Almost Timely News: ๐️ Improving AI With Command Line Tools (2026-04-12)
Almost Timely News: ๐️ Improving AI With Command Line Tools (2026-04-12) :: View in Browser
The Big PlugsSo many new things! 3️⃣ A free 25 minute webinar Katie and I did on GEO - even though it says the date is past, it still works and takes you to the recording. Content Authenticity Statement100% of this week’s newsletter content was originated by me, the human. You’ll see me working with Claude Code in the video version. Learn why this kind of disclosure is a good idea and might be required for anyone doing business in any capacity with the EU in the near future. Watch This Newsletter On YouTube ๐บ
Click here for the video ๐บ version of this newsletter on YouTube » Click here for an MP3 audio ๐ง only version » What’s On My Mind: Improving AI With Command Line ToolsLast week I talked about the command line interface and how useful it was with today’s agentic AI tools, and I gave three examples. Many of you wrote back to say “we’d like to see more examples”. So this issue is your wishes fulfilled. Part 1: Why the Command Line MattersFor years now, we’ve talked about how things like MCPs - model context protocol servers - were the way to connect AI to external systems. That’s true to a great degree, but it turns out MCP implementations are horrendously inefficient. When you use an MCP to connect to a database or a web service, you’re telling your favorite AI tool how to talk to it and interact with it - pulling and pushing data. If this sounds familiar, it should. MCPs are to AI what APIs - application programming interfaces- are to regular software. The difference is, in many, many measured tests, AI tools and agents use MCPs incredibly inefficiently. They do a lot of reinventing the wheel every time they interact with an MCP. For casual use where you’re typing into a tool like Claude or ChatGPT, that doesn’t matter a ton. But once you start using AI agents, tools like Claude Code, Claude Cowork, OpenWork, OpenCode, Qwen Code, OpenClaw, etc., efficiency becomes very important. The reason why is that AI agents produce far more inputs and outputs than humans do. To give you a sense of scale, if you spend half an hour chatting with a tool like ChatGPT, you’ll probably generate somewhere in the range of 15-20 thousand words, about the length of a short business book. An agent like Google Antigravity or Claude Cowork, in that same half hour, will generate 15-20 MILLION words, three orders of magnitude greater. Why? Partly because AI tools can read far faster than any human can, and partly because agent tools aren’t sequential. When you use ChatGPT, it’s you and one conversation thread. When you’re using something like Claude Cowork, behind the scenes there can be 50 different agents working in 50 different conversations at the same time. My record was having 120 agents all in flight at the same time, all simultaneously. (It was writing and editing a book, so each chapter had 4 agents working together - a writer, an editor, a reviewer, and a proofer) If an MCP is involved, AI agents are reinventing the wheel every time they interact with it. That makes it very slow, introduces the potential for lots of randomness and lots of mistakes, and when you’re using something like an API where you pay by the word, agents using MCPs can run up massive bills very quickly. In the early days of OpenClaw, early adopters weren’t watching the meter and more than a few got ten thousand dollar bills from companies like Anthropic. Oops. The alternative to the MCP is the command line interface, or CLI. If you’re old like me, you used to use these when you interacted with computers. Back in the days of the Apple IIe and VisiCalc, AppleWorks, Lotus 1-2-3, and MS-DOS, there was no graphical user interface (GUI). There was no mouse. There was you and the text command line, and every program you interacted with had text-based commands. Perhaps you’ve heard of Zork or similar role-playing games where you’d type things like direction names, or instruct your character to open a treasure chest, and the game would tell you in words what was happening:
These text-based apps were all the rage until the Macintosh computer in 1984 (well, technically the Xerox PARC computer had the mouse and GUI first, but Apple commercialized it first) when we got the mouse and GUI. But the command line interface never went away. It’s been present in every computer since the dawn of computing. On a Windows computer, it’s the Command Prompt, CMD. On a Mac and Linux, it’s the Terminal. And operating systems themselves on computers have many, many little applications built into the command line, simple pieces of software that do one thing, but do it well. This was the original architecture of computer systems like UNIX, because memory was so scarce that it was better to have a tool that did one thing very well than a tool that tried to do many things and did them all poorly. For example, on the Mac and Linux systems, there’s an app called wc. wc counts things - letters, words, and bytes. Give it a text document like this:
And it will tell you how many words are in that document. That’s all it does. That’s all it needs to do. Hopefully you see where this is going. Who loves to type and is great at typing at ridiculous speeds? AI. Instead of a slow, cumbersome, error-prone MCP, a command line application (also known as a CLI) provides a deterministic (non-random) way to access the same services that provide MCPs. But here’s the twist: in testing, many folks have found that AI agents burn through 2/3 less usage using a CLI as it does an MCP. If you’re on Anthropic’s Claude subscription plans, you’ve no doubt hit usage limits. If you’re using APIs, you’ve no doubt gotten bills from AI providers. What if you could cut those bills down significantly? With CLIs instead of MCPs, you can do exactly that. Part 2: Switching OverThere’s a gotcha with CLIs. You have to tell AI agents how to use them. Depending on the system you’re working with, your AI agent may need to install it themselves (this is often the case in container-based systems like Claude Cowork, which run in a sandbox on your computer, isolated from the rest of your computer), or your AI agent may be able to access it directly (Claude Code, OpenClaw) which is more risky because the agent is working directly on your computer. That’s the first hurdle to overcome. The easiest way to overcome it is to ask your AI tool of choice how it can access CLIs, what it needs to do. I should point out here that NONE of the web-based tools (like ChatGPT, for example) can use CLIs at all, so MCPs are still the only way for those web-based tools to access third party services. What AI tools can use CLIs? Anything agentic:
It’s also worth pointing out that today, I use a coding environment (Claude Code and OpenCode) for almost all my AI usage including many, many non-coding tasks. I rarely, if ever, use the web-based chats any more. More on that in a second. Your second step, after making sure you’ve got AI that can use CLIs, is to determine what software you’d want to use a CLI with. Think of it this way: what software do you use every day that you wish you could have AI use on your behalf? What about GMail or Outlook? Microsoft Word? Google Sheets? NotebookLM? Your CRM? Once you’ve made a list of the things you wish you could hand off to AI in some capacity, it’s time to do a bit of Googling (or have an AI agent do it). Google for this:
For example:
This will do a search to see if there’s a CLI for my notetaking app, Joplin. And there is! Now I don’t have to worry about APIs or MCPs or all kinds of contortionism to get AI to talk to my note-taking tool. Instead, I install the CLI and now there’s a text-based way for AI to interact with it. Not all software packages have CLI tools. As a sidebar, if you work for a software company and you don’t offer a CLI, you’re almost obsolete. As more and more people use AI agents, the demand for interfaces like CLIs will become greater, and companies that fail to offer first class interfaces to AI will inevitably experience a lot of churn. Okay, you’ve figured out that your favorite software has a CLI. Install it, and then what? Great question. We have to tell AI that it’s available and how to use it. There’s an easy way to do this; almost every CLI tool has a documentation page of some kind. We point our AI tool at that page and ask it to make its own user guide. Here’s a suggested prompt:
What this will produce is a condensed version of the manual and documentation ready for AI to use. You can do this right inside your agentic system like Claude Cowork and have it write the YAML file to your hard drive. Then, depending on you have your agentic system set up, you can give it brief instructions when you want to invoke the CLI, or better yet, incorporate it into skills and hooks so that your AI agent automatically knows when to use it and how. We talked a little about this on the Trust Insights Livestream this past week. It’s also worth pointing out that one advantage CLIs have over MCPs is that they’re actual applications. If you’re old like me, you remember using apps back in the day exactly like this, and you can pick up and use these CLIs as apps, as a human. For example, suppose you’re using Atlassian’s Jira, but you find the website cumbersome to navigate. You can read the same manual that AI wrote for itself and use Jira in a Terminal just like your AI does. This is not for everyone, especially since younger folks have never had computers without GUIs, but depending on how your brain works, you might even prefer a CLI to a GUI app. If you’re easily distracted, CLIs can be a great way to single task and focus. If you or someone you know is low-vision, CLIs are AMAZING. Part 3: Demo WalkthroughIn the video version of the newsletter, you can watch me set this up using Joplin’s CLI step by step to see the flow. Part 4: A Compendium of Common CLIsNow that you’ve got the general idea about how to use these CLIs, let’s look at a rogues’ gallery of some of the most common ones, with links so you can go find them. I would strongly, strongly encourage you to use a package manager for CLI tools when possible, because it makes keeping them up to date much easier. On the Mac, this is Homebrew. On Windows, this is Chocolatey. On Linux, it’s apt or yum or deb or… well, there’s a gazillion package managers, honestly. Use the one that’s best for your distribution. Read up on how to install the appropriate package manager, if you’re allowed to (some corporate IT departments frown on systems like this because it makes device management very difficult). Some software companies have published official CLIs. Others have not, but because their software has APIs, folks have made unofficial versions. In general, prefer official CLIs over unofficial ones to minimize security and privacy risks. If you have to use an unofficial one and it’s on Github, you can ask your agentic coding tool of choice to audit it for safety, security, and privacy risks before installing it. This is a generally good best practice to get in the habit of and one of the primary reasons to use open source software - you can audit the software itself. The list of CLIs is massive - 135 of them, so I’ll highlight a few here and put the rest as an appendix at the end of the newsletter. Cloud Platforms & InfrastructureAI & ML PlatformsCommunication & ChatCRM & SalesPart 5: Wrapping UpCommand line interface tools are the best way for AI to interact with non-AI systems today. They’re deterministic - AI has mandated ways to interact with the tools and inputs and outputs are rigid. They’re incredibly efficient - unlike browsing a web site or managing a virtual keyboard and mouse, typing out commands is low bandwidth and low effort for AI and humans. They don’t consume tokens/AI usage getting data in and out of the target systems because the CLI does that without AI; it’s a black box from AI’s perspective. Your homework is to follow the process in this newsletter with the CLI of one of the tools you use, handing it to a system like Claude Code or Claude Cowork, and asking it to help you get set up to use that CLI in your work. You may be surprised to find out just how much AI can take on. How Was This Issue?Rate this week’s newsletter issue with a single click/tap. Your feedback over time helps me figure out what content to create for you. Here’s The UnsubscribeIt took me a while to find a convenient way to link it up, but here’s how to get to the unsubscribe. If you don’t see anything, here’s the text link to copy and paste: https://almosttimely.substack.com/action/disable_email Share With a Friend or ColleaguePlease share this newsletter with two other people. Send this URL to your friends/colleagues: https://www.christopherspenn.com/newsletter For enrolled subscribers on Substack, there are referral rewards if you refer 100, 200, or 300 other readers. Visit the Leaderboard here. ICYMI: In Case You Missed ItHere’s content from the last week in case things fell through the cracks:
On The TubesHere’s what debuted on my YouTube channel this week: Skill Up With ClassesThese are just a few of the classes I have available over at the Trust Insights website that you can take. PremiumFree
Advertisement: New GEO 101 CourseWhen I talk to folks like you, being recommended by AI is one of your top marketing concerns in 2026. We’ve taken everything we’ve learned from OpenAI’s documentation, Google’s technical papers, patents, sample code, plus our years of experience in generative AI to assemble a high-impact 90-minute course on GEO 101 for Marketers. In this course, you’ll learn:
This course is meant to be used. In addition to the course itself, you’ll also receive:
And best of all, this is our most affordable course yet. GEO 101 for Marketers is USD 99 and is available today. ๐ Enroll here in GEO 101 for Marketers! Get Back To Work!Folks who post jobs in the free Analytics for Marketers Slack community may have those jobs shared here, too. If you’re looking for work, check out these recent open positions, and check out the Slack group for the comprehensive list.
Advertisement: My AI Book!In Almost Timeless, generative AI expert Christopher Penn provides the definitive playbook. Drawing on 18 months of in-the-trenches work and insights from thousands of real-world questions, Penn distills the noise into 48 foundational principles-durable mental models that give you a more permanent, strategic understanding of this transformative technology. In this book, you will learn to:
Stop feeling overwhelmed. Start leading with confidence. By the time you finish Almost Timeless, you won’t just know what to do; you will understand why you are doing it. And in an age of constant change, that understanding is the only real competitive advantage. ๐ Order your copy of Almost Timeless: 48 Foundation Principles of Generative AI today! How to Stay in TouchLet’s make sure we’re connected in the places it suits you best. Here’s where you can find different content:
Listen to my theme song as a new single: Advertisement: Ukraine ๐บ๐ฆ Humanitarian FundThe war to free Ukraine continues. If you’d like to support humanitarian efforts in Ukraine, the Ukrainian government has set up a special portal, United24, to help make contributing easy. The effort to free Ukraine from Russia’s illegal invasion needs your ongoing support. ๐ Donate today to the Ukraine Humanitarian Relief Fund » Events I’ll Be AtHere are the public events where I’m speaking and attending. Say hi if you’re at an event also:
There are also private events that aren’t open to the public. If you’re an event organizer, let me help your event shine. Visit my speaking page for more details. Can’t be at an event? Stop by my private Slack group instead, Analytics for Marketers. Required DisclosuresEvents with links have purchased sponsorships in this newsletter and as a result, I receive direct financial compensation for promoting them. Advertisements in this newsletter have paid to be promoted, and as a result, I receive direct financial compensation for promoting them. My company, Trust Insights, maintains business partnerships with companies including, but not limited to, IBM, Cisco Systems, Amazon, Talkwalker, MarketingProfs, MarketMuse, Agorapulse, Hubspot, Informa, Demandbase, The Marketing AI Institute, and others. While links shared from partners are not explicit endorsements, nor do they directly financially benefit Trust Insights, a commercial relationship exists for which Trust Insights may receive indirect financial benefit, and thus I may receive indirect financial benefit from them as well. Thank YouThanks for subscribing and reading this far. I appreciate it. As always, thank you for your support, your attention, and your kindness. Please share this newsletter with two other people. See you next week, Christopher S. Penn Appendix: CLI AppsCloud Platforms & InfrastructureDevOps & CI/CDDatabasesAI & ML PlatformsContainerization & OrchestrationMonitoring & ObservabilitySecurity & IdentityCommunication & ChatProject ManagementE-CommerceAccounting & FinanceCMS & WebsiteSocial MediaCloud StorageVersion ControlNetworking & VPNData OrchestrationDeveloper ProductivityDocument & KnowledgeCRM & SalesInvite your friends and earn rewards
If you enjoy Almost Timely Newsletter, share it with your friends and earn rewards when they subscribe.
|
Comments