AtlasThe Atlas blog
Building software with AI coding agents
What's new in AI coding, explained plainly. Guides for founders, product owners and testers who work with an AI team, and hands-on how-tos for the engineers who run Claude Code and OpenAI Codex.
- Plain EnglishWhat's newCodex Memory v2 on by Default: What Teams Should KnowCodex CLI 0.165.0 (27 Oct 2026) turns on memory v2 for fresh profiles and can import memories from other agents. What it means for your team.
- TechnicalExplainerClaude Code Status Line: Show Context, Cost and LimitsSet up a Claude Code status line that shows context fill, session cost, plan limits and cache health, with a working bash script and fixes for a blank line.
- Plain EnglishExplainerWhy AI-Built Work Comes Back for Rework, and How to Cut ItWhy does AI-built software keep coming back for fixes? The common causes of rework with AI coding agents, and the plain habits that cut it and save money.
- Plain EnglishWhat's newGPT-6.1 Terra in Codex: What Changed and Who Should CareOpenAI added GPT-6.1 Terra to Codex on 26 Oct 2026: a cheaper, faster model built for screens and images. What it is, what it costs, and how to test it.
- TechnicalFrom AtlasRun Only Affected Tests in a Monorepo with AI AgentsCut test time when AI agents change a monorepo: run only affected tests with pnpm filters and Vitest, plus the safety rules that keep narrowing honest.
- Plain EnglishExplainerWhat Is a Flaky Test? A Plain Guide for AI-Built SoftwareA flaky test passes one run and fails the next on the same code. Learn why they happen, what they cost when AI agents build your software, and what to ask.
- Plain EnglishWhat's newClaude Code Mods: What They Are and the Risks to CheckClaude Code mods are plugins that run code inside the tool itself. See what changed in October 2026, what mods can reach, and what a team should decide.
- TechnicalFrom AtlasClaude Code OpenTelemetry: Track Cost and Tool UseSet up Claude Code OpenTelemetry to stream token, cost and tool metrics to your own stack. Env vars, managed settings, privacy flags and queries to start.
- Plain EnglishExplainerAI Coding Agent Usage Limits Explained in Plain EnglishWhy your AI coding agent stops mid-job on Claude Pro or Max, what the five-hour and weekly limits mean, and how to plan work so you are not stuck waiting.
- Plain EnglishWhat's newClaude Fast Mode for Opus 5.5: Cost and When It PaysAnthropic took Claude Opus 5.5 fast mode out of research preview on the API on 15 Oct 2026. What it costs and when a team should pay for the speed.
- TechnicalHow-toClaude Code settings.json: Scopes and Precedence ExplainedWhich Claude Code settings file wins? The four scopes, precedence order, list merging, a team setup and fixes for settings that seem ignored.
- Plain EnglishExplainerAI Coding Agent Terms Explained in Plain EnglishRepository, branch, pull request, context window, subagent: the words your AI coding agent keeps using, explained without code and with everyday examples.
- Plain EnglishWhat's newAgent Skills Now Belong to a Foundation: What It MeansOn 22 Oct 2026 Anthropic gave the Agent Skills standard to the Agentic AI Foundation. Here is what skills are and what the move means for your team.
- TechnicalFrom AtlasClaude Code Plugins: Build a Team MarketplacePackage skills, subagents and hooks as a Claude Code plugin, host a team marketplace in git, and make every teammate get it. Commands and config included.
- Plain EnglishHow-toHow to Run a First AI Coding Agent Pilot: A Plain GuideThinking of trying an AI coding agent? Pick the right first project, set a pass/fail test, cap the risk and decide after two weeks. A plain-English guide.
- Plain EnglishWhat's newClaude API Version 2026-10-21: What Teams Must CheckAnthropic released Claude API version 2026-10-21 with breaking changes. Here is what changed, who is affected and what to ask your team to check first.
- TechnicalHow-toClaude Code GitHub Actions: Set Up @claude on Your RepoSet up Claude Code GitHub Actions: install with /install-github-app, write the @claude workflow, run PR reviews and cron jobs, and cap cost and permissions.
- Plain EnglishExplainerWhy AI Coding Agents Forget and How to Fix ItAI coding agents start every session blank and can lose early instructions mid-task. Here is why, and the plain-English fixes that make your rules stick.
- Plain EnglishWhat's newClaude Code Safety Event: A Log of Every Blocked ActionClaude Code 2.1.307 adds a safety event that logs when a permission rule, auto mode, a safety check, a hook or the sandbox stops an action. What it means.
- TechnicalHow-toClaude Code Sandbox: Limit Files and Network for BashTurn on Claude Code's built-in sandbox: set which files and hosts shell commands can reach, fix what breaks, and know what still runs outside it.
- Plain EnglishExplainerYour Role When AI Builds the Software: A Plain GuideWhat changes for founders, product owners and managers when AI agents write the code: you decide, define "done" and check evidence. A plain-English guide.
- Plain EnglishWhat's newClaude Code Auto Mode Setup: Teach It Your EnvironmentClaude Code auto mode blocks what it doesn't know is yours. Since 19 Oct 2026, /auto-mode-setup works on more setups. What it does and what to check.
- TechnicalHow-toTest-First with Claude Code: Failing Tests Before CodeRun test-first development with Claude Code: commit failing tests, block edits to them with a hook, finish on a /goal or Stop hook, then review in a fresh context.
- Plain EnglishExplainerHow AI-Built Software Gets Released: A Plain GuideWhat happens between "the AI says it's done" and "customers can use it"? A plain guide to safe releases, with the questions to ask before you say go.
Nothing here yet — new articles arrive three times a day.