# The AI-Augmented Engineer Teaching software engineers how to accelerate their careers with AI. Deep, technical guides on Claude Code, Codex, Cursor, and more. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## 6 principles for using Grok Bot DevFeed: [6 principles for using Grok Bot]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-09-15T10:46:18Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [agent orchestration](), [Tool](), [Bot]() Tags: [agent](), [agent-orchestration](), [tool]() ### AI overview The article presents six principles for using Grok Bot and describes Grok Bot as a general agent orchestration tool. The supplied evidence does not provide the individual principles. ### Source excerpt Grok Bot is a great general agent orchestration tool, if you know how to use it right ## How to link CLAUDE.md and AGENTS.md DevFeed: [How to link CLAUDE.md and AGENTS.md]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-09-11T11:48:32Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [file]() Tags: [file]() ### AI overview The article presents two ways to link CLAUDE.md and AGENTS.md so that one instruction file can be used across different harnesses. ### Source excerpt Two ways to keep one instruction file for every harness ## How to secure AI coding agents with permissions, approval gates, hooks, and sandboxing DevFeed: [How to secure AI coding agents with permissions, approval gates, hooks, and sandboxing]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-09-08T10:07:38Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [agentic-coding](), [Artificial Intelligence](), [AI-assisted coding](), [coding]() Tags: [agents](), [ai](), [ai-coding-agents](), [claude-code](), [coding-agents](), [how-to](), [least-privilege](), [permissions](), [sandboxing](), [security]() ### AI overview The article explains why coding-agent instructions such as CLAUDE.md are behavioral guidance rather than enforceable security boundaries. It discusses least privilege, Claude Code permissions, approval gates, hooks, and sandboxing as technical controls for limiting agent actions. ### Source excerpt Learn how to use the principle of least privilege, Claude Code permissions, approval gates, hooks, and sandboxing to keep your agentic coding secure ## How to use Gemini Notebook to learn faster DevFeed: [How to use Gemini Notebook to learn faster]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-08-26T10:06:43Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Learning](), [Artificial Intelligence](), [App](), [Google](), [Obsidian](), [Markdown]() Tags: [ai](), [app](), [drive](), [gemini](), [how-to](), [learn](), [learning](), [markdown](), [notes]() ### AI overview This tutorial explains how to use Gemini Notebook as a source-grounded learning tool. It covers adding sources such as pasted text, uploaded files, links, and Google Drive content, then generating study materials including briefing documents, quizzes, flashcards, and podcasts. ### Source excerpt Gemini Notebook can help you learn anything twice as fast. I'll show you how. ## How to set up a project to let agents validate work DevFeed: [How to set up a project to let agents validate work]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-08-20T12:24:06Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [App]() Tags: [agents](), [how-to](), [project]() ### AI overview A tutorial on setting up a project so agents can use an app to validate their work. ### Source excerpt Agents are most useful when they can actually use your app to validate their work. I'll show you how to make it easy for them ## How to use OpenCode DevFeed: [How to use OpenCode]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-08-13T10:34:23Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [coding](), [Software]() Tags: [build](), [coding](), [how-to](), [opencode](), [software]() ### AI overview A tutorial on using OpenCode to build software without coupling the coding harness to a model provider. ### Source excerpt Wouldn't it be great if your coding harness wasn't coupled to your model provider? I'll show you how to use OpenCode to build software. ## How to ship features with Cursor Mobile DevFeed: [How to ship features with Cursor Mobile]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-08-06T10:30:42Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [cursor](), [Mobile](), [App]() Tags: [app](), [cursor](), [features](), [how-to](), [mobile]() ### AI overview A how-to article about using the Cursor mobile app to ship features remotely. ### Source excerpt The Cursor mobile app is letting me ship features from my front porch. Let me show you how. ## Parallel agent orchestration is compatible with deep work DevFeed: [Parallel agent orchestration is compatible with deep work]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-08-03T10:21:16Z Content type: opinion Language: en Sources: [The AI-Augmented Engineer]() Topics: [agent orchestration](), [Orchestration](), [Large Language Model](), [Cosmos]() Tags: [agent](), [agent-orchestration](), [ai](), [claude](), [claude-code](), [codex](), [cosmos](), [parallel]() ### AI overview The author argues that AI agents can be managed in parallel as background tasks while preserving focused attention for complex design and decision-making. They recommend delegating routine implementation, while keeping nuanced architectural thinking with humans. ### Source excerpt Agent orchestration is making me rethink how I work ## Using AI for agentic software testing DevFeed: [Using AI for agentic software testing]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-07-30T14:26:39Z Content type: opinion Language: en Sources: [The AI-Augmented Engineer]() Topics: [Testing](), [Software Testing](), [Artificial Intelligence](), [developer tooling]() Tags: [agentic](), [ai](), [ai-tools](), [software-testing](), [testing]() ### AI overview The article argues that as AI makes code generation faster, testing and quality engineering become more important for safely shipping software. It discusses common testing compromises and cites a 2026 report stating that 60% of organizations regularly ship untested code to production. ### Source excerpt Testing is a place where dedicated AI tools make an insane difference ## Cost-effective orchestration with Fable 5 DevFeed: [Cost-effective orchestration with Fable 5]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-07-21T11:37:27Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Fable](), [Claude Code](), [Orchestration]() Tags: [better](), [claude-code](), [cost](), [effective](), [fable](), [how-to](), [results]() ### AI overview This tutorial presents Fable 5 in Claude Code as an orchestration approach and claims it can produce better results at lower cost. The supplied text does not provide implementation details or supporting measurements. ### Source excerpt Fable 5 in Claude Code is effective. I'll show you how to use Fable as an orchestration to get better results at a fraction of the cost ## Choosing Among Fable 5, GPT-5.6, and Grok 4.5 for Software Engineering DevFeed: [Choosing Among Fable 5, GPT-5.6, and Grok 4.5 for Software Engineering]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-07-16T11:25:05Z Content type: comparison Language: en Sources: [The AI-Augmented Engineer]() Topics: [Fable](), [Frontier Model](), [AI-assisted coding](), [long-context](), [migration](), [Ruby](), [OpenAI]() Tags: [ai](), [anthropic](), [coding](), [coding-agents](), [frontier-model](), [migration](), [openai](), [ruby]() ### AI overview This comparison examines how software engineers might choose among Fable 5, GPT-5.6, and Grok 4.5. It discusses Fable 5's long-context, adaptive-reasoning, and autonomous-work capabilities, while comparing reported evaluation results, coding performance, and cost considerations across the models. ### Source excerpt Software engineers should be happy that no AI lab can hold the lead for long. I'll walk you through how to choose between Fable 5, GPT-5.6, and Grok 4.5 ## How to use loops in Claude Code DevFeed: [How to use loops in Claude Code]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-07-13T11:10:13Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code]() Tags: [claude-code](), [how-to](), [loops]() ### AI overview A tutorial about using loops in Claude Code, with the description indicating that it explains why the /loop feature has attracted attention. ### Source excerpt The internet won't shut up about /loop in Claude Code. I'll show you why ## Codex vs Claude Code DevFeed: [Codex vs Claude Code]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-07-02T11:41:03Z Content type: comparison Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [codex](), [AI Development](), [Command-line interface](), [cursor]() Tags: [ai](), [claude-code](), [cli](), [codex](), [comparison](), [developers]() ### AI overview This comparison explains the difference between Codex and Claude Code, focusing mainly on their developer harnesses rather than the underlying models. It presents Codex as the author's preference while noting that Claude Code has a better CLI, and describes both as tools that can understand and modify a codebase. ### Source excerpt Codex and Claude Code are both incredible tools for developers, which might leave you wondering which you should choose. ## Cosmos is a shared platform for coordinating AI agents across software development workflows DevFeed: [Cosmos is a shared platform for coordinating AI agents across software development workflows]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-24T10:16:51Z Content type: opinion Language: en Sources: [The AI-Augmented Engineer]() Topics: [Cosmos](), [agentic-engineering](), [AI Development](), [AI-assisted coding](), [Software Engineering]() Tags: [agent](), [agentic](), [agentic-engineering](), [ai](), [claude-code](), [engineering](), [generation](), [software-development](), [workflow]() ### AI overview The article argues that AI agents are moving software development beyond the IDE and that teams need an operating model for coordinating agent-driven work. It presents Cosmos, Augment's unified cloud agents platform, as a shared system for workflows including triage, specification, implementation, review, testing, deployment, and feedback. ### Source excerpt Cosmos is a new tool for AI-native engineering teams ## Redesigning a mobile app with Claude Code DevFeed: [Redesigning a mobile app with Claude Code]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-23T12:14:59Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [iphone](), [Mobile](), [App]() Tags: [app](), [claude-code](), [how-to](), [iphone](), [mobile]() ### AI overview A tutorial about using Claude Code to redesign an old iPhone app. ### Source excerpt Learn how to use Claude Code to redesign an old iPhone app ## Claude Code learning hub DevFeed: [Claude Code learning hub]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-20T12:11:50Z Content type: article Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [Terminal](), [Command-line interface](), [npm]() Tags: [claude-code](), [guides](), [install](), [npm](), [terminal]() ### AI overview A collection of Claude Code guides gathered from the newsletter archive, including instructions for installing Claude Code with npm through a terminal. ### Source excerpt Every article the newsletter has about Claude Code ## AI slop cannons and their consequences DevFeed: [AI slop cannons and their consequences]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-18T10:47:34Z Content type: opinion Language: en Sources: [The AI-Augmented Engineer]() Topics: [Artificial Intelligence](), [Code](), [Software](), [Claude Code]() Tags: [ai](), [claude-code](), [code](), [engineering](), [software]() ### AI overview This commentary argues that AI amplifies a developer's existing abilities: strong engineers can become more productive, while developers who prioritize output over quality may produce maintainability problems and technical debt. It introduces principles for using AI tools effectively while continuing to build independent engineering judgment and skills. ### Source excerpt Using AI without care or precision almost guarantees you become an AI slop cannon. Here's how to be sure you're using it to create real value ## Building an info product in Claude Code DevFeed: [Building an info product in Claude Code]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-16T10:46:55Z Content type: article Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code](), [Code](), [Deployment]() Tags: [building](), [claude-code](), [code](), [deployment](), [product]() ### AI overview The article describes using Claude Code to accelerate the design and deployment of websites for hosting information products. ### Source excerpt Claude Code is a great way to accelerate the design and deployment of beautiful websites to host info products ## Codex wants to work on more than just code DevFeed: [Codex wants to work on more than just code]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-11T11:44:06Z Content type: opinion Language: en Sources: [The AI-Augmented Engineer]() Topics: [codex](), [Artificial Intelligence](), [ChatGPT](), [MCP](), [agentic workflows](), [Claude Code]() Tags: [agentic-workflows](), [ai](), [chatgpt](), [claude-code](), [codex](), [mcp]() ### AI overview This opinion article examines OpenAI Codex's expansion from a coding assistant into a broader work assistant. It discusses integrations with Gmail, Slack, Google Drive, Linear, and Stripe, the role of the open MCP standard, and OpenAI's plan to bring Codex into ChatGPT. The author questions whether this broader direction is wise. ### Source excerpt My favorite AI assistant for code is making the leap into becoming the AI assistant for work. I mean, take a look at the landing page as of today. ## How to make a custom Claude Code status line DevFeed: [How to make a custom Claude Code status line]() Original publisher: [Read original article]() Author: Jeff Morhous Published: 2026-06-09T11:46:04Z Content type: tutorial Language: en Sources: [The AI-Augmented Engineer]() Topics: [Claude Code]() Tags: [claude-code](), [how-to]() ### AI overview A tutorial explaining how to configure a custom Claude Code status line to display useful information. ### Source excerpt The Claude Code status bar can be configured to show you useful information - I'll show you how!