leader who spent over 14 years at Google leading developer experience across Chrome and, in recent years, AI (Gemini, coding agents, and agentic engineering), most recently as a Director at Google Cloud AI. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Human judgment doesn't leave the software factory. It relocates. DevFeed: [Human judgment doesn't leave the software factory. It relocates.]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-21T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Software](), [coding](), [event driven](), [implementation](), [GitHub](), [Claude Code](), [codex]() Tags: [agent](), [architecture](), [automated](), [batch](), [build](), [claude-code](), [codex](), [event-driven](), [github](), [linear](), [maintainability](), [mutation-testing](), [pull-requests](), [quality](), [scanners](), [slack](), [software](), [testing](), [verification]() ### AI overview A field guide to building a repeatable software factory while keeping humans responsible for product intent, system design, quality standards, code review, and final merge decisions. It recommends early and continuous quality checks, deliberate constraints, and event-driven automation when ordinary coding workflows are no longer sufficient. ### Source excerpt A field guide to building a software factory that still has an owner. ## Practical Loop Engineering DevFeed: [Practical Loop Engineering]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-14T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Loop Engineering](), [AI Agent](), [Claude Code](), [codex](), [Bash]() Tags: [agent](), [agents](), [ai](), [ai-agent](), [bash](), [claude-code](), [code-review](), [codex](), [complexity](), [engineering](), [loops](), [workflows]() ### AI overview The article explains loop engineering as an autonomous, self-correcting feedback cycle in which an AI agent acts, tests results, and adjusts its approach toward a defined goal. It discusses Claude Code and Codex primitives, earlier Bash-based loops, and the need to define goals and constraints carefully before delegating work, especially in complex or high-risk codebases. ### Source excerpt Goals, loops, and the discipline of not delegating your judgment ## Agentic Code Quality DevFeed: [Agentic Code Quality]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-08-08T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Code quality](), [Testing](), [mutation-testing](), [engineering-culture]() Tags: [code-quality](), [mutation-testing](), [testing](), [tests](), [time]() ### AI overview The article argues that code quality for agent-generated software depends on quality gates and deterministic constraints enforced through the surrounding harness, environment, and operating system. It discusses unit, property, acceptance, and mutation testing, along with code-quality metrics and checks on the scope and safety of proposed changes. ### Source excerpt Quality now depends on the constraints you set around your agents. ## Software Factories, Light and Dark DevFeed: [Software Factories, Light and Dark]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-20T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Loop Engineering](), [Software](), [Artificial Intelligence]() Tags: [agentic](), [agents](), [ai](), [build](), [code](), [loops](), [software]() ### AI overview The article revisits the idea of software factories as repeatable, instrumentable production systems and describes light and dark factories based on how much human oversight they retain. It presents loop engineering as the design of agentic systems that repeatedly gather context, act, check results, and continue until a condition is met, with harnesses providing tools, memory, sandboxes, and completion gates. ### Source excerpt A software factory is harnessing loops at scale - the system that builds your software instead of you. You can run the loop with humans in it (light factory) or you can ignore the humans (dark factory) and let those agents scope, build and ship code, without anyone really reading the details. But if people stop reading, they'll stop understanding your software. Your hardest job now is knowing which checks to build and how much autonomy to delegate. ## Owning Accountability for Agentic Engineering Systems DevFeed: [Owning Accountability for Agentic Engineering Systems]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-15T00:00:00Z Content type: opinion Language: en Sources: [Addy Osmani]() Topics: [Artificial Intelligence](), [trust](), [implementation](), [coding]() Tags: [agentic-engineering](), [agents](), [delegation](), [quality](), [trust](), [verification]() ### AI overview This commentary argues that engineers must own the accountability boundary around agentic engineering systems. It defines quality as pre-release checks, verdict as the human production decision, and answerability as the ability to explain why a decision was made. It presents agents as models combined with harnesses and repeatable investigate-implement-verify cycles, with humans retaining responsibility for decisions at the boundary. ### Source excerpt Engineers need to own the outer loop, the accountability for these systems. A written version of my AI Engineer World's Fair 2026 closing keynote: quality, verdict, and answerability, the three hidden costs of delegation, and building software factories you can stand behind. ## Earning taste and judgment DevFeed: [Earning taste and judgment]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-14T00:00:00Z Content type: opinion Language: en Sources: [Addy Osmani]() Topics: [Artificial Intelligence](), [coding](), [Code]() Tags: [ai](), [developer](), [junior](), [junior-developer](), [microsoft](), [race-condition]() ### AI overview An opinionated analysis argues that AI coding agents automate the repetitive work through which junior developers traditionally developed taste and judgment, weakening the path from entry-level to senior roles. It discusses labor-market evidence and suggests that choosing what to build and evaluating its quality are increasingly durable skills. ### Source excerpt Taste used to be a byproduct of the reps. Agents took the reps. So if you're junior you now have to go get the taste and judgment on purpose. A builder's look at the weakening entry level, the two debts we now owe, and concrete ways to build judgment when the machine writes the code. ## Career Advice for Engineers in the Age of AI Agents DevFeed: [Career Advice for Engineers in the Age of AI Agents]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-06T00:00:00Z Content type: opinion Language: en Sources: [Addy Osmani]() Topics: [Artificial Intelligence](), [agentic-coding](), [Vibe coding](), [coding](), [LeetCode]() Tags: [agentic-coding](), [ai](), [career](), [coding](), [job](), [vibe-coding]() ### AI overview This commentary argues that AI will make answer-based problem solving and routine software shipping cheaper, while durable career advantages will come from choosing worthwhile problems, building systems, understanding people, judging quality, and developing a strong reputation and relationships. ### Source excerpt AI gets good at anything with an answer key. Your career is everything that doesn't have one. ## Agentic Autonomy Levels DevFeed: [Agentic Autonomy Levels]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-07-02T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [Artificial Intelligence](), [Orchestration](), [Agent Skill]() Tags: [agentic](), [agentic-engineering](), [ai](), [delegation](), [multi-agent](), [orchestration](), [scale](), [scopes](), [trust](), [verification]() ### AI overview The article argues that agent autonomy should be evaluated on two separate axes: agency, describing how independently an agent pursues a goal, and orchestration, describing the ability to coordinate multiple agents. It emphasizes choosing an autonomy level per task and defending that choice through verification. ### Source excerpt The action in agentic engineering has moved from prompting to operating. Autonomy isn't one ladder, it's two axes (agency and orchestration) and six levels you move between per task. The real question is what level a task deserves, and what verification makes that level defensible. ## How AI and Vibe Coding Are Changing the Software Development Lifecycle DevFeed: [How AI and Vibe Coding Are Changing the Software Development Lifecycle]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-06-16T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [sdlc](), [Vibe coding](), [Artificial Intelligence](), [Code]() Tags: [agent](), [ai](), [engineering](), [google](), [sdlc](), [vibe-coding]() ### AI overview This developer article highlights ideas from a Google whitepaper about AI's impact on the software development lifecycle. It argues that an agent consists of a model plus a larger harness of instructions, tools, sandboxes, orchestration, hooks, and observability, and that many agent failures are configuration failures rather than model failures. It also introduces context engineering as an important part of the system. ### Source excerpt I co-wrote a Google whitepaper about how AI is changing the software lifecycle. I'm not going to summarize the whole thing. Instead, here are the handful of ideas in it I think actually matter, plus six figures you're welcome to reuse. ## Agentic Code Review DevFeed: [Agentic Code Review]() Original publisher: [Read original article]() Author: Addy Osmani Published: 2026-06-15T00:00:00Z Content type: article Language: en Sources: [Addy Osmani]() Topics: [agentic code review](), [Code review](), [AI-assisted coding](), [Claude Code](), [codex]() Tags: [agentic](), [agentic-code-review](), [ai](), [claude-code](), [code-review](), [codex](), [queue]() ### AI overview This article argues that coding agents have shifted the main engineering constraint from writing code to deciding whether generated changes are trustworthy. It presents code review as increasingly important and describes using Claude Code and Codex to triage batches of incoming pull requests. ### Source excerpt Coding agents are extraordinarily good now, and getting better fast. The interesting consequence is that the hard part of engineering moved from writing code to deciding whether to trust it, which makes review the most leveraged skill in software right now. How you approach it depends enormously on who you are: a solo developer with no users and a team maintaining a ten-year-old application are not solving the same problem.