Documenting the mess before you automate with AI

Documenting the mess before you automate with AI

Documenting the Mess Before You Automate "Automating a broken process just breaks things faster."  In this episode of The Missing Manual, JCK and Julia take you behind the scenes of their own operational chaos. This is part 3 of our ongoing series on operationalizing AI for a specific, real-world use case: running this exact podcast. Julia does a complete verbal download of the current, highly manual production workflow, from editing in Riverside and wrestling with inconsistent thumbnail creation in Canva/Google, to manual file renaming on her Mac downloads folder and navigating the LinkedIn algorithm.  Before touching a single automation line, the team uses Claude to map out the current state. JCK steps onto her soapbox to explain why HR, TA, and business leaders must document every shadow process and departmental variation before trying to automate. If you don't map the friction, you simply bake the friction directly into your AI system. Tune in to hear: • The critical difference between automating a process and optimizing it first. • How to use your least favorite manual tasks as a bullseye for AI opportunities. • The debate: Do you fix the gaps before you write the project instructions, or solve them inside the system? Stay tuned for the next episode as we dive into defining the rules of the road and building out the actual project instructions!

Two Brand Voices, One Show: How We Train AI to Speak for Both of Us

Two Brand Voices, One Show: How We Train AI to Speak for Both of Us When two distinct creators collaborate, how do you ensure the content speaks with a unified voice—without losing the hard-earned, earned beliefs of either host? In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas dive deep into the mechanics of operationalizing their show using AI. This isn't about quick hacks or shortcuts; it's a strategic, behind-the-scenes look at how to merge individual "Brand Voice Bibles" into a singular, cohesive AI grounding document. Tune in as we discuss how we are training our AI to step into the role of our virtual Production Assistant and Chief of Staff. You’ll learn how to establish unified guardrails (like our shared, yet distinct, hatred of the em-dash), how to handle stylistic friction, and why the secret to scaling your workflow lies in defining a clear "blueprint for good." Key Takeaways for Your Work: * Don't get stuck on the tool: The foundational strategy applies whether you are using Claude Projects, Gemini Gems, or Custom GPTs. * Why your AI needs to know what "bad" looks like just as much as it knows what "good" looks like. * The workflow pipeline: How to collaborate with the tool to get a draft 85% of the way there, and how to feed your final 100% version back in to train it for the future. Have you built a grounding document for your own business operations yet? Let us know your thoughts on LinkedIn at The Missing Manual page!

How to Build an AI Workflow for Any Repetitive Task

In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas teach you how to build an AI workflow for any repetitive task by working through a real example in real time. They use their own podcast production process as the case study, but the framework they walk through applies to almost anything clunky and manual that drains hours from your week. The three moves are simple: follow the friction, map the process, reverse engineer it with AI and automation. Julia and JCK make the case that the real skill in working with AI is not picking one perfect tool, it's knowing when to use best-in-class for a specific gap and when good-enough all-in-one is the smarter call. Julia brings the operator's lens from her work in talent acquisition leadership, where she's evaluated this exact tradeoff with talent technology. JCK reframes the conversation around systems thinking, pushing listeners to zoom out from the specific use case and look at the underlying pattern they can copy. A through-line of the episode is keeping the human in the loop on purpose. AI tools still produce odd outputs, hands with extra fingers, faces that drift across ethnicities, so the hosts are designing their workflow to let AI generate a slate of options while a human makes the final call. It's a practical model for anyone who wants to use AI without handing over judgment. This is the kickoff of a multi-part series on The Missing Manual where Julia and JCK build the workflow live, including the stumbles. If you have a repetitive task at work or at home that is ripe for automation, this episode gives you the framework to start on it today. Find The Missing Manual wherever you listen to podcasts.

Mowing the Digital Grass: Taming Your Downloads Folder with Claude Co-work

"Hope is not a strategy." If your desktop is a sea of icons and your Downloads folder is a graveyard of unnamed PDFs, this episode is for you. Julia and JCK dive into a practical, day-to-day use case for AI that goes beyond the hype: digital organization. In this episode, we document the process of turning digital chaos into a streamlined system. We discuss the shift from "manual" organization to "agentic" workflows, where the AI doesn't just give you a template, it co-creates a methodology with you. In this episode, you’ll learn: * Why "mowing the grass" is the best metaphor for digital maintenance. * How to use Claude Co-work to audit your hard drive and flag duplicates. * The difference between "chasing best practices" and building a system that fits your specific brain (The "One Size Fits One" approach). * How to stop wasting mental calories on file management and start "capacity enabling" your work week. Resources Mentioned: * Claude Co-work * The "Grass Mowing" Prompt (Check our YouTube for the screen share!) Connect with us: Follow Julia Levy and Jenny Cotie Kangas on LinkedIn for more "Strategy, Not Hacks" and AI-driven insights. Don’t forget to subscribe to The Missing Manual on YouTube to see the live demos!

Stop Building Better Bad Processes: The Missing Manual for AI Troubleshooting

In this episode of The Missing Manual, JCK and Julia Levy go "under the hood" of their own AI experiments to discuss what happens when the tech fails to meet your standards. From Julia’s frustrating experience cloning her voice to JCK’s "agentic design" approach, they break down why AI is a "one-size-fits-one" solution. They explore the "Step Zero" of process mapping, the power of handoff documents, and why you should treat different LLMs (Claude vs. ChatGPT vs. Gemini) like specialized team members rather than a single source of truth. THE BREAKDOWN: [00:00] Intro: The Missing Manual for TA leaders and practitioners. [01:06] Julia’s Use Case: Building a Talent Intelligence web app and the frustration of "bad" AI voice clones. [02:15] Defining "Good": Why AI reverse-engineers the wrong results without established guardrails. [03:15] The Golden Rule: Don’t use AI to automate a broken process (Stop making "better bad processes"). [04:36] Model Switching: When to use Gemini vs. Claude vs. ChatGPT for specific tasks. [09:31] The "Learning Out Loud" Community: Curating your own AI news pulse. [11:18] Beyond Business: How Julia used AI to plan a multi-generational family trip to Moab, Utah. [15:54] The "Challenge Me" Prompt: How to stop your AI from being a "Yes-Man." [19:39] Final Summary: The critical role of Handoff Documents in grounding your AI.