# quality Published articles for quality. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Kacey Musgraves' Quest Concert Shows How Good Immersive Music Can Be DevFeed: [Kacey Musgraves' Quest Concert Shows How Good Immersive Music Can Be]() Original publisher: [Read original article]() Author: Craig Storm Published: 2026-09-16T21:26:59Z Content type: opinion Language: en Sources: [UploadVR]() Topics: [3D](), [Meta]() Tags: [3d](), [4k](), [audio](), [camera](), [cameras](), [immersive-video](), [lighting](), [meta](), [music](), [production](), [quality](), [wi-fi]() ### AI overview A review of Kacey Musgraves: Middle of Nowhere, a 49-minute made-for-VR concert filmed at Billy Bob's Texas for Quest 3. The reviewer finds its stereoscopic 3D presentation immersive and natural, with clear visuals over hotel Wi-Fi and strong audio. ### Source excerpt We had to stop ourselves from applauding. Kacey Musgraves' new made-for-VR concert on Quest 3 shows just how good immersive music can be. ## Priyanka Halder on responsible AI, software quality, and scaling technology strategy DevFeed: [Priyanka Halder on responsible AI, software quality, and scaling technology strategy]() Original publisher: [Read original article]() Author: Rajrupa Roychowdhury Published: 2026-09-16T08:22:04Z Content type: article Language: en Sources: [BrowserStack Blog]() Topics: [Testing](), [AI Engineering](), [Responsibility & Safety](), [AI Strategy](), [legacy]() Tags: [ai-engineering](), [cloud-native](), [engineering](), [icons-of-quality](), [quality](), [responsible-ai](), [software](), [testing]() ### AI overview BrowserStack profiles Priyanka Halder, an engineering executive at Deloitte, discussing responsible AI at scale, software quality, buy-versus-build decisions, and the skills needed to create scalable solutions with measurable business value. ### Source excerpt To celebrate the relentless passion and invaluable contributions of leaders in software quality, BrowserStack is proud to Icons of Quality. ## Honoring #IconsOfQuality: Huib Schoots DevFeed: [Honoring #IconsOfQuality: Huib Schoots]() Original publisher: [Read original article]() Author: Rajrupa Roychowdhury Published: 2026-09-16T08:21:48Z Content type: article Language: en Sources: [BrowserStack Blog]() Topics: [Testing](), [Software Testing](), [Artificial Intelligence](), [Software Engineering]() Tags: [ai](), [icons-of-quality](), [quality](), [software-testing](), [thought-leadership]() ### AI overview An interview with Huib Schoots explores software testing as a thinking activity centered on questioning assumptions, exploring risks, and helping teams make better decisions. Schoots also discusses using AI to support testing while preserving human judgment. ### Source excerpt To celebrate the relentless passion and invaluable contributions of leaders in software quality, BrowserStack is proud to honour Icons of Quality. ## Honoring #IconsOfQuality: Pricilla Bilavendran DevFeed: [Honoring #IconsOfQuality: Pricilla Bilavendran]() Original publisher: [Read original article]() Author: Rajrupa Roychowdhury Published: 2026-09-16T08:21:09Z Content type: article Language: en Sources: [BrowserStack Blog]() Topics: [Testing](), [Test automation](), [Artificial Intelligence](), [Playwright](), [Postman](), [Amazon Machine Learning]() Tags: [ai](), [api-testing](), [community](), [icons-of-quality](), [playwright](), [postman](), [quality](), [test-automation](), [testing]() ### AI overview BrowserStack profiles Pricilla Bilavendran, a quality engineering and API testing leader, and discusses her views on AI-assisted quality engineering, human curiosity, critical thinking, and the continuing importance of testers' judgment. ### Source excerpt To celebrate the relentless passion and invaluable contributions of leaders in software quality, BrowserStack is proud to honour Icons of Quality. ## Honoring #IconsOfQuality: Mark Hrynczak DevFeed: [Honoring #IconsOfQuality: Mark Hrynczak]() Original publisher: [Read original article]() Author: Rajrupa Roychowdhury Published: 2026-09-16T08:20:52Z Content type: opinion Language: en Sources: [BrowserStack Blog]() Topics: [Testing](), [Loop Engineering](), [Artificial Intelligence](), [site-reliability-engineering](), [Amazon Web Services](), [atlassian]() Tags: [agentic](), [ai](), [atlassian](), [aws](), [icons-of-quality](), [quality](), [sre](), [testing](), [tooling]() ### AI overview BrowserStack profiles Mark Hrynczak, Canva's Head of Quality and QA Director, discussing how distributed quality ownership, agentic testing, and AI-driven decision support can help engineering teams move faster while maintaining reliability. ### Source excerpt To celebrate the relentless passion and invaluable contributions of leaders in software quality, BrowserStack is proud to honour Icons of Quality. ## Building the new GitHub Copilot Inline Suggestions Model: Part One DevFeed: [Building the new GitHub Copilot Inline Suggestions Model: Part One]() Original publisher: [Read original article]() Author: Julia Gong, Ben Liggett, Ulugbek Abdullaev Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Visual Studio Code - Code Editing. Redefined.]() Topics: [GitHub Copilot](), [AI-assisted coding](), [coding](), [Development](), [GitHub](), [Software Engineering]() Tags: [agent](), [ai-assisted-coding](), [blog](), [coding](), [github](), [github-copilot](), [quality](), [vs-code](), [workflows]() ### AI overview GitHub Copilot unified completion-style ghost text, nearby next edit suggestions, and long-distance edits into a single "3-in-1" model. The article explains that training, evaluation, and editor design evolved together, and that the unified model can improve suggestion selection and cache additional edits for faster subsequent interactions. ### Source excerpt Explore how GitHub Copilot unified completion, next edit, and long-distance suggestions into one model for a faster, more cohesive coding experience. Read the full article ## Beyond the model: Engineering AI infra with scientific judgement DevFeed: [Beyond the model: Engineering AI infra with scientific judgement]() Original publisher: [Read original article]() Author: AirbnbEng Published: 2026-09-15T17:06:18Z Content type: article Language: en Sources: [The Airbnb Tech Blog - Medium]() Topics: [Agent Harness](), [AI Agent](), [Data Science](), [data](), [datasets](), [Large Language Model]() Tags: [agent-harness](), [ai](), [ai-agent](), [data](), [data-science](), [datasets](), [engineering](), [llms](), [quality](), [science](), [trust]() ### AI overview Airbnb describes an agent harness for data science that embeds scientific methodology around an AI model. The system guides agents through framing questions, selecting evidence, and recording decisions so unstructured-data investigations can be reproduced, audited, challenged, and extended across languages, geographies, and LLM-based products. ### Source excerpt How Airbnb's agent harness transforms unstructured data exploration by encoding scientific methodology into scalable, reproducible, and audit-ready infrastructure. By: Wren Dougherty Ask a coding agent to analyze 100,000 customer support conversations and within minutes you'll have a polished taxonomy, precise prevalence numbers, and an executive-ready summary. What you can't see is the investigation that produced them: the methods it chose, the evidence it weighed, how much to trust it, or whether a second request would agree. All that reaches you is the polish. The model is undeniably intelligent, but intelligence without methodology is not science. LLMs certainly make for confident scientists, but we need them to be responsible ones. Smarter models help, but intelligence has never been the whole of science, in people or in machines. The method is as much the product as the answer. That is the idea behind the agent harness we built for data science: the methodology itself, built as infrastructure around the model. It governs how an AI agent operates, from framing a question to selecting evidence to recording decisions, so results can be reproduced, audited, and challenged, and the method shared, inspected, and built on. The challenge of unstructured data exploration In 2025, Airbnb was preparing to launch an AI customer service assistant. Before it could ship, we needed to understand exactly what kinds of situations it would face in the real world. That included rare events that could be risky for AI to interact with, and involved examining their taxonomy and prevalence to create the datasets that would help us build a more responsible product. The investigative work to do this was rigorous, but the process was deeply artisanal. Months of high-touch iteration went into each investigation, from finding the right data, reviewing samples with experts, and generating representative datasets, and the method was manually curated across notebooks, tables, docs, and indiv ## Honoring #IconsOfQuality: Gaurav Singh DevFeed: [Honoring #IconsOfQuality: Gaurav Singh]() Original publisher: [Read original article]() Author: Rajrupa Roychowdhury Published: 2026-09-15T11:29:38Z Content type: article Language: en Sources: [BrowserStack Blog]() Topics: [Software Testing](), [Test automation](), [Microsoft](), [Microsoft Teams](), [CI/CD](), [Meta](), [Artificial Intelligence]() Tags: [ai-agents](), [ci-cd](), [icons-of-quality](), [microsoft](), [microsoft-teams](), [quality](), [software-testing](), [test-automation]() ### AI overview BrowserStack profiles Gaurav Singh, a Senior Software Engineer at Microsoft, as an Icon of Quality. The article highlights his work on scalable engineering systems, testing infrastructure, CI/CD pipelines, developer productivity, mentorship, and the role of determinism and feedback loops in automated testing. ### Source excerpt To celebrate the relentless passion and invaluable contributions of leaders in software quality, BrowserStack is proud to honour Icons of Quality. ## Mintlify rebuilds automations around pre-built templates for common use cases DevFeed: [Mintlify rebuilds automations around pre-built templates for common use cases]() Original publisher: [Read original article]() Author: Patrick Foster Published: 2026-09-15T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Automation](), [Documentation](), [changelog](), [Pull Request](), [Markdown](), [YAML]() Tags: [announcements](), [automation](), [changelog](), [docs](), [documentation](), [execution](), [markdown](), [prompt](), [quality](), [rest]() ### AI overview Mintlify rebuilt its automations around pre-built templates for common use cases, including syncing content with code changes, generating changelogs, and improving documentation from user feedback and support signals. Custom prompts remain available for specialized tasks. ### Source excerpt We redesigned automations for quicker setup with pre-built automations optimized for common use cases. Choose the right automations for your project and you're set. No context engineering required. ## Use AI to Accelerate Delivery Without Lowering Software Quality DevFeed: [Use AI to Accelerate Delivery Without Lowering Software Quality]() Original publisher: [Read original article]() Author: Fran Soto Published: 2026-09-13T04:01:35Z Content type: opinion Language: en Sources: [Strategize Your Career]() Topics: [Software](), [Artificial Intelligence](), [coding](), [context]() Tags: [accelerate](), [ai](), [context](), [quality](), [software]() ### AI overview An opinion piece arguing that AI should speed delivery without reducing software-quality standards, using engineering judgment as scalable context, constraints, and checks. ### Source excerpt AI should accelerate delivery, not lower your standards. Turn engineering judgment into context, constraints, and checks that scale ## Temporally stable generative illumination with a one-step diffusion model DevFeed: [Temporally stable generative illumination with a one-step diffusion model]() Original publisher: [Read original article]() Author: SungYe Kim; Harish Anand; Alexandr Kuznetsov; Wojciech Uss; Wojciech Kaliński; Rama Harihara Published: 2026-09-09T13:00:00Z Content type: article Language: en Sources: [AMD GPUOpen]() Topics: [real-time rendering](), [VAE]() Tags: [arr-group](), [article-release](), [diffusion](), [generation](), [gi](), [inference](), [lighting](), [ml](), [model](), [optimization](), [quality](), [ray-tracing](), [raytracing](), [real-time](), [real-time-rendering](), [research](), [white-paper]() ### AI overview The article presents a single-step latent diffusion method for real-time global illumination. It conditions image generation on scene signals and lighting hints, and uses a Temporal VAE decoder with motion-vector reprojection to improve temporal stability and reduce flicker. ### Source excerpt A generative method for real-time global illumination using a single-step latent diffusion model, delivering stable, high-quality lighting without costly iterative processing. ## Catch AI Regressions Before They Ship with AI Evals in CI/CD DevFeed: [Catch AI Regressions Before They Ship with AI Evals in CI/CD]() Original publisher: [Read original article]() Author: Shibam Dhar Published: 2026-09-02T00:00:00Z Content type: article Language: en Sources: [Harness Blog]() Topics: [AI Agent](), [CI/CD](), [Testing](), [AI Development]() Tags: [agent](), [ai](), [ai-agent](), [ai-evals](), [ci-cd](), [datasets](), [production](), [quality](), [tests]() ### AI overview Harness AI Evals uses golden datasets, response-quality metrics, and blocking quality gates in CI/CD to catch AI agent regressions before production. In an e-commerce support-agent test, an early run passed about 65% of cases, below the 70% deployment threshold, revealing incorrect, missing, or incomplete answers. ### Source excerpt Harness AI Evals tests AI agent quality in CI/CD, using golden datasets and quality gates to catch behavioral regressions before production. | Blog ## Data Engineering Weekly #285 DevFeed: [Data Engineering Weekly #285]() Original publisher: [Read original article]() Author: Ananth Packkildurai Published: 2026-08-31T02:51:19Z Content type: article Language: en Sources: [Data Engineering Weekly]() Topics: [data-engineering](), [AI, ML & Data Engineering](), [Data Quality](), [observability](), [Artificial Intelligence]() Tags: [agentic-ai](), [automated](), [data-engineering](), [newsletter](), [observability](), [privacy](), [python](), [quality](), [recovery](), [weekly]() ### AI overview Data Engineering Weekly #285 covers building data platforms, AI chip architectures, preparing data for agentic AI, post-AI data stacks, data modernization, automated data contract breach handling, and privacy-preserving measurement tools. ### Source excerpt The Weekly Data Engineering Newsletter ## CircleCI Smarter Testing: Stop running tests that don't matter DevFeed: [CircleCI Smarter Testing: Stop running tests that don't matter]() Original publisher: [Read original article]() Author: Nathan Fish Published: 2026-08-26T19:00:00Z Content type: article Language: en Sources: [The CircleCI Blog Feed | CircleCI]() Topics: [Testing](), [CI/CD]() Tags: [accelerate](), [auto-rerun-failed-tests](), [ci-cd](), [circleci](), [circleci-news](), [developer-productivity](), [dynamic-test-splitting](), [engineering-productivity](), [flaky](), [intelligent-test-selection](), [parallel](), [pipeline](), [quality](), [reduce](), [smarter-testing](), [test-impact-analysis](), [testing](), [tests](), [time]() ### AI overview CircleCI describes Smarter Testing, a set of features designed to reduce CI/CD test execution time by skipping tests unaffected by changes, balancing parallel nodes, and retrying flaky tests. The article says early users have seen test runs up to four times faster. ### Source excerpt Testing eats up to half your pipeline time. See how CircleCI Smarter Testing skips unaffected tests, rebalances parallel nodes, and retries flaky tests. ## 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: 2026-08-21T14:31:12Z Content type: article Language: en Sources: [Elevate]() Topics: [Software](), [Testing](), [event driven](), [Architecture & Design](), [GitHub](), [pull-requests](), [mutation-testing](), [Security]() Tags: [agent](), [architecture](), [claude-code](), [codex](), [event-driven](), [github](), [mutation-testing](), [pull-requests](), [quality](), [security](), [software](), [testing]() ### AI overview This field guide explains how to build a repeatable software factory while preserving human judgment and ownership. It recommends human involvement in product intent, system design, quality standards, code review, and merge decisions, supported by automated checks and deliberate experimentation. The article argues that a factory is most useful when work must be repeatable and event-driven across queues such as GitHub issues, Slack, Linear, or a backlog. ### Source excerpt A field guide to building a software factory that still has an owner. ## 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. ## Want to use AI agents safely? Start with design DevFeed: [Want to use AI agents safely? Start with design]() Original publisher: [Read original article]() Author: Colin Eberhardt Published: 2026-08-18T13:12:00Z Content type: opinion Language: en Sources: [Scott Logic]() Topics: [Artificial Intelligence](), [AI Strategy](), [Security](), [Monitoring](), [Architecture & Design](), [Resilience]() Tags: [agentic-ai](), [agents](), [ai](), [artificial-intelligence](), [auditability](), [design](), [end-to-end-process](), [featured](), [governance](), [guardrails](), [monitoring](), [observability](), [operational-resilience](), [quality](), [risk-management](), [security](), [service-design](), [systems](), [trust]() ### AI overview This article argues that organisations adopting AI agents should begin with process and system design rather than controls alone. It explains that design should account for human and machine strengths, establish proportionate guardrails, and define how observability and monitoring evolve as the system matures. ### Source excerpt Concerns about control are one of the biggest barriers to adopting agentic AI, particularly in regulated environments. In this post, we discuss how organisations can harness AI safely by designing processes around the strengths of both humans and machines, then applying the right controls, guardrails and monitoring. ## Beyond Relevance: Building a Quality-Aware Retrieval Layer for RAG DevFeed: [Beyond Relevance: Building a Quality-Aware Retrieval Layer for RAG]() Original publisher: [Read original article]() Author: Shay Ben-Elazar Published: 2026-08-18T07:16:01Z Content type: article Language: en Sources: [Data Science at Microsoft]() Topics: [Retrieval Augmented Generation (RAG)](), [Large Language Model](), [Artificial Intelligence]() Tags: [ai](), [data-science](), [education](), [machine-learning](), [microsoft](), [quality](), [rag](), [retrieval]() ### AI overview The article examines how a metadata-aware quality layer could improve educational RAG systems by ranking or filtering retrieved sources for reliability, clarity, evidence, and suitability for teaching. It argues that relevance alone does not ensure educational quality and that filtering weak sources can also reduce context noise, token use, and inference costs. ### Source excerpt How a metadata-aware quality layer can help educational RAG systems retrieve sources that are relevant, reliable, and ready for teaching Shay Ben-Elazar, Principal Applied Data Science Manager, Microsoft Rob Mauceri, Distinguished Engineer, Microsoft A student asks an AI tutor a science question: "Why do flu vaccines need to be updated over time?" A retrieval-augmented generation (RAG) system searches its index, retrieves passages about influenza viruses, vaccine development, immunity, and seasonal outbreaks, then generates an answer grounded in those sources [1]. At first glance, the system appears to have done its job. The passages are relevant, and the answer cites supporting information. But a deeper question remains: were the retrieved sources actually good sources to learn from? Some passages may be outdated, overly technical, weakly supported, or poorly organized for a student audience. Others may provide clearer explanations, stronger evidence, and a more coherent path to understanding. Both may be relevant, yet only one is likely to help a learner build accurate understanding [2]. This distinction matters because relevance alone is not the same as educational quality. Retrieved passages can match the topic while lacking clear definitions, supporting evidence, or an easy-to-follow explanation. In a student-facing product, those differences shape not only what the student learns, but also how much they trust the system. There is also a practical systems reason to care. Web-scale RAG applications operate within limited context windows and real compute budgets. Filtering weak sources earlier, or downranking them before generation, reduces noise, preserves tokens for stronger evidence, and lowers inference costs, compounding across products used by millions of learners [3]. RAG has become one of the most practical ways to make large language model applications more grounded. It can make answers more current, more domain-specific, and easier to connect back to so ## AI success depends on data foundations DevFeed: [AI success depends on data foundations]() Original publisher: [Read original article]() Author: James Heward Published: 2026-08-14T14:19:00Z Content type: article Language: en Sources: [Scott Logic]() Topics: [data-architecture](), [AI Strategy](), [AI Development]() Tags: [agentic-ai](), [ai](), [ai-readiness](), [artificial-intelligence](), [data](), [data-engineering](), [governance](), [integration](), [legacy-it](), [legacy-modernisation](), [prototypes](), [quality](), [silos]() ### AI overview Strong data foundations--discoverable, high-quality, accessible, governed, and integrated--are presented as essential for reliable AI outcomes, especially as organisations adopt more autonomous agentic systems. ### Source excerpt As organisations invest in AI, many discover that their biggest challenges are not AI-related at all. In this post, I explore why strong data foundations, from quality and accessibility to governance and integration, are essential for turning AI ambition into reliable, production-ready outcomes. ## Sentry's Greg Pstrucha on why a better prompt won't fix your agent's code DevFeed: [Sentry's Greg Pstrucha on why a better prompt won't fix your agent's code]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-06T00:04:02Z Content type: opinion Language: en Sources: [WorkOS Blog]() Topics: [Artificial Intelligence](), [Tooling](), [coding](), [Software](), [Large Language Model]() Tags: [agent](), [agents](), [ai](), [ai-engineer](), [code](), [evals](), [metrics](), [quality](), [sentry](), [software](), [software-engineer](), [test](), [tests](), [tooling]() ### AI overview Sentry staff engineer Greg Pstrucha argues that improving AI-generated code requires more than better prompts. In his discussion of the "Stop Prompting" talk, he recommends linters, strong tests, type systems, frameworks, and skills as baseline safeguards, supplemented by evaluations for harder-to-codify quality judgments. ### Source excerpt Sentry staff engineer Greg Pstrucha on linters, stronger tests, evals for Seer, and the quality metrics agents game -- from AI Engineer World's Fair 2026. ## How Do You Test an AI Agent? A Look at Harness AI Evals DevFeed: [How Do You Test an AI Agent? A Look at Harness AI Evals]() Original publisher: [Read original article]() Author: Shibam Dhar Uri Scheiner Published: 2026-08-05T00:00:00Z Content type: tutorial Language: en Sources: [Harness Blog]() Topics: [AI Agent](), [Testing](), [Artificial Intelligence](), [SDK](), [Deployment]() Tags: [ai](), [ai-agent](), [deployment](), [open-source](), [prompt-injection](), [quality](), [sdk](), [test]() ### AI overview This article explains how Harness AI Evals tests non-deterministic AI agents before and after deployment. It describes shared metrics and datasets for offline and online evaluation, an open-source evaluation SDK, configurable quality thresholds, and release-pipeline quality gates that help detect regressions before shipping. ### Source excerpt From defining quality to catching regressions: how Harness AI Evals scores AI agents before and after deployment. | Blog ## Why Readiness Should Be a Habit, Not a Final Gate DevFeed: [Why Readiness Should Be a Habit, Not a Final Gate]() Original publisher: [Read original article]() Author: Dean Hume Published: 2026-08-03T08:41:00Z Content type: opinion Language: en Sources: [Dean Hume]() Topics: [Testing](), [Software](), [systems](), [bug](), [Network](), [API]() Tags: [api](), [bug](), [game-development](), [habits](), [launches](), [network](), [quality](), [teams](), [technical-leadership](), [technical-program-manager](), [testing]() ### AI overview The article argues that software quality is established through everyday team habits rather than a final testing phase. It emphasizes defining expected behavior for interruptions and failures early, instead of labeling unspecified behavior as bugs during release pressure. ### Source excerpt Quality isn't decided in the final review. The teams with the smoothest launches built it through daily habits, long before anyone thought about a release date. ## Harness AI Evals adds CI/CD quality gates for testing and monitoring AI agents DevFeed: [Harness AI Evals adds CI/CD quality gates for testing and monitoring AI agents]() Original publisher: [Read original article]() Author: Shibam Dhar Uri Scheiner Published: 2026-07-21T00:00:00Z Content type: release Language: en Sources: [Harness Blog]() Topics: [Artificial Intelligence](), [CI/CD]() Tags: [agents](), [ai](), [ai-agents](), [ai-evals](), [ci-cd](), [evals](), [monitor](), [production](), [quality](), [releases](), [test]() ### AI overview Harness introduces AI Evals, a tool for testing, scoring, and monitoring AI agents before and after deployment. It provides a native CI/CD pipeline step, evaluation metrics, and blocking or advisory pass strategies intended to prevent poor releases from reaching production. ### Source excerpt Harness AI Evals helps you test, score, and monitor AI agents with native CI/CD quality gates, blocking poor releases before production. | Blog ## ChatGPT Live and the New Architecture of Voice AI DevFeed: [ChatGPT Live and the New Architecture of Voice AI]() Original publisher: [Read original article]() Author: RisingStack Engineering Published: 2026-07-16T12:38:22Z Content type: article Language: en Sources: [RisingStack]() Topics: [voice ai](), [Artificial Intelligence](), [ChatGPT](), [OpenAI](), [systems]() Tags: [ai](), [architecture](), [audio](), [chatgpt](), [engineering](), [gpt](), [here](), [interrupt](), [messages](), [models](), [openai](), [quality](), [speaking](), [speech](), [systems](), [talk](), [tool](), [update](), [voice-ai](), [voices]() ### AI overview The article explains how OpenAI's GPT-Live models power ChatGPT Voice through a full-duplex architecture. The system can listen and speak simultaneously, handle interruptions, pause while users think, and delegate deeper reasoning, web search, or other complex work to another model. ### Source excerpt OpenAI has introduced GPT-Live, a new generation of voice models that now powers ChatGPT Voice. At first, this may sound like another voice-quality update. The voices have been remastered, ChatGPT should interrupt less often, and it can respond more naturally when you pause, change direction or speak over it. But GPT-Live is more than a [...] The post ChatGPT Live and the New Architecture of Voice AI appeared first on RisingStack Engineering. [Next page]()