The Missing Manual Show

Julia Levy, Jenny Cotie Kangas

The Missing Manual: Documentation for the Doers In the world of work, there are the skills that get you the job, and then there’s the tradecraft required to actually build. Hosted by Julia Levy (Fortune 500 Talent Acquisition Executive) and Jenny Cotie Kangas (Future of Work Disruptor), this is an unscripted deep-dive into the high-stakes execution that doesn't come with an instruction book. We go beyond "career hacks" to provide a forensic look at organizational navigation and institutional tradecraft. From the mechanics of a multi-million dollar RFP to the front lines of Agentic AI and Talent Operations, we explore how the corporate machine actually moves so you can build within it effectively. What we document: The Future of Work: Moving beyond the "cracked" resume infrastructure and into Agentic AI handoffs. Organizational Mechanics: Navigating the "unwritten rules" of cross-functional execution and budget defense. Operational Strategy: Using Design Thinking and lean execution to save work from failure. We don't believe in "easy buttons." We believe in the hard, intentional work of building something that lasts. If you are a builder looking for the map to the modern corporate landscape, this is your manual.

  1. 12h ago

    Persistent AI Agents Explained

    Your always-on AI agent can break without telling you. Julia Levy found out the hard way, and the fix she built is where this episode of The Missing Manual starts. A persistent AI agent keeps its memory, its place in a task and its role from one day to the next. It runs on a schedule or reacts to a trigger, such as a new email or a set time, without waiting for a prompt. Julia Levy and Jenny Cotie Kangas explain how that differs from a scheduled automation that finishes its job and goes quiet. They also make the case that most professionals can get close to persistence with tools they already pay for, without buying anything new. The first risk is the silent failure. One of Julia’s always-on agents stopped running, and she only caught it when she noticed what wasn’t showing up. Now an audit agent checks the others. Jenny built the same safeguard earlier: a scheduled automation whose only job is to confirm her other automations are still on. From there the conversation turns to Julia’s AI chief of staff dashboard, which she over-built and is now trimming with a weekly review of what she actually used. Jenny’s prompt for that work: tell your AI to “Coco Chanel” it and remove anything that doesn’t earn its keep, because addition doesn’t scale and subtraction does. The center of the episode is a real disagreement about autonomy. Julia onboards an agent the way she’d onboard a new recruiter. Nobody gets admin rights to the ATS on day one, so her agent reads her email and calendar, never holds her passwords and drafts before anything sends. Jenny drafts with her agent in chat and lets it send the final version. That keeps sharpening her voice, and it also left her inbox looking like hundreds of open emails she had already handled. Jenny closes with a talent acquisition example: a recruiting team whose agents re-pull every system every two hours, so recruiters reach niche candidates before a competitor does. The Missing Manual covers agentic work, AI strategy and workplace tactics for people building the system while they use it. Questions this episode answers What is a persistent AI agent? A persistent AI agent keeps its memory, its task state and a consistent role over time. It acts on schedules or triggers, such as a new email, instead of waiting for a person to prompt it. What is the difference between a scheduled automation and a persistent agent? A scheduled automation runs at a set time, finishes and stops until the next run. A persistent agent stays on and responds whenever something changes. Can you build a persistent AI agent without new software? Yes, partly. Scheduled agents built in tools you already use, set to sweep your systems every few hours, give you most of the benefit. Jenny Cotie Kangas calls this “persistent-ish.” How do you know if an AI agent has stopped working? Build a second scheduled check whose only job is confirming your other agents ran and produced what you expected. Silent failure is the main risk of any agent that runs while you aren’t watching. How much autonomy should an AI agent get? Treat it like a new hire. Start with read access, no passwords and drafts that wait for your review. Let a task run on its own only after the agent handles it correctly, consistently, without your edits. About the hosts Julia Levy has spent 25 years in Fortune 500 talent acquisition, including two roles as Global Head of TA at AutoZone and CommScope (julia-levy.com). Jenny Cotie Kangas is the founder and Chief Solution Architect of Whiterock Road, where she helps leaders and individuals get AI right (whiterockroad.org). Find The Missing Manual wherever you listen to podcasts.

  2. Nov 12

    AI Handoff Documents That Stop Hallucinations

    An AI handoff document is a short summary of a long chat that you edit yourself before carrying it into a fresh one. It is the simplest way to stop Claude, ChatGPT or Gemini from dropping your rules and making things up. On this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas explain why the editing step matters more than the summary, and why your AI work should live somewhere you control. Julia Levy spent 25 years in Fortune 500 talent acquisition, twice as Global Head of TA, and now works as an HR tech and AI advisor. She opens with the moment Claude suggested a handoff on its own, because she had written so many that it learned her cue. She still decides what goes in. Jenny Cotie Kangas, who leads the Experience, Systems and Agentic Design practice at GBS Worldwide and founded Whiterock Road, explains why automatic compacting does not replace that step: it is the model's best guess about where to pick up, and it does not know which constraint from the first ten minutes you care about most. Jenny's handoffs have grown into a standing practice. Each client has grounding documents and running notes saved on her own computer, not inside a single AI account, a rule she set after a friend lost their entire Claude history. Her AI reads and adds to those files and asks her what matters most before it records anything, because hope is not a strategy. Julia shares how she is steering routine work away from Fable, the most expensive model, and Jenny describes the weekly scheduled lookback she recommended to a client team to check which model each task should have used and whether they need a bigger plan. This is AI strategy you can use on your next long chat: ask for the handoff, edit it, and keep the file somewhere that outlasts any one account. The Missing Manual is about the how that nobody wrote down. Find The Missing Manual wherever you listen to podcasts.

  3. Nov 6

    I Had 33 AI Agents. Now I Have One.

    Jenny Cotie Kangas was running 33 AI agents before she realized she had built herself a second job. On this episode of The Missing Manual, she explains how she replaced all of them with one front door agent. It runs every morning, checks every system she works in, and keeps adding to a map of where her day actually goes. The answer to “how many AI agents do I need” is usually fewer than you have, all running through one place that sees everything. Julia Levy came at the same problem from the opposite side. Every new AI tool on a podcast or in an ad made her wonder if she was falling behind. That left her paying for more subscriptions than she needed, the same way recruiters used to juggle a pile of add-ons bolted onto their ATS. So she had Claude review every tool she pays for. She canceled the ones whose functions she could rebuild inside the setup she already uses. When the hosts compared their builds, the differences were the lesson. Julia’s agent is a visual dashboard with buttons she taps. Jenny’s is a chat she talks to by voice. It’s built that way because, since losing her memory in 2020, a dashboard isn’t how she thinks. Both setups work because each one fits the person using it. Seeing Jenny’s made Julia realize she had designed hers around years of habits from older tech, and she never thought to build in voice. Jenny also walks through the habits that keep a front door agent useful over time. It builds a Waze-style system map, so she hasn’t typed a URL in ages. It reviews its own week: what worked, what didn’t, what to change. And it has standing rules to save anything that will help future you. The Missing Manual treats every agent as an experiment that keeps running, not a project you finish. Quick answers What is a front door agent? A front door agent is a single AI agent you go through for all of your work. It runs on a schedule and checks your calendar, files and systems, so it knows what’s happening before you ask it anything. How many AI agents should one person run? Jenny Cotie Kangas went from 33 agents to one. Running many separate agents creates its own management overhead. One agent with access to everything usually gives better context and less friction. How do you keep a personal AI agent useful over time? Schedule a weekly review where the agent checks what worked and what didn’t and suggests changes. Then give it standing rules to save anything that will help future you. Find The Missing Manual wherever you listen to podcasts.

  4. Oct 29

    AI Conference Prep: I Built It, Then Gave It Away

    The fastest way to get more out of a conference is to build an AI game plan before you go. Julia Levy, co-host of The Missing Manual, built an app for the HR Technology Conference. It researched every exhibitor, matched vendors to her LinkedIn connections, and scheduled her days around meetings, booth locations, and breaks. Two to three weeks of outreach and follow-up lived in one place, and she walked in with meetings already booked. Then Julia shared the app with John Zila, who consults on sales and rev ops for many of the same tech companies. He added his own context and rebuilt it to show which people they had in common, and the two walked the floor together. Jenny Cotie Kangas explains why that works: good is subjective, so everyone who touches a build brings a version of good the original builder could not see. Guarding your AI workflows feels safe, but it limits what they become. Julia and JCK also dig into what the expo floor revealed. Much of today’s HR tech still chases more applicants, while TA teams are buried in volume and fighting what JCK calls a filtering war. Julia argues the fix starts upstream, with intake that defines the problem a role exists to solve and a job description that shows what good looks like. The episode closes with practical AI strategy for agentic work. JCK walks through her AI chief of staff agent, which runs a daily signal brief and prompts her to add repeatable steps to its instructions. Julia shares a habit most people miss: tell your AI when it gets something right, because feedback that only flags mistakes leaves your best results to chance. Common questions answered in this episode How can AI help you prepare for a conference? AI can research every exhibitor, match vendors to people you already know, track outreach and follow-ups, and build a daily schedule around meetings and booth locations, so you arrive with a plan instead of a map. What is the filtering war in recruiting? Jenny Cotie Kangas uses the term for today’s hiring reality, where TA teams receive far more applicants than they can screen. The real challenge is identifying the right candidates, not attracting more of them. Why should you give your AI positive feedback? When you tell your AI what worked, it learns to repeat it. Julia Levy notes that correcting only mistakes makes your best results harder to reproduce. Find The Missing Manual wherever you listen to podcasts.

  5. Oct 22

    The LinkedIn Button That Lies to You

    Halfway into a conversation about LinkedIn visibility, Jenny Cotie Kangas realized a month of posts had never reached her profile. Julia Levy had been tagging her as a collaborator on every Missing Manual post. LinkedIn collaborator posts only appear on your profile after you accept the invite, and Jenny never had. Worse, the Accept button stays on screen after you click it, so the only way to check is your own profile. Jenny opened a browser agent on the spot and had it work back through every invite while the recording kept going. That moment opened up the bigger question of what consistency looks like when life doesn’t cooperate. Julia stepped away from posting for a few months and came back with a rhythm she can actually keep. Her recent post on layoffs has drawn between 250,000+ impressions. She has been laid off herself and has had a say in who was affected on her own team, and she holds a master’s in counseling. Now she’s studying why that post broke through when LinkedIn’s algorithm makes reach so hard to predict. Jenny took the opposite path. She went quiet on LinkedIn while building her company, set up a chief revenue agent and a chief of staff agent, and has three deals about to close. Her lesson for anyone chasing growth: fix the leaks in your funnel before you add more to the top. Julia adds a warning to read LinkedIn’s terms of service before pointing any AI agent at your account. For product teams, The Missing Manual closes with a direct note. When you ship a feature, teach people how to use it, and make sure your interface shows what still needs action. Find The Missing Manual wherever you listen to podcasts.

  6. Oct 15

    AI Agents are not Set it and Forget it.

    AI agents and scheduled automations are not set it and forget it. The requirements you start with are an educated guess, and you often discover what you need only after the agent does something you don’t need. In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas explain how to tune an agent once it is running, and why telling the AI where it falls short is the step most people skip. Jenny starts with a question from a recent workshop. An attendee built a Gmail agent to triage her inbox, and the agent kept stopping to ask for permission. The fix was in the architecture. An agent connected to Gmail on the back end should not need permission every time, but one working through the browser will. Jenny then describes her own signal brief, which drafted replies in her voice across email, WhatsApp, LinkedIn, and text. If she left one email unanswered for five days, she came back to five drafts of the same reply. She rebuilt the agent so it shows her where her attention needs to go, and then they work through each response together. Julia adds that AI models change, so anything built on a model can drift over time. She recommends putting regular reviews of your automations on the calendar, the same way you would review a website. She has Claude interview her at the start of a build and ask what she isn’t thinking of. Then she runs the same conversation through Gemini and ChatGPT to catch what she missed. Jenny suggests going one step further with a scheduled automation that reviews your other automations, checking which model each one uses, its outputs, and its token use. The closing advice from both hosts is direct. If an agent frustrates you, say so to the AI, because it cannot match your idea of good until you define what good is and what it isn’t. Then have the AI ask you questions and challenge you rather than agree with everything. The Missing Manual is also opening up to guests, so if you are building something interesting with AI, Julia and Jenny want to hear from you. Find The Missing Manual wherever you listen to podcasts.

  7. Oct 8

    AI in Recruiting is Solving the Wrong Problems

    AI in recruiting fails most often because companies apply it to the wrong problem. In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas bring back what they heard at RecFest Nashville. Their main observation is that many organizations are using AI to get to the wrong answers faster. The clearest example of AI used well came from a team that pointed AI agents at its recruiting funnel conversion data instead of adding more applicants at the top. The analysis showed that Indeed was not producing quality candidates for those roles. The team turned it off and ended up with stronger candidates. The counterexample was a large company that fixed its internal process but never brought its MSP along. Candidates got a worse experience, and that experience reflected on the employer's brand, not on the MSP. Julia Levy explains why AI screening breaks down when job postings are never fixed. Candidates use AI to match their resumes to the posting, and screening tools grade them against that same posting. If the requirements are wrong, both sides are optimizing toward the wrong target. She also shows how a weak needs analysis and a rushed intake conversation lead to scope creep three months into a search. Jenny Cotie Kangas calls this the same problem wearing different clothes: misalignment that never gets captured in the process. Her fix is to treat AI change as a program rather than a project, and to use AI to build a runbook that helps a first-time hiring manager pre-mortem the search before the role opens. The Missing Manual is a podcast for working professionals about the unwritten rules of work, careers, leadership, and AI strategy, with every episode under 20 minutes. Find The Missing Manual wherever you listen to podcasts.

  8. Oct 1

    AI Needs the How

    Talent acquisition teams do not need more convincing to use AI. At RecFest 2026 in Nashville, most of the leaders in the room already had leadership buy-in and access to tools like Claude and ChatGPT. What they wanted was the actionable how: which use case to start with and how to build it. In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas recap two days of hosting, speaking and listening at one of the biggest TA and HR conferences in the US. Jenny Cotie Kangas spoke on the applied AI stage. When she asked the standing-room-only audience who had leadership buy-in and who had AI tools at work, almost every hand went up both times. The notes came out when leaders described agents they had actually built, such as a job posting checker and a signal brief. Julia Levy spoke on the "Your ATS Sucks" panel, where teams of every size described the same problems and different ways to work around them. The hosts also explain why RecFest feels like an unconference, and why the relationships built there matter. On the Unplugged Stage, they gave every audience two minutes to meet a stranger, and attendees kept telling them about those connections for the rest of the event. Julia connects this to her relationship bank account idea and to the peers she has called for advice over the years, including people at competing companies, because the problems in TA rarely change from one company to the next. Julia is also honest about her plans that never happened: the QR code business cards, the badge photos and the notebook that stayed blank. The takeaway for your next conference is to go in with a plan, meet people outside your own team and follow up afterward. Find The Missing Manual wherever you listen to podcasts.

About

The Missing Manual: Documentation for the Doers In the world of work, there are the skills that get you the job, and then there’s the tradecraft required to actually build. Hosted by Julia Levy (Fortune 500 Talent Acquisition Executive) and Jenny Cotie Kangas (Future of Work Disruptor), this is an unscripted deep-dive into the high-stakes execution that doesn't come with an instruction book. We go beyond "career hacks" to provide a forensic look at organizational navigation and institutional tradecraft. From the mechanics of a multi-million dollar RFP to the front lines of Agentic AI and Talent Operations, we explore how the corporate machine actually moves so you can build within it effectively. What we document: The Future of Work: Moving beyond the "cracked" resume infrastructure and into Agentic AI handoffs. Organizational Mechanics: Navigating the "unwritten rules" of cross-functional execution and budget defense. Operational Strategy: Using Design Thinking and lean execution to save work from failure. We don't believe in "easy buttons." We believe in the hard, intentional work of building something that lasts. If you are a builder looking for the map to the modern corporate landscape, this is your manual.