# context window Published articles for context window. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How LLMs Handle Memory Through Context and Surrounding Applications DevFeed: [How LLMs Handle Memory Through Context and Surrounding Applications]() Original publisher: [Read original article]() Author: ByteByteGo Published: 2026-09-15T15:31:12Z Content type: article Language: en Sources: [ByteByteGo]() Topics: [Large Language Model](), [context window](), [App](), [long-context]() Tags: [article](), [context](), [context-window](), [cost](), [latency](), [llms](), [memory]() ### AI overview LLMs do not usually retain personal or persistent memory between interactions. Surrounding applications create the appearance of memory by storing messages, maintaining summaries, retrieving relevant information, and supplying it to the model. As conversations grow, this processing increases cost and latency, while context-window limits require older information to be removed, summarized, or stored elsewhere. ### Source excerpt In this article, we will learn how LLMs handle memory so that they are useful to end users in performing complex tasks that require conversation and holding context. ## Laravel MCP 1.0 Is Released DevFeed: [Laravel MCP 1.0 Is Released]() Original publisher: [Read original article]() Author: Eric L. Barnes Published: 2026-09-15T14:27:51Z Content type: release Language: en Sources: [Laravel]() Topics: [Laravel](), [Model Context Protocol (MCP)](), [OAuth](), [pkce](), [Caching](), [servers]() Tags: [caching](), [context-window](), [laravel](), [mcp](), [news](), [oauth](), [pkce](), [servers]() ### AI overview Laravel MCP 1.0 is the first stable release of Laravel's package for building Model Context Protocol servers. It adds protocol revision 2026-07-28 support, searchable tool catalogs, cache hints, stateless request handling, OAuth changes requiring PKCE, and Client ID Metadata Documents. ### Source excerpt Laravel MCP 1.0 ships protocol revision 2026-07-28, stateless servers, searchable tool catalogs, cache hints, and reworked OAuth with required PKCE. The post Laravel MCP 1.0 Is Released appeared first on Laravel News. Join the Laravel Newsletter to get Laravel articles like this directly in your inbox. ## Inside the AI Stack of an $8.3B AI Company's Product Team | Together AI DevFeed: [Inside the AI Stack of an $8.3B AI Company's Product Team | Together AI]() Original publisher: [Read original article]() Author: Aakash Gupta Published: 2026-09-14T23:05:28Z Content type: article Language: en Sources: [Product Growth]() Topics: [Artificial Intelligence](), [context](), [repo](), [context window](), [Developer experience](), [GitHub](), [Linear]() Tags: [ai](), [context](), [context-window](), [developer-experience](), [github](), [linear](), [product](), [repo](), [team](), [tools]() ### AI overview The article examines Together AI's AI-oriented product team and describes four parts of its working stack: a shared context repository, reusable skills for research and product documentation, an orchestrator for product leaders, and agent evaluations. It explains how shared context files and workflows support collaboration across product areas, including automated weekly status updates using Linear, GitHub, and strategy documents. ### Source excerpt I got a truly AI-pilled product team to demo the 4 key tools in their stack ## AWS Weekly Roundup: OpenAI GPT-6 Astra on Amazon Bedrock, Amazon Quick desktop GA, Kiro for students, and more (September 14, 2026) DevFeed: [AWS Weekly Roundup: OpenAI GPT-6 Astra on Amazon Bedrock, Amazon Quick desktop GA, Kiro for students, and more (September 14, 2026)]() Original publisher: [Read original article]() Author: Micah Walter Published: 2026-09-14T15:56:33Z Content type: news Language: en Sources: [AWS News Blog]() Topics: [Amazon Bedrock](), [Frontier Model](), [OpenAI](), [context window](), [browser](), [ChatGPT](), [codex](), [macOS](), [Windows](), [Mobile]() Tags: [agents](), [ai](), [ai-agents](), [amazon](), [amazon-bedrock](), [amazon-elastic-block-store-amazon-ebs](), [amazon-opensearch-service](), [amazon-quick-suite](), [aws](), [aws-lambda](), [aws-outposts](), [aws-transform](), [bedrock](), [browser](), [chatgpt](), [codex](), [context-window](), [frontier-model](), [google-play](), [gpt](), [kiro](), [launch](), [macos](), [mobile](), [openai](), [week-in-review](), [windows]() ### AI overview This AWS Weekly Roundup highlights the general availability of OpenAI GPT-6 Astra on Amazon Bedrock, describing its reasoning, writing, design, computer-use, browser-use, and million-token context-window capabilities. It also covers the Amazon Quick desktop app for macOS and Windows, including synchronized conversations and agents across desktop and mobile, plus other AWS launches and updates. ### Source excerpt There's a particular energy to mid-September in New York. Pumpkin spice lattes are flowing, temperatures are dropping, and it's nearly sweater weather. The city is back at full speed, and so is the AWS launch calendar. This week that energy showed up in a new frontier model on Amazon Bedrock, a desktop app for Amazon [...] ## SwiftUI Agent Skill: Install and use with AI coding tools DevFeed: [SwiftUI Agent Skill: Install and use with AI coding tools]() Original publisher: [Read original article]() Author: Antoine van der Lee Published: 2026-09-14T11:49:33Z Content type: article Language: en Sources: [SwiftLee]() Topics: [SwiftUI](), [Agent Skill](), [ai-coding](), [Code quality](), [context window](), [Command-line interface]() Tags: [agent-skill](), [ai-coding](), [ai-development](), [cli](), [code-quality](), [context-window](), [installation](), [open-source](), [swiftui]() ### AI overview This article introduces an open-source SwiftUI Agent Skill for AI coding tools. The skill helps agents build or refactor SwiftUI views, improve generated code quality, and load focused references only when they are relevant to a task. It also explains installation, updates, and compatibility considerations for the skills command-line tool. ### Source excerpt A SwiftUI Agent Skill that helps you build better views or refactor existing ones. It's the reality we're in today, and I honestly can't live without it anymore myself. Several skills helped me improve the code quality produced by agents, and I'm happy to introduce you to my open-source skill for SwiftUI. Before reading this ... -> The post SwiftUI Agent Skill: Install and use with AI coding tools appeared first on SwiftLee. ## Claude Managed Agents: How They Work and Where They Fit DevFeed: [Claude Managed Agents: How They Work and Where They Fit]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-09-14T11:29:41Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Harness](), [Claude](), [Artificial Intelligence](), [sdlc](), [context window](), [Network](), [Processes]() Tags: [agent](), [agents](), [ai](), [claude](), [context-window](), [infrastructure](), [network](), [platform](), [sandbox](), [sdlc](), [software](), [tools]() ### AI overview This article explains Claude Managed Agents, a hosted runtime and managed agent harness operated by Anthropic. It describes how the harness coordinates tools and execution, the sandbox provides isolated command and file access, and the session preserves durable task history outside the model's context window. It also discusses the additional platform layer needed to connect multiple agents across a business process and the SDLC. ### Source excerpt What Claude Managed Agents are, how the runtime works, and how platform teams connect several agents across the SDLC. ## Designing Reliable AI Agent Memory for Stale Facts and Policy Changes DevFeed: [Designing Reliable AI Agent Memory for Stale Facts and Policy Changes]() Original publisher: [Read original article]() Author: Raul Junco Published: 2026-09-12T12:10:58Z Content type: tutorial Language: en Sources: [System Design Classroom]() Topics: [AI Agent](), [context window](), [context]() Tags: [ai-agent](), [context](), [context-window](), [memory]() ### AI overview This article explains that AI agent memory should be treated as evidence rather than truth, especially when policies or other facts change. It recommends attaching version, scope, source, and authoritative-data checks to memory, while keeping the context window limited to the information needed for a task. ### Source excerpt Learn how to design reliable AI agent memory that handles stale facts, policy changes, scoped retrieval, conflict resolution, and safe deletion. ## Enable on-demand expertise with Agent Skills in Genkit Go DevFeed: [Enable on-demand expertise with Agent Skills in Genkit Go]() Original publisher: [Read original article]() Author: Daniela Petruzalek Published: 2026-09-12T11:04:33.891311Z Content type: tutorial Language: en Sources: [Google Developers Blog]() Topics: [Agent Skills](), [Agent Harness](), [context window](), [Go](), [Script]() Tags: [agent](), [agent-skills](), [architecture](), [context-window](), [developers](), [go](), [skills](), [workflows]() ### AI overview This article explains how Agent Skills in Genkit Go provide on-demand specialized expertise through progressive disclosure. Skills package instructions, references, and scripts in modular SKILL.md bundles, exposing only metadata initially and loading full content when a task requires it. ### Source excerpt To prevent context window bloat and reduce token consumption, Genkit Go introduces Agent Skills based on a progressive disclosure architecture. Developers can package specialized instructions, scripts, and references into modular SKILL.md bundles where only the frontmatter metadata is initially exposed to the agent's system prompt. When a task matches the skill's description, Genkit's middleware dynamically loads the full instruction body and associated assets, ensuring the model accesses precise workflows exactly when needed. ## A better way to build MCP servers with Laravel DevFeed: [A better way to build MCP servers with Laravel]() Original publisher: [Read original article]() Author: Pushpak Chhajed Published: 2026-09-11T12:01:00Z Content type: article Language: en Sources: [Laravel Blog]() Topics: [MCP](), [Laravel](), [MCP Server](), [context window](), [JSON Schema](), [Cloudflare]() Tags: [cloudflare](), [context-window](), [json-schema](), [laravel](), [mcp](), [mcp-server]() ### AI overview The article explains how Laravel MCP 1.0 uses searchable tool catalogs to avoid loading every MCP tool definition into an agent's context on every request. It describes the context costs of large tool surfaces and the evolution of the author's implementation. ### Source excerpt Every MCP tool loads on every request. Laravel MCP 1.0 fixes that with searchable tool catalogs: the same payload for 10 or 100 tools. ## DeepSeek V4.1 Flash now available on AI Gateway DevFeed: [DeepSeek V4.1 Flash now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [deepseek](), [Artificial Intelligence](), [API](), [Language models](), [AI-assisted coding](), [Claude Code](), [codex](), [cursor]() Tags: [ai](), [ai-gateway](), [api](), [caching](), [codex](), [context-window](), [cursor](), [deepseek](), [responses](), [tool](), [vercel](), [vision]() ### AI overview DeepSeek V4.1 Flash is now available through Vercel's AI Gateway, offering native image understanding, a 1 million token context window, responses up to 384,000 tokens, reasoning, tool use, and prompt caching. Developers can use it in Claude Code, Codex, Cursor, and other coding agents with the model name deepseek/deepseek-v4.1-flash. ### Source excerpt DeepSeek V4.1 Flash is now available on AI Gateway with native image understanding. V4.1 Flash has vision support and accepts text and images in the same request, so you can ask questions about screenshots, read charts, and extract information from visual content. The model has a 1 million token context window and supports responses up to 384,000 tokens, along with reasoning, tool use, and prompt caching. Its new architecture processes input and generates output with separate components, reducing the active computation needed for each stage. Use deepseek/deepseek-v4.1-flash as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select deepseek/deepseek-v4.1-flash in the agent. See the coding agents guide for details. Try DeepSeek V4.1 Flash in the model playground. 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. You can view all language models available on AI Gateway. Read more ## Ling 3.0 Flash Sante is now available on AI Gateway for free DevFeed: [Ling 3.0 Flash Sante is now available on AI Gateway for free]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-04T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Artificial Intelligence](), [context window]() Tags: [agentic](), [ai](), [ai-gateway](), [coding](), [context-window](), [free](), [healthcare](), [model](), [retrieval]() ### AI overview Ling 3.0 Flash Sante, a healthcare-focused model from inclusionAI, is available on AI Gateway for free through October 4. It supports medical reasoning, research, evidence retrieval, multi-step healthcare tasks, function calling, and a 256K-token context window. ### Source excerpt Ling 3.0 Flash Sante from inclusionAI is now available on AI Gateway, and free through October 4. Ling 3.0 Flash Sante is the healthcare-focused version of Ling 3.0 Flash. It's built for medical reasoning, research, evidence retrieval, and multi-step healthcare tasks. It has a 256K-token context window, supports function calling, and retains the base model's general reasoning, coding, and agentic capabilities. Choose a model ID based on what should happen after the free period: inclusionai/ling-3.0-flash-sante continues serving requests at standard rates after October 4. inclusionai/ling-3.0-flash-sante-free stops serving requests after October 4. Free requests remain visible in your usage and traces but show a cost of $0. Use the model: Try Ling 3.0 Flash Sante in the model playground, or see the free model page. Read more ## GLM-5.3 is 50% off through DigitalOcean on AI Gateway DevFeed: [GLM-5.3 is 50% off through DigitalOcean on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-02T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Digital Ocean](), [Language models](), [long-context](), [AI-assisted coding](), [Claude Code](), [codex](), [cursor]() Tags: [ai-gateway](), [claude-code](), [codex](), [coding-agents](), [context-window](), [cursor](), [digitalocean](), [language-models](), [model](), [tokens](), [vercel]() ### AI overview Vercel announces a 50% discount on GLM-5.3 through DigitalOcean on AI Gateway until September 8. The article explains the temporary promo model name, standard provider routing, model limits, spend tracking, and setup for coding agents. ### Source excerpt GLM-5.3 is 50% off on AI Gateway through Tuesday, September 8, in partnership with DigitalOcean. How to use the model during the offer period Using the promo name (zai/glm-5.3-promo-50) gets the discounted rate. It routes only to DigitalOcean, with no fallback to another provider, and it stops serving when the offer ends. Using the standard name (i.e., zai/glm-5.3) with provider options to sort DigitalOcean as the preferred provider keeps working after September 8 and routes across every provider that serves the model, at their usual rates. Because the promo name goes away when the offer ends, treat it as something you switch on for the window rather than hardcode. To keep the standard name in your code instead, pin the provider with order: ['digitalocean'] under providerOptions.gateway, which prefers DigitalOcean and falls back to the others if it cannot serve the request. GLM-5.3 takes text input, with a 1M token context window and a maximum output of 128K tokens. Discounted requests appear in your spend dashboard and carry a trace like any other request. Try GLM-5.3 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 zai/glm-5.3-promo-50 inside the agent. You can view all language models available on AI Gateway. Read more ## Gemini 3.8 Flash now available on AI Gateway DevFeed: [Gemini 3.8 Flash now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-09-02T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Artificial Intelligence](), [Language models](), [Google](), [context window](), [AI-assisted coding]() Tags: [ai](), [ai-gateway](), [coding-agents](), [context-window](), [flash](), [google](), [inference](), [language-models]() ### AI overview Vercel announces that Gemini 3.8 Flash from Google is available on AI Gateway, with a 1M-token context window, multimodal input, tool calling, web search, and a 65,536-token maximum output. The model is discounted by 50% through December 31 and is positioned as an improvement for software engineering, agent work, and multi-step reasoning. ### Source excerpt Gemini 3.8 Flash from Google is now available on AI Gateway. The model is 50% off through December 31st. It has a 1M token context window, accepts text, image, PDF, and video input, returns text, and supports tool calling and web search. Maximum output is 65,536 tokens. Gemini 3.8 Flash improves on prior Flash models at software engineering, agent work, and multi-step reasoning, at the same speed and cost as the previous release. Thinking is on by default. To use Gemini 3.8 Flash, set model to google/gemini-3.8-flash: 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, OpenCode, Cursor, Pi, and more and select google/gemini-3.8-flash inside the agent. Try Gemini 3.8 Flash in the model playground. 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. You can view all language models available on AI Gateway. Read more ## Using Six Scoped Subagents to Manage Context Windows DevFeed: [Using Six Scoped Subagents to Manage Context Windows]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-09-01T05:00:29Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [context window](), [long-context](), [Artificial Intelligence](), [Code](), [coding](), [Claude](), [Claude Code](), [codex](), [LangChain](), [Python](), [Cloud]() Tags: [agent](), [agents](), [ai](), [claude](), [claude-code](), [cloud](), [codex](), [coding](), [coding-agents](), [context-engineering](), [context-window](), [langchain](), [python]() ### AI overview This tutorial explains how splitting research work among six parallel subagents can reduce context-window noise and limit the state returned to an orchestrator agent. It also covers designing subagent protocols, maintaining an agent registry, and running parallel agent workflows. ### Source excerpt The harness determines what your orchestrator agent never sees, not the model. ## Scaling llms.txt with a Hierarchy of Files DevFeed: [Scaling llms.txt with a Hierarchy of Files]() Original publisher: [Read original article]() Author: Kyan Yang Published: 2026-09-01T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [navigation](), [Website]() Tags: [agents](), [context-window](), [documentation](), [engineering](), [files](), [generation](), [navigation]() ### AI overview Mintlify rebuilt llms.txt generation as a hierarchy of files to keep large documentation sites within the 100,000-character limit while preserving access to pages. In tests across 200 tasks on ten documentation sites, the improved version completed tasks 52.1% faster and used 44.8% fewer tokens. ### Source excerpt Large documentation sites were hitting Mintlify's 100,000-character llms.txt limit and omitting pages. We rebuilt generation as a hierarchy of files so agents can reach every page without loading the entire index. ## Need to know: How Webflow keeps secrets out of agent context DevFeed: [Need to know: How Webflow keeps secrets out of agent context]() Original publisher: [Read original article]() Author: Webflow Security Team Published: 2026-08-28T00:00:00Z Content type: opinion Language: en Sources: [Webflow Blog]() Topics: [AI Agent](), [ai-coding](), [Security](), [Command-line interface](), [Artificial Intelligence](), [Open Source](), [Amazon Web Services]() Tags: [agent](), [ai](), [ai-agent](), [ai-coding](), [aws](), [cli](), [context-window](), [open-source](), [secrets](), [security]() ### AI overview Webflow describes how an AI coding agent exposed a live AWS session token during debugging and presents ctxcop, an open source CLI that removes secrets from agent context before they reach the model. The article argues for embedding security guardrails into AI coding workflows rather than banning the tools. ### Source excerpt An AI agent nearly leaked an AWS token during a debug session. Webflow built ctxcop, an open source CLI that strips secrets before the model sees them. ## 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... ## Qwen 3.8 Flash now available on AI Gateway DevFeed: [Qwen 3.8 Flash now available on AI Gateway]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-08-26T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [qwen](), [Artificial Intelligence](), [SDKs](), [AI-assisted coding](), [long-context](), [Claude Code](), [codex](), [cursor]() Tags: [ai](), [ai-gateway](), [api-keys](), [claude-code](), [codex](), [coding-agents](), [context-window](), [cost](), [cursor](), [opencode](), [pricing](), [qwen](), [routing](), [sdk](), [tokens](), [vercel]() ### AI overview Qwen 3.8 Flash from Alibaba is now available through Vercel AI Gateway. The model accepts text and images, supports a 1-million-token context window, and can generate responses of up to 65,000 tokens. It is recommended for coding, tool use, and multi-step agent workflows, and can be used through the AI SDK, coding agents, and the model playground. AI Gateway offers unified model access, usage and cost tracking, reliability features, reporting, retention controls, API key budgets, routing, and provider pricing without markup or inference platform fees. ### Source excerpt Qwen 3.8 Flash from Alibaba is now available on AI Gateway. It takes text and images as input, serves a context window of 1 million tokens, and can return up to 65k tokens in a response. Alibaba recommends it for coding, tool use, and multi-step agent workflows. To use Qwen3.8-Flash, set model to alibaba/qwen3.8-flash in the AI SDK: 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 alibaba/qwen3.8-flash inside the agent. Try Qwen3.8-Flash in the model playground. 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. Read more ## Why AI coding agents need context graphs DevFeed: [Why AI coding agents need context graphs]() Original publisher: [Read original article]() Author: Talia Kohan Published: 2026-08-25T16:00:00Z Content type: article Language: en Sources: [Postman Blog]() Topics: [AI-assisted coding](), [Graphs](), [coding](), [API](), [internal developer platform](), [context window](), [long-context]() Tags: [ai-coding-agents](), [api-governance](), [apis](), [context-window](), [developer](), [developer-platform](), [engineering](), [general](), [graphs](), [knowledge-graphs]() ### AI overview The article argues that AI coding agents struggle in real codebases primarily because they lack access to a knowledge graph connecting code, APIs, services, ownership, dependencies, policies, and related organizational context. It describes service catalogs, API registries, ownership maps, dependency graphs, and internal developer platforms as different forms of the same underlying structure. It also argues that simply increasing the context window does not solve retrieval and context-quality problems. ### Source excerpt AI coding agents don't fail from small context windows. They fail without a knowledge graph of your code, APIs, and vendors. The post Why AI coding agents need context graphs appeared first on Postman Blog. ## Context Engineering for Coding Agents DevFeed: [Context Engineering for Coding Agents]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-08-25T05:01:37Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [context window](), [AI-assisted coding](), [coding](), [Claude](), [codex]() Tags: [agents](), [claude](), [codex](), [coding-agents](), [context](), [context-engineering](), [context-window](), [harness]() ### AI overview This tutorial explains context engineering for coding agents, focusing on memory, skills, LSP servers, compaction, and feedback loops. It presents these techniques as ways to keep an agent's context high-signal and improve coding-agent performance. ### Source excerpt The 4 harness components that keep your context window high-signal. ## What makes a good AI coworker? With OpenAI's Codex product lead DevFeed: [What makes a good AI coworker? With OpenAI's Codex product lead]() Original publisher: [Read original article]() Author: info@1password.com (Chris Fowler) Published: 2026-08-25T00:00:00Z Content type: article Language: en Sources: [Blog on 1Password Blog]() Topics: [Artificial Intelligence](), [codex](), [OpenAI](), [long-context](), [Filesystems](), [coding](), [cursor]() Tags: [agent](), [agentic](), [agents](), [ai](), [ai-coding](), [autonomous](), [codex](), [context-window](), [cursor](), [dev](), [developers](), [engineering](), [filesystems](), [memory](), [openai](), [podcast](), [podcasts]() ### AI overview An episode featuring OpenAI Codex product lead Rohan Varma explores what makes AI agents effective coworkers. It focuses on shared context, durable memory and state outside the context window, filesystem-based task continuity, and steerability so people can understand and guide agent output. ### Source excerpt Zero-Shot Learning is a podcast about how AI is built, secured, and deployed. Hosted by Nancy Wang, 1Password CTO, and Dev Tagare, Senior Director of Engineering at Google Gemini, it offers a builder's view of the architecture and complex decisions involved in shipping AI. In this episode, Rohan Varma, Product Lead for Codex at OpenAI, described what happens when teams move from using agents for one-off tasks to enabling autonomous coworkers. Having worked on AI coding products at Cursor and OpenAI, Ro understands what people need to work effectively with agents and what agents need to work effectively with people. What makes a good (agentic) coworker? With any coworker, collaboration works best when everyone is working from the same context, toward a shared goal. Human coworkers are accustomed to working toward shared goals. With proper context and resources, they can divide work without losing sight of how their contribution affects the team. The difference between teams of people and agents is that people don't need to be told how to remember things. Everything they do carries historical context. When a team works together, their shared knowledge expands exponentially. Agents work within context windows, a temporary working memory that fills as a task continues. When the window is full, the system has to summarize the work without losing decisions and constraints that could cause the agent to miss crucial directives. State is a fundamental building block for making an agent feel more like a coworker. Without memory, every time you prompt an agent, it's kind of like its first day on planet Earth." -Rohan Varma, Codex Product Lead, OpenAI To be a useful long-term collaborator, an agent's memory has to exist outside its context window. The system has to preserve the work durably to understand which files were changed, which decisions were made, which results were gathered, and which tasks are yet to be completed. That shared state lets one agent resume a task, anoth ## Preloading Knowledge Into a Model Instead of Retrieving It DevFeed: [Preloading Knowledge Into a Model Instead of Retrieving It]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-24T17:13:39Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Retrieval Augmented Generation (RAG)](), [Caching](), [long-context](), [Inference](), [Self-hosted](), [model-deployment](), [GPU]() Tags: [caching](), [compute](), [context-window](), [deployment](), [inference](), [rag](), [retrieval](), [self-hosted](), [storage]() ### AI overview This article introduces a three-part RAG Systems course about preloading a knowledge corpus into a model's stored KV cache so subsequent queries can skip retrieval, chunking, and embedding. It covers naive, compressed, modular, and trained preloading, along with context limits, provider and self-hosted economics, cache compression constraints, and production deployment. ### Source excerpt How to process your corpus once, skip retrieval entirely, and serve every query from a stored cache. Three parts covering the full spectrum. ## Artificial Intelligence: Glossary DevFeed: [Artificial Intelligence: Glossary]() Original publisher: [Read original article]() Author: Caleb Sponheim Published: 2026-08-21T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [AI Agent](), [AI Development](), [Algorithms](), [Prompt Engineering]() Tags: [agentic-ai](), [agents](), [ai-agent](), [ai-definitions](), [ai-evals](), [ai-glossary](), [ai-glossary-for-ux](), [ai-hallucination](), [ai-terminology](), [ai-terminology-for-product-teams](), [ai-terms](), [ai-terms-for-designers](), [ai-vocabulary](), [article](), [artificial-intelligence](), [artificial-intelligence-glossary](), [context-window](), [genai-glossary](), [generative-ai](), [generative-ui](), [glossary](), [knowledge-cutoff](), [large-language-model](), [machine-learning](), [model-context-protocol](), [prompt-engineering](), [prompt-injection](), [rag](), [tokens](), [ux](), [vibe-coding]() ### AI overview A plain-language glossary of artificial-intelligence terminology used in products and UX work. It explains concepts including agents, agentic systems, AI development, algorithms, AI-generated content, and AI-related claims, while noting that terminology can vary among vendors and researchers. ### Source excerpt Plain-language definitions of the AI terms that come up in product and design work, from tokens and context windows to agents, evals, and prompt injection. ## Gradle Is Going Agentic DevFeed: [Gradle Is Going Agentic]() Original publisher: [Read original article]() Author: Laura Kassovic Published: 2026-08-19T04:00:00Z Content type: opinion Language: en Sources: [The Gradle Blog]() Topics: [Gradle](), [Tooling](), [benchmarking](), [configuration](), [Cache]() Tags: [agentic](), [benchmarking](), [cache](), [configuration](), [context-window](), [gradle](), [tooling]() ### AI overview Gradle describes Agentic Gradle, a project focused on helping agents use Gradle effectively. It plans to provide official Gradle skills and add Gradle features for build workflows that agents make more difficult, supported by repeatable benchmarking scenarios. ### Source excerpt More and more of the people who run Gradle every day aren't typing ./gradlew build themselves. They're asking an agent to run a build, paste it the failure, then ask it to fix the thing that failed. The agent is now part of the build loop, whether the build tool invited it or not. This is not a Gradle-specific oddity. Every build tool is being driven by a new kind of user: not a person with muscle memory for flags and log output, but a model with a terminal, a context window, and alarming confidence. New user, new failure modes. We have hit enough of them that pretending this is temporary started to feel silly. So we started a project. We're calling it Agentic Gradle. The practical version has two buckets: skills that teach agents how to use Gradle effectively, and new Gradle features for the places where agents make today's build tooling awkward. Not because Gradle is bad at this, but because agents push builds in ways we never had to support before. Picking it up meant we didn't do something else this cycle. We'll get to that, because it is the more interesting part of the story. But first, what we're actually building. What this looks like in practice There are three pieces, in the order we're putting real time behind them. Official Gradle skills. A skill is a small, focused set of instructions that teaches an agent how to do something specific with Gradle: read a build failure, run the right task, understand what a Build Scan is telling it. Skills also make vague prompts less dangerous. Give an agent "speed up my build" and, left to its own devices, it'll reach for whatever pattern it saw most often on the internet, which is often years out of date. A focused Gradle performance Skill can keep it closer to the boring advice that works: enabling the configuration cache, reaching for a version catalog, avoiding configuration-time anti-patterns it wouldn't otherwise think to check. We've been experimenting with these throughout the year, and a few are close to ready [Next page]()