# agentic-coding Published articles for agentic-coding. 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. ## GitHub Copilot's Project HydraFusion Promises Frontier Level Performance Through Multi-Model Routing DevFeed: [GitHub Copilot's Project HydraFusion Promises Frontier Level Performance Through Multi-Model Routing]() Original publisher: [Read original article]() Author: Olimpiu Pop Published: 2026-09-13T06:06:00Z Content type: news Language: en Sources: [InfoQ]() Topics: [GitHub Copilot](), [Model Routing](), [AI-assisted coding](), [Orchestration]() Tags: [agentic-coding](), [ai](), [ai-ml-data-engineering](), [benchmarks](), [development](), [frontier-model](), [github-copilot](), [github-hydrafusion](), [ml-data-engineering](), [model-routing](), [news](), [orchestration]() ### AI overview GitHub's Project HydraFusion research preview for Copilot orchestrates multiple models at runtime for coding tasks. Its single, cascade, and critique execution patterns aim to balance task quality, latency, and estimated cost. ### Source excerpt GitHub's Project HydraFusion is a research preview for GitHub Copilot that enhances coding intelligence through runtime model orchestration. It dynamically assembles execution plans using models from various providers. The system employs three execution patterns based on task complexity. Evaluations indicate that it achieves high task quality while significantly reducing operational costs. By Olimpiu Pop ## Project HydraFusion: Frontier quality via multi-model orchestration DevFeed: [Project HydraFusion: Frontier quality via multi-model orchestration]() Original publisher: [Read original article]() Author: GitHub Staff Published: 2026-09-04T16:04:14Z Content type: release Language: en Sources: [GitHub Engineering]() Topics: [Orchestration](), [Model Routing](), [GitHub Copilot](), [AI-assisted coding](), [Optimization](), [Claude]() Tags: [agentic-coding](), [ai-ml](), [benchmarking](), [benchmarks](), [claude](), [cost](), [github-copilot](), [llms](), [optimization](), [orchestration](), [routing]() ### AI overview GitHub introduces Project HydraFusion, a GitHub Copilot research preview that selects multi-model execution workflows to balance quality, cost, and latency for coding tasks. ### Source excerpt In controlled offline evaluations, HydraFusion's selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research preview in GitHub Copilot. The post Project HydraFusion: Frontier quality via multi-model orchestration appeared first on The GitHub Blog. ## How we make AI coding more cost efficient without sacrificing task quality DevFeed: [How we make AI coding more cost efficient without sacrificing task quality]() Original publisher: [Read original article]() Author: Erik Kristensen Published: 2026-09-02T18:00:00Z Content type: article Language: en Sources: [GitHub](), [GitHub Engineering]() Topics: [GitHub Copilot](), [AI-assisted coding](), [GitHub Copilot CLI](), [coding](), [GitHub Copilot app](), [GitHub Copilot code review]() Tags: [agentic-ai](), [agentic-coding](), [ai](), [ai-coding](), [ai-ml](), [architecture-optimization](), [benchmarks](), [compression](), [cost](), [engineering](), [experiments](), [github-copilot](), [github-copilot-cli](), [github-copilot-code-review](), [llms](), [prompt-engineering]() ### AI overview GitHub Copilot's efficiency work focuses on total task cost and duration rather than minimizing tokens in individual tool responses. The article describes evaluating changes with coding benchmarks and controlled experiments, and explains that overly compressed output can cause agents to repeat work. ### Source excerpt Why shorter outputs can cost more, and how GitHub Copilot reduces wasted work across the complete coding task. The post How we make AI coding more cost efficient without sacrificing task quality appeared first on The GitHub Blog. ## Claude Fable 5.1 now available on AI Gateway DevFeed: [Claude Fable 5.1 now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-01T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Language models](), [AI-assisted coding](), [AI, ML & Data Engineering](), [Vulnerabilities](), [cursor]() Tags: [agentic](), [agentic-coding](), [ai-gateway](), [anthropic](), [api](), [claude](), [language-models](), [safety](), [vulnerabilities]() ### AI overview Claude Fable 5.1 is available on AI Gateway, with model fallback support for safety-classifier refusals and compatibility across its API formats. ### Source excerpt Claude Fable 5.1 from Anthropic is now available on AI Gateway. Fable 5.1 improvements compared to previous Claude models are concentrated in long, multi-stage work like agentic coding, knowledge work, and research that takes several rounds of searching and following up. Anthropic ships Fable 5.1 with cybersecurity and biology safety classifiers enabled. Finding vulnerabilities in source code is allowed, but some routine coding and debugging may still be refused. To ensure requests are still serviced when the safety classifiers are triggered, use model fallbacks. Add a models array to providerOptions.gateway listing the models to try. AI Gateway sends the request to Fable 5.1 first, and if Anthropic refuses it, works down the array in order and returns the response from the first model that succeeds: This request falls back to Opus 5, then Sonnet 5, if a safety classifier is triggered. The same models option works on every AI Gateway API format, including Chat Completions, Messages, and OpenAI Responses. Try Fable 5.1 in the model playground. To use it in a coding agent, see the coding agents guide, then run vercel ai-gateway coding-agents setup to connect agents like Claude Code, Codex, OpenCode, Cursor, Pi, and more and select anthropic/claude-fable-5.1 inside the agent. Anthropic does not support Zero Data Retention for Fable 5.1. Prompts and completions are retained for 30 days and are not used to train Claude. You can view all language models available on AI Gateway. Read more ## 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. ## NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt DevFeed: [NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-24T15:00:05Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [AI-assisted coding]() Tags: [agentic-ai](), [agentic-ai-generative-ai](), [agentic-coding](), [ai-agent](), [ai-agents](), [ai-factory](), [ai-infrastructure](), [benchmark](), [blackwell](), [cache](), [cloud-networking](), [cloud-services](), [data-center-cloud](), [gb300-nvl72](), [hardware](), [inference](), [long-context](), [mixture-of-experts-moe](), [nemotron](), [nvidia](), [performance](), [software-defined-data-center](), [tools](), [vera-rubin](), [vera-rubin-nvl72]() ### AI overview The article examines the SemiAnalysis AgentX benchmark for measuring infrastructure efficiency on replayed agentic coding sessions. It compares Vera Rubin and Blackwell NVL72 systems by agentic throughput per megawatt and explains why dynamic, stateful sessions require more realistic evaluation than fixed-length inference tests. ### Source excerpt AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents, and carry growing... ## 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. ## 10x more capacity for Laguna S 2.1 on AI Gateway DevFeed: [10x more capacity for Laguna S 2.1 on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-07-31T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [vercel ai sdk](), [AI-assisted coding](), [SDKs]() Tags: [agentic-coding](), [ai](), [ai-gateway](), [ai-models](), [api](), [coding](), [leaderboard](), [vercel]() ### AI overview Laguna S 2.1 on AI Gateway now has 10x more capacity for both paid and free model versions. The article explains configuring the model through the AI SDK or a coding agent, and describes AI Gateway features including usage tracking, retries, failover, and a model-usage leaderboard. ### Source excerpt Laguna S 2.1 from Poolside now has 10x more capacity on AI Gateway. The increase applies to the paid version, poolside/laguna-s-2.1, and the free version, poolside/laguna-s-2.1-free, so you can send far more requests, good for high-volume agentic coding and long-running tasks. 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: To run it in a coding agent, use vercel ai-gateway coding-agents setup to connect your agents to AI Gateway, then select poolside/laguna-s-2.1 or poolside/laguna-s-2.1-free in the agent's model configuration. See the coding agents guide. AI Gateway gives you one API to hundreds of models, with usage tracking, retries, failover, and higher-than-provider uptime built in. It reflects provider pricing with no markup and no platform fee, including on Bring Your Own Key requests. Try Laguna S 2.1 in the model playground. Read more ## Inkling Small from Thinking Machines is now available on AI Gateway DevFeed: [Inkling Small from Thinking Machines is now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-07-30T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI, ML & Data Engineering](), [vercel ai sdk](), [AI-assisted coding](), [SDKs]() Tags: [agentic-coding](), [ai-gateway](), [ai-models](), [audio](), [cost](), [images](), [leaderboard](), [reasoning](), [tool]() ### AI overview Inkling Small is now available through AI Gateway. The release highlights multimodal reasoning, configurable thinking effort, visual inspection capabilities, coding and tool-use workflows, Zero Data Retention support, and AI SDK integration. ### Source excerpt Inkling Small from Thinking Machines is now available on AI Gateway. Inkling Small reaches performance comparable to the larger Inkling model at about a quarter of the size, using much less compute per task. It is a broad generalist with native reasoning over audio and images, and it holds up well on reasoning, agentic coding, and tool use. Controllable thinking effort lets you trade quality against cost and latency, from minimal to maximum reasoning. For visual tasks, it can crop, zoom, and inspect images programmatically, which helps on documents and charts where the relevant detail is small. To use Inkling, set model to thinkingmachines/inkling-small in the AI SDK: Inkling-Small is compatible with Zero Data Retention. Turn it on team-wide from the dashboard, or per request with zeroDataRetention: true, and AI Gateway routes only to providers that delete prompts and responses after each request. Inkling-Small is also a cost-efficient choice for coding and tool-use workflows. Run vercel ai-gateway coding-agents setup to connect your coding agents to AI Gateway, then select thinkingmachines/inkling-small in the agent's model configuration. See the coding agents guide. 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 Inkling Small in the model playground. Read more ## Claude Opus 5 now available on AI Gateway DevFeed: [Claude Opus 5 now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-07-24T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI-assisted coding](), [vercel ai sdk](), [SDKs]() Tags: [agentic-coding](), [ai-gateway](), [anthropic](), [claude](), [claude-code](), [cybersecurity](), [reasoning](), [speed]() ### AI overview Claude Opus 5 is now available through AI Gateway, with features for agentic coding, configurable reasoning effort, model fallbacks, fast mode, and multi-provider access. ### Source excerpt Claude Opus 5 from Anthropic is now available on AI Gateway. Opus 5 improves on previous Opus models for long-horizon agentic coding, handling multi-file features, larger refactors, and end-to-end feature work, and completing full tasks rather than leaving stubs or placeholders. Opus 5 is effective at low and medium effort, which produce quality at a fraction of the tokens and latency of higher settings. Vision is stronger on charts, documents, diagrams, and UI replication, and Opus 5 makes effective use of tools to analyze, crop, and verify visual work. It also coordinates teams of subagents well, which suits multi-agent workflows. Reasoning is on by default. In AI SDK 7, set the reasoning effort with the top-level reasoning option, from minimal up to xhigh, or none: Like Fable 5, Opus 5 ships with elevated cybersecurity safeguards, so benign security work can occasionally trigger a safety classifier and get blocked. To add a backstop, use AI Gateway's model fallbacks. List backup models in a models array under providerOptions.gateway, and the gateway tries them in order when the primary model fails. The same option works across every AI Gateway API format. Opus 5 is compatible with Zero Data Retention. Fast mode To enable fast mode, pass speed: 'fast' in the anthropic provider options in AI SDK: Providers and endpoints Opus 5 can be served by more than one provider. To see every provider serving it, along with per-provider pricing, supported parameters, uptime, throughput, and latency, call the model endpoints API: Use Opus 5 in your coding agent Route your coding agent through AI Gateway to run Opus 5 with unified spend tracking, model fallbacks, and access to every model. Run vercel ai-gateway coding-agents setup to detect the agents on your machine, provision a key, and write their config. See how to set it up in Claude Code. Read more ## 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 ## What a $20 coding subscription actually buys DevFeed: [What a $20 coding subscription actually buys]() Original publisher: [Read original article]() Author: Kevin Purdy Published: 2026-07-17T16:00:00Z Content type: tutorial Language: en Sources: [Blog on Tailscale]() Topics: [AI Chat]() Tags: [agentic-coding](), [ai](), [llm](), [openai]() ### AI overview A guide to using Tailscale Aperture with Claude Code or ChatGPT/Codex subscriptions to track token costs and manage access. ### Source excerpt Someone's subsidizing your coding agent. Aperture shows whether it's you. ## Developers who move fast still need to do it together DevFeed: [Developers who move fast still need to do it together]() Original publisher: [Read original article]() Published: 2026-07-17T07:40:00Z Content type: news Language: en Sources: [Stack Overflow Blog]() Topics: [AI-assisted coding]() Tags: [agentic-ai](), [agentic-coding](), [ai](), [announcements](), [coding-community](), [community](), [dev-life](), [developers](), [github-copilot](), [github-copilot-app](), [microsoft](), [podcast](), [sdlc](), [se-stackoverflow](), [se-tech]() ### AI overview A discussion of how agentic coding changes developer work, the continuing importance of human judgment and community, and GitHub Copilot announcements from Microsoft. ### Source excerpt At MS Build, Ryan is joined by Cassidy Williams, Senior Director of Developer Advocacy at GitHub and former Stack Overflow Podcast host, to discuss how agentic coding is shifting dev work towards higher-level strategy while increasing decision fatigue; why human taste, community feedback, and mentorship are becoming more essential than ever for developer careers; and the new GitHub Copilot announcements coming out of Microsoft, including the new GitHub Copilot app. ## 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. [Next page]()