# docs Published articles for docs. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Mintlify rebuilds automations around pre-built templates for common use cases DevFeed: [Mintlify rebuilds automations around pre-built templates for common use cases]() Original publisher: [Read original article]() Author: Patrick Foster Published: 2026-09-15T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Automation](), [Documentation](), [changelog](), [Pull Request](), [Markdown](), [YAML]() Tags: [announcements](), [automation](), [changelog](), [docs](), [documentation](), [execution](), [markdown](), [prompt](), [quality](), [rest]() ### AI overview Mintlify rebuilt its automations around pre-built templates for common use cases, including syncing content with code changes, generating changelogs, and improving documentation from user feedback and support signals. Custom prompts remain available for specialized tasks. ### Source excerpt We redesigned automations for quicker setup with pre-built automations optimized for common use cases. Choose the right automations for your project and you're set. No context engineering required. ## A Week of Symfony #1028 (September 7-13, 2026) DevFeed: [A Week of Symfony #1028 (September 7-13, 2026)]() Original publisher: [Read original article]() Author: Javier Eguiluz Published: 2026-09-13T07:05:00Z Content type: news Language: en Sources: [Symfony Blog]() Topics: [Code](), [OAuth 2.0](), [OpenID connect (OIDC)](), [Security]() Tags: [cache](), [code](), [development](), [docs](), [http](), [pull-requests](), [security](), [symfony]() ### AI overview Symfony's weekly roundup covers standalone framework bundles, Docker-style console subcommands, expanded OAuth2 and OpenID Connect support, and SymfonyCon Warsaw 2026 announcements. It also reports merged pull requests, closed issues, and selected development fixes. ### Source excerpt This week, Symfony introduced standalone bundles for the framework features (MessengerBundle, HttpClientBundle, PropertyInfoBundle, etc.), added Docker-style console subcommands, and expanded OAuth2 and OpenID Connect support. In addition, we announced the... ## Set Up Cloud OIDC From the Pulumi CLI DevFeed: [Set Up Cloud OIDC From the Pulumi CLI]() Original publisher: [Read original article]() Author: Sean Yeh Published: 2026-09-11T00:00:00Z Content type: tutorial Language: en Sources: [Pulumi]() Topics: [OpenID connect (OIDC)](), [Command-line interface](), [AWS IAM](), [Cloud](), [AWS Identity and Access Management (IAM)](), [Azure](), [Google Cloud Platform (GCP)]() Tags: [automated](), [aws](), [azure](), [cli](), [cloud](), [configuration](), [docs](), [esc](), [google-cloud](), [how-to](), [iam](), [identity](), [oidc](), [openid-connect](), [product](), [pulumi](), [pulumi-cli](), [security](), [terminal](), [workflow]() ### AI overview This tutorial explains how to use the Pulumi CLI command pulumi env setup to configure Pulumi ESC as an OIDC provider for AWS, Azure, and Google Cloud. It covers interactive onboarding, non-interactive flags for scripts and agents, cloud credentials, account selection, access policies, and automatic creation of identity providers, IAM roles, policy attachments, and ESC environments. ### Source excerpt Pulumi ESC can act as an OpenID Connect (OIDC) provider for AWS, Azure, and Google Cloud, issuing short-lived, signed tokens that these clouds exchange for temporary credentials. This eliminates hard-coded credentials and improves your security posture. Last year, we introduced an onboarding flow in the Pulumi Cloud console that makes it super easy to configure OIDC for your cloud provider in a few guided steps. We're bringing Pulumi Cloud into the CLI so agents can use its capabilities directly from the terminal, without requiring a human to complete steps in the console. The new pulumi env setup command brings OIDC onboarding to that workflow, with interactive prompts for guided setup and non-interactive flags for scripts and agents. pulumi env setup - how it works Run the command with your desired cloud provider (aws, azure, gcp). For example: pulumi env setup aws The command then asks what it needs to configure your cloud, including your credentials, the accounts to configure, and the level of access. The questions differ per cloud. For AWS, it asks: How to authenticate to AWS. It uses the credentials you already have, or it signs you in with AWS SSO. Which accounts to configure. Which policy to attach to the OIDC role. Choose AdministratorAccess for Pulumi Deployments, ReadOnlyAccess for Pulumi Insights, or any other policy ARN. Then, it will print out the plan: About to configure OIDC for organization my-org: account 111111111111: create role pulumi-esc-oidc-622e86ea-319ba4c675bb3c00-role attach arn:aws:iam::aws:policy/AdministratorAccess create ESC environment my-org/aws-login/sandbox-account-env Proceed? [yes/no] After you confirm, the command creates the identity provider, the IAM role, and the policy attachment in each account. It then creates one ESC Environment per account, with the aws-login provider already configured. Non-interactive setup You can also run the command without interactive prompts by passing in the necessary flags. Each cloud has its ow ## Testing Astra 6 v Fable 5.1 on a Gradle docs bug DevFeed: [Testing Astra 6 v Fable 5.1 on a Gradle docs bug]() Original publisher: [Read original article]() Author: Laura Kassovic Published: 2026-09-09T04:00:00Z Content type: article Language: en Sources: [The Gradle Blog]() Topics: [Gradle](), [Testing](), [ai-coding](), [Benchmark](), [Fable](), [Documentation](), [bug]() Tags: [ai-coding](), [benchmark](), [bug](), [docs](), [fable](), [gradle](), [testing]() ### AI overview An engineering blog compares Astra 6 and Fable 5.1 after each agent fixes the same Gradle Kotlin DSL documentation bug. Both fixes passed independent judging, while the comparison examines cost, speed, and maintainability. The author emphasizes that the result is based on one run per model, one judge, and one bug. ### Source excerpt On the afternoon of September 7th, claude-fable-5-1 was handed a git repository, a GitHub issue, and fifty turns to fix it. Just over three hours later, gpt-6-astra finished the same assignment in another worktree. Same issue. Same constraints. Different CLI wrapped around each model: claude-code for Fable, codex for Astra. Both Agents fixed the bug. Both results were graded as successes by an independent judge. But these results were quite different. You would be forgiven for wondering why an engineering blog is running a two-model bakeoff on a single documentation bug, in a year when everybody and their intern has published an AI coding benchmark. Here's the honest answer: we wanted to know which one actually did the better job, as a side quest of the Agentic Gradle project. But "better" was never going to mean pass-or-fail. Both of these agents passed; if that were the whole story, this post would be four sentences long. What actually separates a fix worth merging from a fix worth sending back is cost, speed, and whether the result is something we would want to maintain, and those three do not all point the same direction, as you are about to see. So: one bug, two agents, and a very literal stopwatch. Here is what this looks like when you actually read the agents' transcripts. Real talk up front: this is n=1. One run per model, one judge, one bug. That's a thin base for anything you'd call a leaderboard, and I'll say so again at the end, but it didn't stop me from landing on an opinion by the time I'd finished reading both transcripts. The bug, briefly Issue #34751, filed August 21st by our very own cobexer, is the kind of bug that is very easy to describe and mildly annoying to fix. In the Kotlin DSL API docs, a type like Attribute linked to the Java 21 Javadoc. It should have linked to Java 17, because Gradle targets Java 17. The reason is almost embarrassingly mundane once you see it. Gradle is built with a JDK 21 toolchain but targets JDK 17, which i ## Announcing rustup 1.29.1 DevFeed: [Announcing rustup 1.29.1]() Original publisher: [Read original article]() Author: The Rustup Team Published: 2026-09-01T00:00:00Z Content type: release Language: en Sources: [Rust Blog]() Topics: [releases]() Tags: [bug](), [cli](), [concurrency](), [docs](), [http](), [releases](), [rust](), [toolchain](), [update](), [windows]() ### AI overview Rustup 1.29.1 improves concurrent update and component-install operations, adds local HTTP documentation serving, and changes several installation behaviors. The release also fixes Windows-related installation issues and updates target terminology. ### Source excerpt The rustup team is happy to announce the release of rustup version 1.29.1. Rustup is the recommended tool to install Rust, a programming language that empowers everyone to build reliable and efficient software. What's new in rustup 1.29.1 The headlines of this release are: Concurrency in certain rustup operations has been improved: When running rustup update, rustup will first check for possible updates in parallel. pr#4752 When running rustup component add with multiple components, they will be installed concurrently. pr#4790 Implicit installation of the active toolchain in rustup-init and rustup invocations has been deprecated where deemed unnecessary and will now produce a warning. pr#4840 Please see our blog post for more details regarding this change. rustup doc now supports the --serve flag which allows serving the docs over local HTTP. This should help users with containerized browser and/or rustup setups. pr#4986 Installing i686-pc-windows-* host toolchains on 64-bit Windows now requires --force-non-host. pr#4935 rustup-init will no longer leave unexpected files on disk after cancelled installations. pr#4996 A bug has been fixed which might cause Windows installation to fail when using rustup-init.sh. pr#4756 "Target triple" has been renamed to "target tuple" across the project to reflect the new terminology. pr#4743 pr#4827 pr#4834 Please note that this is not a breaking change in the CLI since the existing options such as --target are not using this terminology. In addition, rustup now officially supports aarch64-pc-windows-gnullvm as a host platform. pr#4523 Further details are available in the changelog! How to update If you have a previous version of rustup installed, getting the new one is as easy as stopping any programs which may be using rustup (e.g. closing your IDE) and running: $ rustup self update Rustup will also automatically update itself at the end of a normal toolchain update: $ rustup update If you don't have it already, you can get rustup ## Announcing Console IV: the website and Console as one app DevFeed: [Announcing Console IV: the website and Console as one app]() Original publisher: [Read original article]() Author: Aditya Oberai Published: 2026-08-31T00:00:00Z Content type: release Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [Website](), [Command-line interface](), [Documentation](), [SDK](), [Svelte]() Tags: [app](), [cli](), [docs](), [products](), [projects](), [sdks](), [svelte]() ### AI overview Appwrite announces Console IV, a fourth-generation Console that brings documentation, the CLI, Explorer, Terminal, Command Center, and projects together in one application. The release is intended to reduce context switching while preserving existing projects, APIs, bookmarks, API keys, and SDK code. ### Source excerpt Console IV puts the docs, CLI, Explorer, and your projects in one app so you stop bouncing between the IDE, docs, SDKs, terminals, and the agent. ## A new getting started experience for ClickHouse Managed Postgres DevFeed: [A new getting started experience for ClickHouse Managed Postgres]() Original publisher: [Read original article]() Author: Cristina Albu; Yashpreet Bathla Published: 2026-08-28T12:55:15Z Content type: article Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [data](), [Provisioning](), [real-time](), [Replication](), [Databases](), [Command-line interface]() Tags: [analytics](), [cli](), [clickhouse](), [cloud](), [data](), [docs](), [getting-started](), [guide](), [onboarding](), [postgres](), [real-time](), [replication]() ### AI overview ClickHouse Managed Postgres introduces a four-step onboarding experience that guides users from provisioning a Postgres service to loading data, querying it, and replicating it to ClickHouse for real-time analytics. ### Source excerpt See how a four-step onboarding flow helps users move from provisioning ClickHouse Managed Postgres to querying operational data and running real-time analytics with ClickHouse. ## How Uno Platform uses .NET, MCP, and AI to build high quality apps DevFeed: [How Uno Platform uses .NET, MCP, and AI to build high quality apps]() Original publisher: [Read original article]() Author: Sam Basu Published: 2026-08-27T17:00:00Z Content type: article Language: en Sources: [.NET Blog]() Topics: [.NET](), [AI-assisted coding]() Tags: [ai](), [ai-agents](), [api](), [browser](), [c-sharp](), [cross-platform](), [developer-stories](), [docs](), [documentation](), [github-copilot](), [http](), [mcp](), [model-context-protocol](), [net](), [server](), [servers](), [skiasharp](), [tooling](), [uno-platform](), [xaml]() ### AI overview Uno Platform describes using two C# Model Context Protocol servers to give AI agents current documentation and the ability to inspect and drive running cross-platform .NET apps. ### Source excerpt How Uno Platform built two Model Context Protocol servers in C# so AI agents can ground themselves in real documentation and then see and drive a running cross-platform .NET app. The post How Uno Platform uses .NET, MCP, and AI to build high quality apps appeared first on .NET Blog. ## The Python documentation is now available in Russian! DevFeed: [The Python documentation is now available in Russian!]() Original publisher: [Read original article]() Author: Stan Ulbrych Published: 2026-08-22T00:00:00Z Content type: news Language: en Sources: [Python Insider]() Topics: [Python](), [Accessibility]() Tags: [blog](), [community](), [contributors](), [developer](), [docs](), [documentation](), [guide](), [python]() ### AI overview The Python documentation is now available in Russian, thanks to community contributors. The article also invites volunteers to help translate and maintain documentation in other languages. ### Source excerpt The official blog of the Python core development team. ## Vercel Agent is now available in Slack code channels DevFeed: [Vercel Agent is now available in Slack code channels]() Original publisher: [Read original article]() Author: Shilpa Apte Published: 2026-08-20T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Slack](), [Code](), [Pull Request](), [Authorization]() Tags: [agent](), [bugs](), [code](), [coding](), [dependency](), [docs](), [enterprise](), [errors](), [logs](), [pull-requests](), [review](), [slack](), [vercel]() ### AI overview Vercel Agent is available in Slack code channels, enabling teams to assign coding work, follow deployments and diagnostics, review pull requests, and provide additional instructions in conversation. The feature is in public beta for Pro and Enterprise teams. ### Source excerpt Vercel Agent now works in Slack code channels, a new kind of channel launched today for working with a coding agent. Anyone in the channel can follow the work, give Agent new instructions, and review the code it writes. Choose Create a code channel from the Slack sidebar, select Vercel as the agent, and describe what you need to get started. You can also ask Agent to create one from an existing channel or thread. It brings that context with it to the new channel. Use code channels to investigate incidents, write and review code as a team, or manage ongoing work such as dependency upgrades and migrations. Inside a Vercel Agent code channel: Follow the work: Agent posts relevant deployments, logs, errors, and diffs in the channel as it works. Talk without repeated @Vercel mentions: Agent follows the conversation, recognizes which messages are for it, and continues when the team gives it more work. Review pull requests: Ask Agent for a PR review and it posts its findings in the channel. It can find bugs outside the diff, and explain failing checks and their root causes. Approve every change: Agent is read-only by default and never exceeds the requester's permissions. Before making a change, it drafts a plan and waits for approval. For every action, Vercel records who requested and approved it and what Agent ran. Stop work at any time: The person who created the code channel can cancel an active task. Vercel Agent in Slack code channels is available in public beta for Pro and Enterprise teams. Add Vercel to Slack, learn about Slack Code, or read the docs. Read more ## Agent Night demo recap: Evil Martians on making your docs discoverable to agents DevFeed: [Agent Night demo recap: Evil Martians on making your docs discoverable to agents]() Original publisher: [Read original article]() Author: WorkOS Published: 2026-08-17T19:04:06Z Content type: article Language: en Sources: [WorkOS Blog]() Topics: [GitHub](), [dev-tools](), [Large Language Model](), [Search engine optimization (SEO)]() Tags: [agent](), [agents](), [developer-tools](), [docs](), [github](), [llm](), [model-training](), [retrieval]() ### AI overview Irina Nazarova's Agent Night demo recap explains how developer-tool documentation can be discovered by agents through websites and GitHub repositories. It distinguishes retrieval, which depends on access to documentation at request time, from training, which depends on whether content enters model corpora, and emphasizes repository descriptions, topics, licensing, and Markdown access. ### Source excerpt Irina Nazarova's Agent Night lightning demo: why GitHub, not your docs site, is the path into model training sets, and how Evil Martians measured all of it. ## Why we removed AI solutions from Flare DevFeed: [Why we removed AI solutions from Flare]() Original publisher: [Read original article]() Author: Freek Van der Herten (freek@spatie.be) Published: 2026-08-13T10:30:30Z Content type: article Language: en Sources: [freek.dev - all blogposts]() Topics: [debug](), [AI-assisted coding](), [MCP Server](), [Command-line interface](), [Documentation]() Tags: [agent](), [agents](), [ai](), [cli](), [coding-agents](), [debug](), [debugging](), [developers](), [docs](), [flare](), [mcp](), [mcp-server](), [workflow]() ### AI overview The article explains why Flare removed its former AI-generated solutions and replaced them with a workflow for debugging with modern coding agents. The new workflow uses an MCP server, CLI, Copy for AI prompts, and agent-friendly documentation. ### Source excerpt We explain why Flare's old AI-generated solutions no longer fit the way developers debug with modern coding agents. The replacement is a better workflow built around the MCP server, CLI, Copy for AI prompts, and agent-friendly docs. Read more ## Enterprise Managed Users is now generally available DevFeed: [Enterprise Managed Users is now generally available]() Original publisher: [Read original article]() Author: Bel Curcio Published: 2026-08-11T20:38:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel](), [Single sign-on (SSO)](), [Authentication](), [Provisioning]() Tags: [authentication](), [docs](), [enterprise](), [identity](), [provisioning](), [sign-in](), [sso](), [updates](), [vercel]() ### AI overview Vercel Enterprise Managed Users is now generally available, giving organizations centralized control over accounts on verified domains through SAML SSO, Directory Sync, and IdP-managed profiles. ### Source excerpt Enterprise Managed Users (EMU) gives organizations full control over the Vercel accounts tied to their verified domains. It makes the organization's identity provider the single source of truth for authentication and account lifecycle, so accounts on company domains are governed centrally rather than owned by individuals. Now generally available IdP-enforced sign-in: Managed users sign in through SAML SSO only. All other login methods, including email OTP, GitHub, Google, and GitLab, no longer work for managed accounts. SCIM provisioning & lifecycle: Directory Sync creates, updates, and deprovisions managed users automatically, keeping accounts in sync with your IdP. Owned by your organization: Profile settings are managed through your IdP rather than by the individual. Self-serve enablement: Turn EMU on for a verified domain in Team Settings under Security & Privacy, and extend it across multiple eligible teams in a single step. Requires an Enterprise plan, enforced SAML SSO, active Directory Sync, and at least one verified domain. In Beta, available on request Hobby team transition: Members with an existing personal account on a newly managed domain are guided to add a personal email (keeping their hobby projects) or delete the account, then continue to their work through SSO. Automatic conversion: Personal accounts with no content or activity are archived automatically, and their owners land in a new managed account at their next SSO sign-in. To request access, contact your account team. Learn more in the Enterprise Managed Users and Hobby team transition docs. Read more ## Keeping documentation synchronized with product changes using GitHub and an agent DevFeed: [Keeping documentation synchronized with product changes using GitHub and an agent]() Original publisher: [Read original article]() Author: Zaid Daba'een Published: 2026-08-08T15:01:28Z Content type: tutorial Language: en Sources: [DeveloperHub.io]() Topics: [Documentation](), [Code](), [GitHub](), [Pull Request]() Tags: [agent](), [docs](), [engineering](), [github](), [pull-request](), [repository]() ### AI overview This article explains how to reduce drift between product code and documentation by storing both in Git repositories and giving an agent a range of commits to update. It describes DeveloperHub's two-way GitHub Sync, branch-based pull requests, and read-only dry-run checks before changes are published. ### Source excerpt The code ships. The docs don't. So we turned that gap into a diff, pointed an agent at it, and stopped losing the race. ## Android Skills: Philosophy, Selection Criteria, and Evaluation Methodology DevFeed: [Android Skills: Philosophy, Selection Criteria, and Evaluation Methodology]() Original publisher: [Read original article]() Author: Android Developers (noreply@blogger.com) Published: 2026-08-06T16:00:00Z Content type: opinion Language: en Sources: [Android Developers Blog]() Topics: [Android skills](), [Large Language Model](), [Android Studio](), [Command-line interface]() Tags: [agent](), [agents](), [ai-assisted-coding](), [android-skills](), [android-studio](), [antigravity](), [cli](), [docs](), [gemini]() ### AI overview Android Developer Relations explains how official Android Skills are selected, focusing on verifiable knowledge gaps in state-of-the-art models and fast-moving topics. The article also discusses context costs, evaluation requirements, model compatibility, and use of the Android Knowledge Base. ### Source excerpt Posted by Jose Alcérreca, Developer Relations Engineer, Android Developer Relations We released the official Android Skills in April, and the response surpassed all our expectations. In this blog post, I'll address some of the feedback we received, explaining the philosophy and methodology behind the project. Hopefully, this will also help you understand what happens behind the scenes when you install and use skills, allowing you to make better use of tokens and your own time. Why are there so few official skills? Currently, we only consider new skills when there's a verifiable knowledge gap in state-of-the-art (SOTA) models. Put simply: you don't need to teach the model what it already knows. (Though there are a few exceptions--read on!) We've released around 20 official skills so far, and they intentionally target highly specific, fast-moving areas that standard models aren't fully grounded on yet--things like AGP 9, Navigation 3, advanced Camera APIs, and Perfetto SQL. What about core, more general, skills? Every installed skill injects 100-200 tokens into the baseline context of every task you start. If that skill actually activates, that count can quickly jump into the thousands. In most cases, hoarding basic skills is both counterproductive and expensive. Before installing a skill for writing basic Kotlin or Compose, consider if your LLM of choice really needs it, or if it knows those topics well enough already. Evaluating skills Before their release, each skill is tested against a comprehensive set of evals that prove that the skill delivers clear value. These evals should pass when the skill is active, and fail otherwise. Evals are to skills what integration tests are to code. timeout_s: 1200 repository: url: [redacted - internal git repo] working_dir: wear_compose_m3_empty_app category_ids: - wear prompt: |- Add a horizontal pager to MainActivity.kt. Have three pages in the pager. Each page should contain the text "Page 1", "Page 2", and "Page 3" respectively ## 11 Context-Engineering Tips for Using Coding Agents Efficiently DevFeed: [11 Context-Engineering Tips for Using Coding Agents Efficiently]() Original publisher: [Read original article]() Author: Paul Iusztin Published: 2026-08-04T11:04:10Z Content type: tutorial Language: en Sources: [Decoding ML]() Topics: [AI-assisted coding](), [Large Language Model](), [Documentation](), [anthropic](), [codex](), [Obsidian]() Tags: [2026](), [anthropic](), [codex](), [coding-agents](), [context-engineering](), [docs](), [tokens](), [weekly]() ### AI overview The author shares 11 context- and harness-engineering techniques for using coding agents while controlling token use. The advice includes progressive disclosure, detailed planning with cheaper models handling execution, LLM wikis for project context, and subagents that return summaries. ### Source excerpt Context engineering techniques to avoid wasting tokens on what doesn't matter ## How to move documentation from Google Docs to Document360 DevFeed: [How to move documentation from Google Docs to Document360]() Original publisher: [Read original article]() Author: Janeera Published: 2026-08-04T05:34:23Z Content type: tutorial Language: en Sources: [Knowledge Management Tips, Best Practices and More]() Topics: [Documentation](), [migration](), [knowledge-management](), [Google]() Tags: [docs](), [google](), [knowledge-base-software](), [knowledge-management](), [migration]() ### AI overview This article explains why growing documentation becomes difficult to find, version, maintain, and trust in Google Docs. It presents moving to Document360 as a way to organize documentation in a knowledge base and describes signs that a migration may be needed. ### Source excerpt It always starts the same way One Google Doc? Completely manageable. You create ... The post Stuck in Google Docs? Make the move from Google Docs to Document360 appeared first on Document360. ## Developing with Fedora, first flock, and not the last! DevFeed: [Developing with Fedora, first flock, and not the last!]() Original publisher: [Read original article]() Author: Cornelius Emase Published: 2026-08-03T08:00:00Z Content type: opinion Language: en Sources: [Fedora Magazine]() Topics: [Fedora](), [Linux]() Tags: [2026](), [community](), [conference](), [contributors](), [design](), [docs](), [event](), [events](), [flock](), [flock-2026](), [fosdem](), [gnu-linux](), [personal-reflection](), [podcast](), [recognition](), [support]() ### AI overview A personal reflection on attending Flock 2026, the author's first Fedora conference. It covers appreciation for organizers, sponsors, mentors, and local community supporters; participation in the Mentor Summit organizing team; Fedora's inclusive community; contributor recognition; and talks about design, documentation, FOSDEM, and SCaLE. ### Source excerpt Flock 2026 was my first Fedora conference, and it won't be my last. I came home with new ideas, new friendships, and even a new project to work on for next year. Appreciation I want to start by appreciating the Flock organizers and volunteers. Putting together an event like this takes a lot of quiet, [...] ## Are Supabase docs agent-friendly? We didn't know, so we checked DevFeed: [Are Supabase docs agent-friendly? We didn't know, so we checked]() Original publisher: [Read original article]() Author: Miranda Limonczenko; Nik Richers Published: 2026-08-01T07:00:00Z Content type: article Language: en Sources: [Supabase Blog]() Topics: [AI-assisted coding](), [cursor]() Tags: [agent](), [ai-coding](), [claude-code](), [cursor](), [database](), [docs](), [security]() ### AI overview Supabase describes evaluating whether coding agents can successfully use its documentation, beginning with its Row Level Security guide. The evaluation identified risky default database access and drove documentation fixes until it passed. ### Source excerpt We built an eval for our Row Level Security guide, found agents were granted risky default database access, and fixed the docs until the eval passed. ## The state of docs traffic: a 2026 midyear report DevFeed: [The state of docs traffic: a 2026 midyear report]() Original publisher: [Read original article]() Author: Kyan Yang Published: 2026-07-29T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Model Context Protocol](), [Logging](), [Server]() Tags: [2026](), [agent](), [ai-trends](), [clients](), [docs](), [mcp](), [report](), [retrieval](), [search](), [servers](), [tool]() ### AI overview Mintlify's 2026 midyear report examines how agents access documentation. It reports that agents represented 66% of measured web traffic in July, with direct machine routes becoming more common, and separately analyzes MCP assistant responses and tool calls. ### Source excerpt Agents now account for 66% of measured web-traffic across docs powered by Mintlify, with July logging over 213 million agent web requests and 105 million human page loads as the month comes to a close. ## ClickHouse docs relaunch DevFeed: [ClickHouse docs relaunch]() Original publisher: [Read original article]() Author: Shaun Struwig; Dominic Tran; Alexey Milovidov Published: 2026-07-27T00:00:00Z Content type: release Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [MCP Server](), [AI-assisted coding](), [API](), [Open Source]() Tags: [agents](), [api](), [clickhouse](), [docs](), [github](), [markdown](), [mcp](), [mcp-server](), [open-source](), [search]() ### AI overview ClickHouse has relaunched its developer documentation on Mintlify, adding redesigned search and Ask AI features, improved navigation, an interactive API playground, expanded localization, and a docs MCP server intended to support both human readers and coding agents. ### Source excerpt We have relaunched clickhouse.com/docs on Mintlify, with a redesigned search and Ask AI experience, a docs MCP server, simpler navigation, an interactive API playground, and expanded localization -- built for both human readers and the coding agents ## Top reranking models to boost RAG accuracy in 2026 DevFeed: [Top reranking models to boost RAG accuracy in 2026]() Original publisher: [Read original article]() Author: Jeff Mills Published: 2026-07-26T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [Retrieval Augmented Generation (RAG)](), [Redis](), [Large Language Model](), [API]() Tags: [api](), [caching](), [data](), [developer](), [docs](), [engineering](), [guide](), [how-to](), [inference](), [llm](), [memory](), [model](), [models](), [performance](), [production](), [rag](), [redis](), [retrieval](), [retrieval-augmented-generation-rag](), [search](), [tech-de]() ### AI overview This guide explains how reranking improves retrieval-augmented generation accuracy. It distinguishes fast first-stage retrieval from slower, precision-focused second-stage reranking, which reorders candidate chunks so relevant context reaches the LLM's high-attention positions. It also discusses cross-encoder rerankers, context rot, and Redis Iris for serving agent context. ### Source excerpt Your Slack pings mid-afternoon: a product manager says the retrieval-augmented generation (RAG) assistant keeps citing a deprecated API version in its answers to developer questions. You pull the trace and find the retriever grabbed 50 chunks, with th... ## RAG debugging guide: fast ways to reduce retrieval errors DevFeed: [RAG debugging guide: fast ways to reduce retrieval errors]() Original publisher: [Read original article]() Author: Jeff Mills Published: 2026-07-21T00:00:00Z Content type: tutorial Language: en Sources: [Redis Blog]() Topics: [Retrieval Augmented Generation (RAG)](), [debug](), [Monitoring](), [AI search](), [Latency](), [Traces]() Tags: [debugging](), [docs](), [embedding](), [errors](), [guide](), [latency](), [logs](), [monitoring](), [rag](), [retrieval](), [tech-de](), [traces](), [vector]() ### AI overview A practical guide to diagnosing five common production RAG failures across retrieval, ranking, grounding, freshness, and latency. It explains how chunking, vocabulary mismatch, monitoring, logs, and traces can reveal why a system returns confidently incorrect answers. ### Source excerpt Your RAG-backed support assistant just told a customer the refund window is 30 days. It's 14. The retrieval logs look clean: chunks came back, latency was normal, nothing errored. That's what makes RAG failures slippery. The pipeline still returns an ... ## Purge your Remote Cache's build and CI artifacts DevFeed: [Purge your Remote Cache's build and CI artifacts]() Original publisher: [Read original article]() Author: Anthony Shew Published: 2026-07-20T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Cache](), [Caching](), [ci](), [Deployment]() Tags: [cache](), [caching](), [ci](), [deployment](), [docs](), [remote]() ### AI overview Vercel lets Team Owners purge all artifacts from a team's Remote Cache in one click, including build and CI artifacts. The feature is intended for cases where cached artifacts may be poisoned. ### Source excerpt Team Owners can now clear the team's Remote Cache of all artifacts in one click. This is useful when you believe there are poisoned artifacts in your cache. In your team's Build and Deployment settings, visit the Remote Caching section and clear the Remote Cache. Visit the docs to learn more. Read more [Next page]()