# agentic-coding Agentic coding is a software-development approach in which AI coding agents plan and execute complex programming tasks using coding tools and execution environments. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## MLPerf Inference v6.1: 5.7x Per-Accelerator Gains, a 512-GPU Run, and Vera Rubin's First Peer-Reviewed Numbers DevFeed: [MLPerf Inference v6.1: 5.7x Per-Accelerator Gains, a 512-GPU Run, and Vera Rubin's First Peer-Reviewed Numbers]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-16T15:00:00Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [Benchmark](), [Inference Performance](), [Retrieval Augmented Generation (RAG)](), [agentic-coding](), [GPU](), [Vera Rubin NVL72](), [Nvidia](), [Vera Rubin]() Tags: [agentic-coding](), [ai](), [benchmark](), [enterprise](), [gpt-oss](), [gpu](), [inference](), [llama-cpp](), [numbers](), [nvidia](), [qwen3](), [rag]() ### AI overview MLCommons published MLPerf Inference v6.1 with record participation, two new inference tests, and peer-reviewed results for several newly covered accelerators. The release reports a 5.7x improvement in the best per-accelerator DeepSeek-R1 server result compared with v5.1. ### Source excerpt MLCommons has published MLPerf Inference v6.1, and the round sets a participation record with 30 submitting organizations and 486 datacenter and edge results. Two new tests join the suite: an End-to-End RAG pipeline for the datacenter and an Edge Agentic Inference benchmark for single-user devices, and the results carry the first peer-reviewed numbers for NVIDIA's The post MLPerf Inference v6.1: 5.7x Per-Accelerator Gains, a 512-GPU Run, and Vera Rubin's First Peer-Reviewed Numbers appeared first on StorageReview.com. ## Why developers should avoid relying on frontier-model APIs in trusted systems DevFeed: [Why developers should avoid relying on frontier-model APIs in trusted systems]() Original publisher: [Read original article]() Author: Niels Provos Published: 2026-09-16T05:42:22Z Content type: opinion Language: en Sources: [APNIC Blog]() Topics: [Artificial Intelligence](), [Frontier Model](), [agentic-coding](), [coding](), [Claude]() Tags: [agentic-coding](), [ai](), [anthropic](), [api](), [artificial-intelligence](), [coding](), [frontier-model](), [gateway](), [guest-post](), [security](), [tech-matters]() ### AI overview This opinion article argues that relying on frontier-lab APIs creates risks around pricing, availability, model behavior, and output integrity. It presents open-weight models as a way to retain control over critical dependencies, while distinguishing coding assistance from placing frontier models in live request paths. ### Source excerpt Guest Post: A frontier API can refuse, change, or vanish out from under you. Open weights keep the model you depend on yours. ## Moving from XCTest to Swift Testing \[FREE\] DevFeed: [Moving from XCTest to Swift Testing \[FREE\]]() Original publisher: [Read original article]() Author: renan.dias Published: 2026-09-11T18:41:42Z Content type: tutorial Language: en Sources: [Kodeco | High quality programming tutorials: iOS, Android, Swift, Kotlin, Unity, and more]() Topics: [Swift Testing](), [Unit testing](), [Xcode](), [agentic-coding](), [SwiftUI](), [iOS]() Tags: [agentic](), [agentic-ai](), [app](), [apple](), [article](), [free](), [how-to](), [ios](), [swift-testing](), [swiftui](), [testing](), [xcode]() ### AI overview A tutorial on migrating unit tests from Apple's XCTest framework to Swift Testing. It explains common testing scenarios, Swift Testing's newer syntax and constructs, and how Xcode's Agentic Coding can assist with the migration while working on a SwiftUI coffee-ordering app. ### Source excerpt Swift Testing is Apple's replacement for the objective-C XCTest unit testing framework. Discover how to migrate your existing XCTest suites over to Swift Testing, including how to get some assistance from Xcode's agentic AI tooling. ## How to secure AI coding agents with permissions, approval gates, hooks, and sandboxing DevFeed: [How to secure AI coding agents with permissions, approval gates, hooks, and sandboxing]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-09-08T10:07:38Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [agentic-coding](), [Artificial Intelligence](), [AI-assisted coding](), [coding]() Tags: [agents](), [ai](), [ai-coding-agents](), [claude-code](), [coding-agents](), [how-to](), [least-privilege](), [permissions](), [sandboxing](), [security]() ### AI overview The article explains why coding-agent instructions such as CLAUDE.md are behavioral guidance rather than enforceable security boundaries. It discusses least privilege, Claude Code permissions, approval gates, hooks, and sandboxing as technical controls for limiting agent actions. ### Source excerpt Learn how to use the principle of least privilege, Claude Code permissions, approval gates, hooks, and sandboxing to keep your agentic coding secure ## Coding Challenge #134 - Agentic Engineering Graph DevFeed: [Coding Challenge #134 - Agentic Engineering Graph]() Original publisher: [Read original article]() Author: John Crickett Published: 2026-08-29T08:01:12Z Content type: tutorial Language: en Sources: [Coding Challenges]() Topics: [agentic-coding](), [Orchestration](), [coding](), [MCP Server](), [Langgraph](), [MCP](), [Chaos Engineering](), [ide]() Tags: [agent](), [agentic](), [agentic-coding](), [agentic-engineering](), [ci](), [code](), [distributed-systems](), [langgraph](), [news](), [orchestration](), [review](), [sonarqube](), [systems]() ### AI overview A coding challenge guides readers through building an agentic engineering graph: a small orchestration system that runs an autonomous coding loop of planning, coding, testing, review, and retry. It uses scripts and files for dispatch and persisted state, adds a deterministic Sonar static-analysis quality gate, and then replaces it with an AI-augmented review node using the SonarQube MCP Server. ### Source excerpt This challenge is to build your own agentic engineering graph. ## Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding DevFeed: [Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding]() Original publisher: [Read original article]() Author: Michelle Horton Published: 2026-08-26T17:07:12Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [qwen](), [long-context](), [Mixture of Experts (MoE)](), [agentic-coding](), [Inference](), [GPU](), [multimodal](), [NeMo](), [sglang](), [TensorRT-LLM](), [vllm](), [rust-ai]() Tags: [agentic-ai-generative-ai](), [agentic-coding](), [benchmarks](), [context-window](), [developer-tools-techniques](), [gb300-nvl72](), [inference](), [mixture-of-experts-moe](), [multimodal](), [nemo](), [nvlink](), [qwen](), [sglang](), [tensorrt-llm](), [top-stories](), [vllm]() ### AI overview This NVIDIA developer article introduces Qwen3.8-Flash-Next, a multimodal mixture-of-experts model released by Alibaba for experimentation and evaluation. It explains the model's long-context hybrid architecture, including Gated DeltaNet and Qwen Sparse Attention, and discusses reported efficiency improvements for million-token workloads. The article also covers inference support through SGLang, vLLM, TensorRT-LLM, and NVIDIA NeMo, plus performance on the NVIDIA GB300 NVL72 platform. ### Source excerpt Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It's... ## Practices for Using Coding Agents to Build Stable Temporal Applications DevFeed: [Practices for Using Coding Agents to Build Stable Temporal Applications]() Original publisher: [Read original article]() Author: Mason Egger Published: 2026-08-26T00:00:00Z Content type: tutorial Language: en Sources: [Temporal Blog]() Topics: [agentic-coding](), [AI-assisted coding](), [Claude Code](), [coding](), [unit test]() Tags: [agentic-coding](), [ai](), [claude-code](), [coding](), [coding-agents](), [temporal-voices]() ### AI overview The article explains how to use coding agents to build stable, production-ready Temporal applications. It recommends providing the right context, applying guardrails, and aligning with the agent on what to build, while noting that the approach is not limited to Claude Code. ### Source excerpt The tools and habits I've found that lead to stable, production-ready Temporal applications. ## Four Days Left to Enter the Ready, Spec, Ship Hackathon DevFeed: [Four Days Left to Enter the Ready, Spec, Ship Hackathon]() Original publisher: [Read original article]() Author: John Crickett Published: 2026-08-19T08:02:04Z Content type: opinion Language: en Sources: [Coding Challenges]() Topics: [Hackathon](), [Kiro](), [agentic-coding]() Tags: [agentic-coding](), [build](), [coding](), [hackathon](), [kiro](), [project]() ### AI overview A reminder that four days remain to enter the Ready, Spec, Ship Hackathon. Participants may enter individually or in teams of up to three, submit multiple projects, and receive free Kiro credits if their entries are verified. The article also describes the $9,600 prize pool and submission deadline. ### Source excerpt What will you build and could you win a prize? ## How to move fast toward the right thing DevFeed: [How to move fast toward the right thing]() Original publisher: [Read original article]() Author: Jake Albaugh Published: 2026-08-13T20:30:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Artificial Intelligence](), [Tech Debt](), [Large Language Model](), [Vibe coding](), [agentic-coding](), [sdlc]() Tags: [agentic-coding](), [ai](), [developers](), [llms](), [sdlc](), [tech-debt](), [vibe-coding]() ### AI overview AI makes software building faster and more accessible, but can also produce tech debt and encourage uncritical acceptance of polished outputs. The article argues that teams should begin with clear intent, carefully decide what is worth building, and use AI to translate that intent into software while retaining human judgment. ### Source excerpt With AI, speed comes easy, but so does tech debt. That's why the best teams don't just ship something fast; they consider it carefully, build it efficiently, and make it stand out. ## Responding to the next frontier of critical cyber capabilities DevFeed: [Responding to the next frontier of critical cyber capabilities]() Original publisher: [Read original article]() Published: 2026-08-07T15:20:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Cybersecurity](), [Artificial Intelligence](), [agentic-coding](), [Benchmark](), [Threat Research](), [Security](), [OpenAI]() Tags: [agentic](), [agentic-coding](), [ai](), [attacks](), [benchmark](), [cybersecurity](), [encryption](), [monitoring](), [network](), [openai](), [safety](), [security](), [systems](), [testing](), [tool]() ### AI overview OpenAI reports preliminary internal evaluations of its upcoming Astra model, indicating significant advances in agentic coding and cybersecurity. The evaluations suggest that the model may approach the Critical cybersecurity capability threshold, including the ability to develop zero-day exploits or execute novel cyberattack strategies against hardened targets without human intervention. OpenAI says it is strengthening safeguards through stricter security controls, isolated testing, restricted network and tool access, encryption, monitoring, detection, and sandboxed execution. ### Source excerpt OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we're taking to strengthen safeguards and security controls. ## Better code, fewer tokens: The benefits of Code Connect in MCP DevFeed: [Better code, fewer tokens: The benefits of Code Connect in MCP]() Original publisher: [Read original article]() Author: Tom Weightman Published: 2026-08-05T18:16:00Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Figma](), [MCP Server](), [Model Context Protocol](), [AI-assisted coding](), [agentic-coding](), [Front end](), [Code quality]() Tags: [agentic-coding](), [agents](), [case-study](), [code](), [code-quality](), [coding](), [design](), [figma](), [mcp]() ### AI overview Figma's Code Connect gives coding agents production-component context through the Figma MCP server. Evaluations found shorter task durations, higher code quality, and lower token usage when Code Connect templates were available. ### Source excerpt When going from design to code, agents lack the context of your production components. With Code Connect in Figma's MCP, they get that context. We measured its impact on token usage, task duration, and code quality. ## Ready, Spec, Ship Hackathon Announces $9,600 Prize Pool and Kiro Credits DevFeed: [Ready, Spec, Ship Hackathon Announces $9,600 Prize Pool and Kiro Credits]() Original publisher: [Read original article]() Author: John Crickett Published: 2026-08-04T15:03:54Z Content type: article Language: en Sources: [Coding Challenges]() Topics: [Hackathon](), [Kiro](), [agentic-coding]() Tags: [agentic](), [agentic-coding](), [coding](), [hackathon](), [kiro]() ### AI overview An announcement for the Ready, Spec, Ship Hackathon, sponsored by Kiro. Participants may enter alone or in teams of up to three, submit multiple projects, and receive Kiro credits for verified entries; submissions close on 23 August. ### Source excerpt Try Kiro for free and win prizes! ## Agentic Coding: Bet on the Primitives DevFeed: [Agentic Coding: Bet on the Primitives]() Original publisher: [Read original article]() Author: Robin Wieruch Published: 2026-07-31T06:00:00Z Content type: opinion Language: en Sources: [Robin Wieruch]() Topics: [agentic-coding](), [coding](), [React](), [SVG]() Tags: [abstraction](), [agentic-coding](), [ai-coding-agents](), [ai-engineer](), [build-vs-buy-components](), [coding](), [d3-vs-recharts](), [opinions](), [react](), [svg]() ### AI overview The article argues that agentic coding lowers implementation costs enough to make owning lower-level primitives more practical. It describes an experiment comparing D3 math primitives with React-rendered SVG against Recharts for custom charts: Recharts reached most of the result faster, but its remaining customization needs and an animation issue led to more workarounds than the primitive-based approach. ### Source excerpt Agentic coding collapses the cost of implementation labor. Why the rational bet is moving from high-level libraries back to primitives you own. ## Announcing new course: AI in Platform Engineering DevFeed: [Announcing new course: AI in Platform Engineering]() Original publisher: [Read original article]() Author: Luca Galante Published: 2026-07-23T05:40:01Z Content type: article Language: en Sources: [Platform Engineering Blog]() Topics: [Platform Engineering](), [AI Platform](), [agentic-coding](), [GPU](), [observability](), [Inference]() Tags: [agentic-coding](), [ai](), [course](), [gpu](), [inference](), [observability](), [platform-engineering](), [sdlc]() ### AI overview This article announces a course on AI in Platform Engineering. It covers AI-native platforms, platforms for AI workloads, agentic coding, conversational observability, AI reference architectures, compliance, model provenance, and the operational requirements of training and inference at scale. ### Source excerpt Supercharge your SDLC and design the next generation of infrastructure for AI/ML workloads. Learn AI-native platform engineering from Mallory Haigh ## Laguna S 2.1 is now available on AI Gateway DevFeed: [Laguna S 2.1 is now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-07-21T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Models](), [agentic-coding](), [Mixture of Experts (MoE)](), [context window](), [API](), [MLOps](), [AI Research](), [API keys](), [Routing (disambiguation)]() Tags: [agentic-coding](), [ai-models](), [ai-research](), [api-keys](), [context-window](), [cost](), [mixture-of-experts](), [mlops](), [routing](), [sdk](), [support]() ### AI overview Poolside's Laguna S 2.1 is now available through Vercel AI Gateway in free and paid versions, with context windows of 256K and 1M tokens. The open-weight Mixture-of-Experts model supports thinking and no-thinking modes and is designed for agentic coding, long-running tasks, browser tooling, MLOps pipelines, and AI research. ### Source excerpt Laguna S 2.1 from Poolside is now available on AI Gateway. There are 2 versions of the model available: Free version (256K context window): poolside/laguna-s-2.1-free Paid version (1M context window): poolside/laguna-s-2.1 Laguna S 2.1 is an open-weight Mixture-of-Experts model that supports a context window of up to 1M tokens and runs in thinking and no-thinking modes. The model specializes in agentic coding and long-running tasks, including writing and debugging code, running tests, building browser-based tooling, and working on MLOps pipelines and AI research. In thinking mode, Laguna S 2.1 reports 70.2% on Terminal-Bench 2.1, 78.5% on SWE-bench Multilingual, and 59.4% on SWE-Bench Pro. To use Laguna S 2.1, set model to poolside/laguna-s-2.1-free or poolside/laguna-s-2.1 in the AI SDK: AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Try Laguna S 2.1 in the model playground. Read more ## How Decagon uses AI for design system saturation DevFeed: [How Decagon uses AI for design system saturation]() Original publisher: [Read original article]() Author: Jenny Xie Published: 2026-07-10T20:30:56.769000Z Content type: article Language: en Sources: [Figma Blog]() Topics: [Figma](), [Model Context Protocol](), [AI-assisted coding](), [agentic-coding](), [Code]() Tags: [agentic](), [agentic-coding](), [agents](), [ai](), [ai-agents](), [code](), [customer-service](), [design](), [developer](), [figma](), [mcp]() ### AI overview Figma MCP and Figma Make helped Decagon scale an organization-wide design system, improve design-to-code handoffs, and support rapid customer-service product development. The article explains how structured Figma libraries give designers, developers, and coding agents a shared source of truth. ### Source excerpt The fast-growing customer experience platform explains how Figma MCP and Figma Make helped them scale a new design system and keep pace with customer requests. ## Using Storybook Workbench to audit AI-generated UIs for dead components and accessibility bugs DevFeed: [Using Storybook Workbench to audit AI-generated UIs for dead components and accessibility bugs]() Original publisher: [Read original article]() Author: Travis Turner (richardturner@evilmartians.com) Published: 2026-07-08T00:00:00Z Content type: tutorial Language: en Sources: [Evil Martians]() Topics: [Storybook](), [Agent Skills](), [agentic-coding](), [AI-assisted coding](), [Accessibility](), [Design system]() Tags: [accessibility](), [agent-experience](), [agent-skills](), [agentic-coding](), [agentic-development](), [ai](), [bugs](), [design](), [design-engineering](), [design-for-devtools](), [design-system](), [dx](), [storybook]() ### AI overview The article presents Storybook Workbench, a bundle of Agent Skills that audits AI-generated web applications by rendering components as Storybook stories. It describes finding dead components, coexisting design systems, conditional component states, and accessibility bugs, based on an internal audit of an agent-coded app. ### Source excerpt Storybook Workbench is a bundle of Agent Skills that turn Storybook into an audit layer for AI-generated UIs: find dead components, design-system drift, and hidden accessibility bugs. ## Community Engineering, Agentic Coding, and Real-User Component Testing DevFeed: [Community Engineering, Agentic Coding, and Real-User Component Testing ]() Original publisher: [Read original article]() Author: Angular Published: 2026-07-07T15:47:29Z Content type: article Language: en Sources: [Angular]() Topics: [Angular](), [agentic-coding](), [Testing](), [Artificial Intelligence](), [browser]() Tags: [agentic-coding](), [ai-agents](), [angular](), [angular-weekly](), [blog](), [browser](), [testing]() ### AI overview This Angular ecosystem roundup highlights community-first engineering, agentic coding support for Angular workspaces, and component testing with Vitest's Full Browser Mode. It also points to resources about Signal Forms, Angular compiler diagnostics, AI image generation with Firebase AI Logic, and restoring CSS classes in Signal Forms. ### Source excerpt What an incredible week for the ecosystem. We are diving deep into what it truly means to build a community-first framework, exploring how AI agents are changing how we write code, and looking at next-level browser testing. Get inspired and upgrade your workflow with this week's resources: The Dev Life Podcast: Community-First Engineering with Magda Kustosz Brooke Avery @JediBravery and Matthew Christiansen sit down for a must-listen conversation with our very own Angular Community Manager, Magda Kustosz 🌟 Dive into the strategy, heart, and insights behind building a community-driven ecosystem. Plus, check out the full playlist intro to catch the rest of the season's tech discussions. Listen to the Community Episode: https://www.youtube.com/watch?v=YAT7vc1zYLg Check out the full playlist: https://www.youtube.com/watch?v=6nmeHYDjZk8| Agentic Coding: AI Support for Angular Johannes Hoppe @JohannesHoppe and Ferdinand Malcher @fmalcher01 explore the frontier of Agentic Coding. Discover how advanced AI agents are moving past simple autocomplete to provide deep, context-aware architectural support tailored specifically for Angular workspaces. Read the blog post: https://angular.schule/blog/2026-02-agentic-coding Test Components Like a Real User with Vitest "Full" Browser Mode Younes Jaaidi @yjaaidi drops a game-changing tutorial on testing. Learn how to leverage Vitest's Full Browser Mode to test your Angular components exactly how a real user interacts with them in an actual browser environment. Watch the testing guide: https://youtu.be/Pu22JQG6jdg Signal Forms & Extended Compiler Diagnostics (Spanish with English Subtitles) Alejandro Cuba Ruiz @zorphdark brings us two fantastic videos with English subtitles. First, a comprehensive deep dive into the practical power of Signal Forms. Second, an essential look at how to leverage the Extended Diagnostics of the Angular Compiler to catch tricky bugs before they hit production. Watch the Signal Forms breakdown: https://youtu. ## Viability of local models for coding DevFeed: [Viability of local models for coding]() Original publisher: [Read original article]() Author: Martin Fowler (martin@martinfowler.com) Published: 2026-07-07T12:34:00Z Content type: article Language: en Sources: [Martin Fowler]() Topics: [coding](), [Large Language Model](), [agentic-coding](), [Hardware](), [quantization](), [MLX](), [Tooling]() Tags: [agentic-coding](), [coding](), [hardware](), [llms](), [local](), [mlx](), [quantization](), [tooling]() ### AI overview This memo examines how viable local language models are for coding, with particular attention to agentic coding rather than autocomplete. It discusses hardware constraints, model size, context windows, response speed, quantization, runtimes, and tooling. The author reports that tool calling remains unreliable but that models can often recover from failures. ### Source excerpt Birgitta Böckeler recently spent some time trying out running local LLMs for some programming tasks. In this memo she outlines the factors that influence how viable they are for the job. more... ## 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. ## Automating Everything That Doesn't Need Me DevFeed: [Automating Everything That Doesn't Need Me]() Original publisher: [Read original article]() Author: Josh Sherman Published: 2026-07-05T00:00:00Z Content type: opinion Language: en Sources: [Josh Sherman]() Topics: [agentic-coding](), [Automation](), [AI Development](), [Code]() Tags: [agentic-coding](), [automation](), [code](), [coding](), [deploy](), [monitoring](), [projects](), [side-projects](), [trust]() ### AI overview The author describes an ongoing experiment in using a personal agent and automation to reduce human involvement across side-project workflows, including design, coding, review, merging, deployment, and monitoring. Trust is built through repeated supervised iterations, with tests and intervention when the agent fails. ### Source excerpt I've been writing a lot about LLMs, AI (or the so-called "Artificial Intelligence") and the like. Part of that is because I haven't been running into many problems that I feel need documenting. Bigger part is because I'm finding that "how-to" content is easy to slop with a robot, so I'd rather write about things that the clankers can't. In a word, I'm just trying to write more human. While I don't think I've achieved full tokenmaxxing AI psychosis levels yet, I do like agentic coding. I'm also a huge proponent for automation. If it comes up regularly, it should be automated. If it can't be fully automated, then it should at least be partially automated. If I don't need to be materially involved, then I shouldn't be involved at all. My latest foray into building my own agent has included a refocus around trying to automate any and everything that I can. I still consider this to be an experiment more than me drinking any sort of Kool-Aid. Similar motives to my push for a dumber home, if I need to be involved, then it doesn't need to be smart. Well if I don't need to be involved, it should be automated. That's led me down a rabbit hole of trying to be less and less involved with certain things. Keep in mind, this is an experiment against my personal agent, and my myriad of smaller side projects. Most of the work is code based, so that includes writing a spec and/or design, slinging code, reviewing it, merging it, and deploying it. Most of that chain doesn't need me at all. Robots can take my half baked idea and turn it into a design spec. They can generate code that's coherent enough. Then they can review the code. I get to play gatekeeper and make them wait for my approval. From there, they can worry about merging it in and monitoring the deploy. I measure success on my agentic game loops by how much trust I have in the output that I'm reviewing. Run the loop enough times with a watchful eye, I can see where it fucks up. We iterate, and repeat the process. Usually wit ## Agentic Coding on Supabase with OpenCode DevFeed: [Agentic Coding on Supabase with OpenCode]() Original publisher: [Read original article]() Author: Eric Kharitonashvili Published: 2026-06-30T07:00:00Z Content type: article Language: en Sources: [Supabase Blog]() Topics: [Supabase](), [agentic-coding](), [ai-coding](), [Model Context Protocol](), [Database](), [Agent Skills](), [coding](), [Terminal]() Tags: [agentic-coding](), [ai-agents](), [ai-coding](), [backend](), [coding](), [database](), [ide](), [mcp](), [open-source](), [writing-code]() ### AI overview Supabase's OpenCode integration connects an open-source AI coding agent to Supabase account and project management APIs, bundled Supabase skills, and--through MCP--project capabilities such as databases, Edge Functions, logs, data queries, and deployments. The integration can also monitor agent activity, create projects, and run within a terminal, IDE, or desktop. ### Source excerpt OpenCode integrates with Supabase. Connect your agent to your database, Edge Functions, and logs. MCP setup is configured automatically. ## An Opinion on LLMs, Vibe Coding, and Agentic Coding DevFeed: [An Opinion on LLMs, Vibe Coding, and Agentic Coding]() Original publisher: [Read original article]() Author: Josh Sherman Published: 2026-06-28T00:00:00Z Content type: opinion Language: en Sources: [Josh Sherman]() Topics: [Large Language Model](), [Vibe coding](), [agentic-coding](), [Artificial Intelligence](), [Code](), [trust]() Tags: [agentic-coding](), [ai](), [coding](), [llms](), [trust](), [vibe-coding]() ### AI overview The author argues that slow websites predate vibe coding and criticizes broad claims that LLM-generated software is inherently poor. They support experimenting with LLMs and agentic coding while maintaining code and product quality, acknowledging that the tools still need guardrails and can require cleanup. ### Source excerpt LLMs are great at pattern detection. Use them long enough, and you get good at it too. Smoking guns, being absolutely right, it's not X but Y. They tend to be cute at first, but then these AI-isms become bad jokes after only a few conversations. Now that I can practically recite all of the dumb shit robots say, I'm starting to see it more and more from humans. That's not to say I see humans using AI-isms, I'm starting to see new patterns emerge. Maybe they've been there the whole time and I'm only now starting to notice. The one I particularly dislike is taking two disparate things, and attempting to use them as inference towards your biased opinion on things. My favorite one thus far cites that every company that has embraced vibe coding now has a 30 second page load or is completely unusable. This was the math behind an eye roll "programming is dead" quip. I guess if you just got here, this makes sense to you. Fun fact, there's always been slow websites. Like, forever. I've been both the contributing factor to slow websites as well as the savior that fixed them for nearly three decades. Most of which didn't include vibe coding. Fine, the robots still go off the rails, and need a lot of guard rails. But to jump to the conclusion that if something is slopped together by an LLM it's complete shit is... it's fucking dumb short sighted at BEST. We're all biased in one way or another. Clearly I'm in the camp that these new technologies are good, and are going to elevate us all. I also find that those sort of opinions are clearly made by people that aren't working with the tools. If they are, they are trying to find the holes to poke, rather than figuring out how we can work past them. I've been operating more and more in an end state with agentic coding. Where can I produce results? How can I remove myself from the things I find to be a waste of time? How do I balance it all while maintaining code and product quality. There are people moving faster than me. They trust t ## Improving token efficiency for GitHub Copilot in VS Code DevFeed: [Improving token efficiency for GitHub Copilot in VS Code]() Original publisher: [Read original article]() Author: Ryan Caldwell, Bhavya U Published: 2026-06-17T00:00:00Z Content type: article Language: en Sources: [Visual Studio Code - Code Editing. Redefined.]() Topics: [GitHub Copilot](), [vs-code](), [agentic-coding](), [Caching](), [context window](), [Latency](), [Model Context Protocol](), [anthropic](), [OpenAI](), [JSON]() Tags: [agentic-coding](), [anthropic](), [blog](), [caching](), [coding](), [context-window](), [cost](), [github-copilot](), [json](), [latency](), [mcp](), [openai](), [vs-code]() ### AI overview This article explains how VS Code improves token efficiency in GitHub Copilot's agentic coding harness. It focuses on prompt-prefix caching and reducing tool-definition overhead to lower token usage, cost, and latency while preserving task success rates across OpenAI and Anthropic models. ### Source excerpt Learn how we're improving token efficiency for GitHub Copilot to reduce costs and latency for VS Code users. Read the full article [Next page]()