# AI Engineering Published articles for AI Engineering. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Why human oversight is shifting from writing code to defining requirements DevFeed: [Why human oversight is shifting from writing code to defining requirements]() Original publisher: [Read original article]() Author: Naseeb Ahmed Mian Published: 2026-09-17T13:00:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [Requirements](), [AI Agent](), [Code](), [Availability]() Tags: [agent](), [agents](), [ai-agents](), [ai-engineering](), [andela](), [automated](), [availability](), [code](), [pipeline](), [post-contributed](), [requirements](), [review](), [software-development](), [sponsor-andela](), [sponsored-post-contributed](), [tests]() ### AI overview The article argues that human oversight of AI-assisted software development should focus on defining and reviewing requirements, not only checking whether generated code conforms to them. It illustrates the risk with a flawed availability-related requirement that passed specification review, generated six passing tests, traceability checks, and automated QA while violating the feature's intended outcome. ### Source excerpt This walks through the pipeline our agents operate inside--from a recorded scoping meeting through unit specs, spec review, generated code, The post Why human oversight is shifting from writing code to defining requirements appeared first on The New Stack. ## The Future of Data Engineering in the Age of AI | Erfan Hesami DevFeed: [The Future of Data Engineering in the Age of AI | Erfan Hesami]() Original publisher: [Read original article]() Author: Daniel Beach Published: 2026-09-16T13:21:19Z Content type: article Language: en Sources: [Data Engineering Central]() Topics: [data-engineering](), [AI Engineering](), [agent observability](), [coding](), [Security]() Tags: [agents](), [ai](), [ai-agents](), [ai-engineering](), [coding](), [data-engineering](), [fundamentals](), [governance](), [security]() ### AI overview An interview with Erfan Hesami examines how AI and agents may change data engineering, including the evolving role of data engineers, the overlap with AI engineering, the continuing importance of fundamentals, and the need to manage governance, security, costs, technical debt, and human judgment. ### Source excerpt AI Agents, Coding & Fundamentals ## 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. ## Google and OpenAI take different approaches to reducing voice-agent latency DevFeed: [Google and OpenAI take different approaches to reducing voice-agent latency]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-15T21:50:15Z Content type: comparison Language: en Sources: [The New Stack]() Topics: [Latency](), [Google AI](), [OpenAI](), [API](), [Orchestration](), [real-time](), [Artificial Intelligence]() Tags: [ai](), [ai-agents](), [ai-engineering](), [api](), [comparison](), [google-ai](), [large-language-models](), [latency](), [openai](), [orchestration](), [real-time]() ### AI overview The article compares Google's Gemini 3.8 Live Extended Thinking with OpenAI's GPT-Live-1 for reducing latency in voice agents. Google keeps speech, reasoning, and asynchronous tool execution in one stateful session, while OpenAI uses a real-time conversation model alongside a backend reasoning model, shifting more orchestration to the application. ### Source excerpt Voice agents have a latency problem that shows up as soon as they have to do real work. Within five The post OpenAI's voice model doesn't think. That's the point. appeared first on The New Stack. ## AWS agents will suggest your new flights. Code decides what gets booked. DevFeed: [AWS agents will suggest your new flights. Code decides what gets booked.]() Original publisher: [Read original article]() Author: Meredith Shubel Published: 2026-09-15T21:27:21Z Content type: news Language: en Sources: [The New Stack]() Topics: [AWS Step Functions](), [Amazon Bedrock AgentCore](), [Orchestration](), [Generative AI](), [Amazon Web Services]() Tags: [ai-agents](), [ai-engineering](), [airline](), [amazon-bedrock-agentcore](), [aws](), [aws-step-functions](), [cloud-services](), [generative-ai](), [orchestration]() ### AI overview AWS published a Step Functions pattern for airline rebooking in which Amazon Bedrock AgentCore agents propose itineraries and compensation messages, while deterministic workflow steps validate proposals before reservations change or payments are issued. ### Source excerpt AWS published a new Step Functions pattern this week that gives AI agents a role in airline rebooking while keeping The post AWS agents will suggest your new flights. Code decides what gets booked. appeared first on The New Stack. ## Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions DevFeed: [Bolt.new tests Forge, offering more coding-model usage in exchange for anonymized developer sessions]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-15T18:47:23Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI-assisted coding](), [Training AI Models](), [Open Source Models & Datasets](), [Agent Harness]() Tags: [agent](), [agent-harness](), [ai](), [ai-development](), [ai-engineering](), [ai-models](), [coding-agents](), [data](), [developer-tools](), [developers](), [training]() ### AI overview Bolt.new is testing Forge, a research preview for individual Pro subscribers that offers up to 50 times more usage of open-weight coding models in exchange for opting in to share anonymized coding sessions. The sessions may include prompts, source code, fix traces, and conversations with the coding agent, and will support an Arcee AI project to train a trillion-parameter-class open-weight model. ### Source excerpt Bolt.new, StackBlitz's browser-based AI development platform, is testing a new trade with developers: more coding-model usage in exchange for training The post Bolt is giving developers 50x more compute. But there's a catch. appeared first on The New Stack. ## AI's best coding agent fails 60% of the time -- and the data backs it up DevFeed: [AI's best coding agent fails 60% of the time -- and the data backs it up]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-14T22:22:27Z Content type: news Language: en Sources: [The New Stack]() Topics: [Benchmark](), [AI-assisted coding](), [Fable](), [Claude Code](), [codex](), [Command-line interface](), [anthropic]() Tags: [ai](), [ai-engineering](), [ai-models](), [benchmark](), [benchmarks](), [claude-code](), [cli](), [codex](), [coding](), [fable](), [performance](), [software-testing]() ### AI overview Real-SWE evaluates coding agents on private company codebases and reports substantially lower success rates than public-repository benchmarks. Claude Fable 5.1, running through Claude Code, led the comparison with a 38.8% score, while the tested systems often failed most attempts. ### Source excerpt Claude Fable 5.1 just won a new coding benchmark despite failing more than six out of 10 times. Its 38.8% The post AI's best coding agent fails 60% of the time -- and the data backs it up appeared first on The New Stack. ## Using Exact-Match Response Caching to Reduce LLM Costs DevFeed: [Using Exact-Match Response Caching to Reduce LLM Costs]() Original publisher: [Read original article]() Author: Abhilash Rao Mesala Published: 2026-09-14T11:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Caching](), [Large Language Model]() Tags: [ai-engineering](), [ai-infrastructure](), [caching](), [contributed](), [cost](), [finops](), [generation](), [hash](), [llm](), [token]() ### AI overview The article explains how to reduce LLM costs by fingerprinting requests, context, model settings, and underlying data to create exact-match cache keys. Valid cached responses can be reused without calling the model. It distinguishes response caching from provider prompt caching, where only eligible prompt computation is reused. ### Source excerpt An LLM can answer the same question a thousand times and charge you each time. Before paying for another answer, The post Why an old caching trick is your secret to lower LLM costs appeared first on The New Stack. ## Chip Huyen explains how to cut inference costs without new hardware DevFeed: [Chip Huyen explains how to cut inference costs without new hardware]() Original publisher: [Read original article]() Author: Tim Koopmans Published: 2026-09-13T15:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Inference Performance](), [Low-Latency Inference](), [model-deployment](), [Optimization](), [Frontier Model](), [AI Engineering](), [Latency](), [math]() Tags: [ai](), [ai-agents](), [ai-engineering](), [ai-infrastructure](), [frontier-model](), [inference](), [low-latency](), [metrics](), [optimization](), [performance](), [post-contributed](), [reasoning](), [scylladb](), [sponsor-scylladb](), [sponsored](), [sponsored-post-contributed](), [tokens]() ### AI overview Chip Huyen explains why inference costs can outweigh one-time frontier-model training costs and outlines ways to optimize inference without new hardware. The article emphasizes latency metrics such as time to first token, time per output token, end-to-end latency, and goodput, especially for reasoning models. ### Source excerpt Last October, the P99 conference -- the online gathering for developers focused on high-performance, low-latency applications -- featured a cracking The post Chip Huyen explains how to cut inference costs without new hardware appeared first on The New Stack. ## It passed CI. It passed your evals. The customer still got the wrong answer. DevFeed: [It passed CI. It passed your evals. The customer still got the wrong answer.]() Original publisher: [Read original article]() Author: Sean O'Dell Published: 2026-09-13T14:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI Agent](), [agent observability](), [observability](), [tracing](), [dynatrace](), [ci](), [coding]() Tags: [ai](), [ai-agent](), [ai-agents](), [ai-engineering](), [ci](), [coding](), [dynatrace](), [observability](), [post-contributed](), [sponsor-dynatrace](), [sponsored](), [sponsored-post-contributed](), [traces]() ### AI overview The article explains how AI-agent failures can pass CI and evaluations while still producing slow or incorrect customer-facing results. It presents distributed traces and agent trajectories--model calls, tool calls, arguments, and results--as evidence for debugging retrieval behavior, release context, and feature-flag state. ### Source excerpt A diff is not evidence. It's a statement of intent. The tests passed. The review's done. The change is live. The post It passed CI. It passed your evals. The customer still got the wrong answer. appeared first on The New Stack. ## The AI-native SDLC won't be one process DevFeed: [The AI-native SDLC won't be one process]() Original publisher: [Read original article]() Author: Anirudh Ramanathan Published: 2026-09-12T14:00:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [AI Bots]() Tags: [agents](), [ai](), [ai-engineering](), [anthropic](), [compliance](), [devops](), [dynatrace](), [github](), [kiro](), [platform-engineering](), [post-contributed](), [sdlc](), [signadot](), [spec-driven-development](), [sponsor-dynatrace](), [sponsor-signadot](), [sponsored](), [sponsored-post-contributed]() ### AI overview The article argues that AI-native software development needs risk- and accountability-based process variants rather than one fixed, spec-driven workflow. It emphasizes deterministic policy enforcement, agent self-checks, human approvals, and auditable records. ### Source excerpt Anthropic recently published its AI-Native SDLC Playbook. Its central claim is that "code is no longer the bottleneck." When agents The post The AI-native SDLC won't be one process appeared first on The New Stack. ## Learn Claude Code, evals, AI systems, and more: ByteByteGo Live is here DevFeed: [Learn Claude Code, evals, AI systems, and more: ByteByteGo Live is here]() Original publisher: [Read original article]() Author: ByteByteGo Published: 2026-09-11T15:32:16Z Content type: release Language: en Sources: [ByteByteGo]() Topics: [Artificial Intelligence](), [Claude Code](), [AI Development](), [AI Engineering]() Tags: [ai](), [ai-development](), [ai-engineering](), [ai-evals](), [claude-code](), [development]() ### AI overview ByteByteGo announces ByteByteGo Live, a membership offering live courses on Claude Code, production AI systems, AI engineering, AI evaluations, cost optimization, and related topics. The announcement cites higher completion rates for live cohorts and says the membership covers courses offered over the next 12 months. ### Source excerpt Most online courses never get finished (~4% completion). Live cohorts get ~40%, roughly 10x higher. Live courses are the only courses people actually finish. So we're launching ByteByteGo Live. ## OpenAI split a voice model's brain. Then one team deleted 23,000 lines of code. DevFeed: [OpenAI split a voice model's brain. Then one team deleted 23,000 lines of code.]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-10T20:08:18Z Content type: news Language: en Sources: [The New Stack]() Topics: [Artificial Intelligence]() Tags: [agent](), [agents](), [ai-agents](), [ai-engineering](), [api](), [architecture](), [backend](), [benchmark](), [code](), [event-driven](), [gpt](), [large-language-models](), [openai]() ### AI overview OpenAI launched GPT-Live-1 in its API to give outside developers a full-duplex voice model that can manage live conversation while delegating heavier processing to other backend models. The article describes its interruption handling, conversational filler during handoffs, event-driven delegation, and reported benchmark results. ### Source excerpt Building an AI voice agent has always been clunkier than it seems. Most voice agents are really a chain of The post OpenAI split a voice model's brain. Then one team deleted 23,000 lines of code. appeared first on The New Stack. ## Shopify spent years on React Native -- then rebuilt everything in 12 weeks DevFeed: [Shopify spent years on React Native -- then rebuilt everything in 12 weeks]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-10T19:46:50Z Content type: news Language: en Sources: [The New Stack]() Topics: [AI-assisted coding]() Tags: [ai](), [ai-agents](), [ai-engineering](), [android](), [coding](), [ios](), [llms](), [mobile](), [react-native](), [shopify](), [software-development]() ### AI overview Shopify is moving its consumer mobile app from React Native to fully native development, arguing that improved coding agents and LLMs reduce the cost of platform-specific implementation. The article also cites an AI-assisted JavaScript-runtime port as an example of rapidly changing rewrite economics. ### Source excerpt In 2020, Shopify made a bet that resonated across the developer world by writing mobile code once in React Native The post Shopify spent years on React Native -- then rebuilt everything in 12 weeks appeared first on The New Stack. ## Fable 5.1 vs. Fable 5: Results on a real-world budget, not the spec sheet DevFeed: [Fable 5.1 vs. Fable 5: Results on a real-world budget, not the spec sheet]() Original publisher: [Read original article]() Author: Jessica Wachtel Published: 2026-09-10T14:00:00Z Content type: comparison Language: en Sources: [The New Stack]() Topics: [Claude](), [anthropic](), [Command-line interface]() Tags: [ai-engineering](), [ai-models](), [anthropic](), [benchmark](), [claude](), [claude-code](), [large-language-models](), [science]() ### AI overview The article compares Claude Fable 5.1 and Fable 5 on five Terminal-Bench-Science tasks under a $12, 60-turn limit per test. It contrasts these constrained runs with Anthropic's published benchmark score and higher-cost leaderboard testing. ### Source excerpt When Anthropic launched Claude Fable 5.1 this month, it centered the announcement around one benchmark result: its Terminal-Bench-Science score. In The post Fable 5.1 vs. Fable 5: Results on a real-world budget, not the spec sheet appeared first on The New Stack. ## 47,000 job listings reveal the engineering roles that AI is creating DevFeed: [47,000 job listings reveal the engineering roles that AI is creating]() Original publisher: [Read original article]() Author: Jennifer Riggins Published: 2026-09-10T13:09:28Z Content type: news Language: en Sources: [The New Stack]() Topics: [Machine Learning & Artificial Intelligence](), [AI Development](), [Machine learning]() Tags: [ai](), [ai-engineering](), [ai-strategy](), [andela](), [engineering](), [jobs](), [machine-learning](), [post](), [skills](), [sponsor-andela](), [sponsored](), [sponsored-post](), [tech-careers](), [work]() ### AI overview Andela's analysis of 47,000 Fortune 500 engineering job postings identifies emerging AI-related roles formed by combining established skill sets. The article argues that organizations should use AI to delegate suitable work while retaining human expertise and specialization. ### Source excerpt Every major transformation in tech has led to roles merging, then new ones emerging. Friction between developers and operations drove The post 47,000 job listings reveal the engineering roles that AI is creating appeared first on The New Stack. ## Stop AI code sprawl before it destroys your software design DevFeed: [Stop AI code sprawl before it destroys your software design]() Original publisher: [Read original article]() Author: Emmanuel Akita Published: 2026-09-10T12:30:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [AI-assisted coding](), [CI/CD](), [ci]() Tags: [ai](), [ai-coding](), [ai-engineering](), [andela](), [architecture](), [ci-cd](), [post-contributed](), [python](), [sponsor-andela](), [sponsored-post-contributed](), [testing]() ### AI overview The article argues that AI-generated code can create "Comprehension Debt" by silently violating architectural boundaries. It advocates enforcing architecture through automated tests and CI/CD pipelines rather than relying on documentation and manual review. ### Source excerpt While AI code generators help teams ship faster than ever, that speed brings a hidden killer: Comprehension Debt. As soon The post Stop AI code sprawl before it destroys your software design appeared first on The New Stack. ## Agent Harness vs Platform Harness: Why Teams Need Both DevFeed: [Agent Harness vs Platform Harness: Why Teams Need Both]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-09-10T04:47:42Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Harness](), [AI Engineering](), [AI Agent](), [Orchestration](), [Software]() Tags: [agentic](), [ai-agent](), [ai-engineering](), [article](), [governance](), [memory](), [orchestration](), [platform](), [tools]() ### AI overview This article distinguishes between an agent harness, which wraps a model with prompts, tools, orchestration, memory, and guardrails, and a platform harness, which adapts an agent to an organization's systems, standards, skills, tools, and governance requirements. It explains why teams need both layers and why vendor-agent adopters should build the platform harness first. ### Source excerpt Agent harness vs platform harness: what each layer covers, who owns it, what breaks when you have only one, and why you need both. ## Claude performed best on a new benchmark for 'agents that build agents'. But it passed fewer than a quarter of the tests. DevFeed: [Claude performed best on a new benchmark for 'agents that build agents'. But it passed fewer than a quarter of the tests.]() Original publisher: [Read original article]() Author: Paul Sawers Published: 2026-09-09T20:14:09Z Content type: news Language: en Sources: [The New Stack]() Topics: [Claude](), [coding](), [anthropic](), [Software]() Tags: [agents](), [ai](), [ai-agents](), [ai-engineering](), [ai-models](), [benchmark](), [claude](), [claude-code](), [codex](), [coding](), [large-language-models](), [leaderboard](), [testing]() ### AI overview Hyper-𝜏-bench evaluates whether AI developer agents can build customer-service agents from simulated business materials. Claude Opus 5 in Claude Code led the six tested configurations at 23.9%, while none exceeded 25%. ### Source excerpt AI models now power all manner of agents, from coding assistants that write and debug software to customer service systems The post Claude performed best on a new benchmark for 'agents that build agents'. But it passed fewer than a quarter of the tests. appeared first on The New Stack. ## OpenAI gave an AI the power to block its own engineers' code DevFeed: [OpenAI gave an AI the power to block its own engineers' code]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-09T19:53:08Z Content type: news Language: en Sources: [The New Stack]() Topics: [Code review](), [Pull Request](), [vulnerability](), [LLM evaluation / benchmarking](), [Deployment]() Tags: [ai](), [ai-engineering](), [benchmark](), [codex](), [model](), [openai](), [pull-request](), [review](), [security](), [software-development](), [vulnerability]() ### AI overview OpenAI uses automated AI security review for every engineer pull request, blocking merges when a vulnerability is found. The article describes specialized code-review models, benchmarking claims, and a shift in human review toward discussing intent earlier in development. ### Source excerpt Every pull request submitted by an OpenAI engineer now goes through an automated security review, and the AI model can The post OpenAI gave an AI the power to block its own engineers' code appeared first on The New Stack. ## Evaluation-First AI Agents: How Zepto Scales Customer Support on Databricks and MLflow DevFeed: [Evaluation-First AI Agents: How Zepto Scales Customer Support on Databricks and MLflow]() Original publisher: [Read original article]() Author: Gireesh Sreedhar KP; Deepak Dhankani; Eash Sharma Published: 2026-09-09T03:00:00Z Content type: article Language: en Sources: [Databricks]() Topics: [AI Agent](), [databricks](), [AI Infrastructure](), [real-time]() Tags: [agents](), [ai](), [ai-engineering](), [architecture](), [best-practices](), [blog](), [company](), [customer](), [customers](), [data-science-and-ml](), [data-strategy](), [databricks](), [efficiency](), [engineering](), [evaluation](), [india](), [industries](), [operations](), [platform](), [product](), [production](), [real-time](), [retail-consumer-goods](), [scale](), [workflows]() ### AI overview This Databricks and MLflow case study describes how Zepto uses an evaluation-first, multi-agent AI system to operate customer support at more than 100,000 tickets per day. It focuses on the system architecture, evaluation framework, quality gate, and development and production loops used to improve reliability as volume, product categories, languages, and failure modes expand. ### Source excerpt Zepto's Push for Reliable, Real-Time Customer SupportZepto is one of India's fastest-growing... ## GPT 6 Astra's performance in a software-engineering workflow DevFeed: [GPT 6 Astra's performance in a software-engineering workflow]() Original publisher: [Read original article]() Author: Armin Ronacher Published: 2026-09-07T00:00:00Z Content type: opinion Language: en Sources: [Armin Ronacher]() Topics: [Artificial Intelligence](), [AI Engineering](), [Software Engineering](), [computer-use](), [ChatGPT](), [Python](), [Concurrency]() Tags: [agent](), [ai](), [ai-engineering](), [chatgpt](), [computer-use](), [python](), [software-engineering](), [thoughts]() ### AI overview The author argues that AI engineering can intensify effort without improving productivity and examines GPT 6 Astra's usefulness for software engineering. A self-managed software factory using Astra produced substantial code and prompts over 35 hours but, according to the author, delivered nothing of value and provided no clear lessons for improving the workflow. ### Source excerpt I'm more and more convinced that all of AI engineering is Neijuan (内卷, meaning curl inwards). In China it describes a system that demands ever more effort and competition without improving output. The way in which it sometimes shows up in the West is the 996 nonsense. The English term for Neijuan is "Involution" from the book Agricultural Involution. Agricultural involution describes the intensification of farming that raises productivity per square meter while leaving productivity per head unchanged. That's how I feel about AI right now. Which brings me to GPT 6 Astra. Astra is by all accounts an incredibly impressive model. There is really not much I can say against this. It's amazing at computer use, understands images and complex topics, and it's relentless in its pursuit of completion. It is absolutely impressive; these types of models are going to change the world in one form or another. But at least for the moment I don't know how to work with it for actual software engineering. Since that got quite a bit of attention on Twitter, I figured I might summarize my thoughts and just share what kind of code comes out of this thing. My Slop Factory "Armin, you should run a software factory!" I've heard that a few times now, so I figured I might celebrate the release of it by running a little software factory over the weekend. If everybody builds slop 3D games, then I should do something useful with it. My software factory was intentionally set up to let the model decide the how of the workflow entirely. It was free to manage its own context and could maintain its own records in an agent-notes folder. Then it spun off subagents to work on stuff. The goal? What if we had a Python with virtual threads and lexical scoping. And well, I burned a full reset's worth of ChatGPT tokens on this which appears to be around 4 billion tokens. 35 hours later, the factory has delivered absolutely nothing of value and also not taught me anything about how to operate a better one. But ## Monitor prompt caching to optimize your token usage DevFeed: [Monitor prompt caching to optimize your token usage]() Original publisher: [Read original article]() Author: Thomas Sobolik Published: 2026-09-02T00:00:00Z Content type: tutorial Language: en Sources: [Datadog | The Monitor blog]() Topics: [Caching](), [Large Language Model](), [Latency](), [Traces](), [SIEM, Security, Observability](), [anthropic]() Tags: [agent-observability](), [agents](), [ai](), [ai-engineering](), [ai-observability](), [anthropic](), [caching](), [cost](), [how-to](), [latency](), [llm](), [models](), [monitor](), [openai](), [traces]() ### AI overview A tutorial on prompt caching for LLM and agent workloads, covering cache behavior, provider differences, and monitoring token use and latency. ### Source excerpt Learn how to use prompt caching effectively and monitor your models and agents to troubleshoot cache invalidations. ## From Chrome DevTools to AI Engineering, with Addy Osmani DevFeed: [From Chrome DevTools to AI Engineering, with Addy Osmani]() Original publisher: [Read original article]() Author: Gergely Orosz Published: 2026-08-19T16:53:57Z Content type: article Language: en Sources: [The Pragmatic Engineer]() Topics: [AI Engineering](), [AI Agent](), [Developer experience](), [Google](), [developer tooling](), [engineering-culture](), [Loop Engineering](), [Chrome]() Tags: [agents](), [ai-agents](), [ai-engineering](), [developer](), [developer-experience](), [devtools](), [engineering](), [google](), [software-engineering](), [workflows]() ### AI overview Addy Osmani discusses his 14 years at Google, including work on Chrome, DevTools, Core Web Vitals, and AI developer experience. The conversation covers AI agents, loop engineering, cognitive surrender, engineering culture, and the broader skills engineers need. ### Source excerpt Addy Osmani shares lessons from 14 years at Google and how AI agents are reshaping software engineering, developer workflows, and the skills engineers need to succeed. [Next page]()