Advertise on podcast: The Missing Manual Show

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.

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.

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.

To get the most out of attending a conference with AI, have it interview you first. Define your goals, the problems you need solved and the tools you already use. Then send AI to research the sessions, speakers and exhibitors that match. On this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas explain how to plan any event around what you actually came for. Jenny Cotie Kangas starts with step zero: know your current state. When AI asks about your goals and your tech stack, it shows you the gaps worth closing and gives your research a direction. Julia Levy adds the next layer. Filter speakers by industry and company size, because they likely face the same problems you do. Then use AI to narrow everything into a schedule that balances sessions, exhibitor conversations, networking and some fun. You cannot boil the ocean in two days. The hosts also cover how to check what a vendor claims. Software companies put their best foot forward, much like an online dating profile. G2 ratings help, although G2 leans positive, so read the lower reviews too. Julia recommends asking peers in professional communities, since a vendor will not hand you a reference who will criticize it. Jenny shares a client project where AI agents collected every speaker's company, found its career site and identified its applicant tracking system, which confirmed her hypothesis about which ATS dominated the lineup. The Missing Manual gives working professionals the practical how behind work, careers, leadership and AI strategy, in under 20 minutes. Find The Missing Manual wherever you listen to podcasts.

Can your applicant tracking system be gamed? Yes, and this episode of The Missing Manual shows you exactly how to check. Julia Levy and Jenny Cotie Kangas break down AI resume prompt injection, the practice of hiding invisible instructions inside a resume that tell an AI screener to move a candidate forward regardless of fit. Research out of Duke University found the pattern in roughly one percent of a 200,000-resume sample, and Julia and Jenny explain why that number is likely to grow as more applicant tracking systems bolt on AI without telling buyers exactly what it touches. The conversation moves quickly from the resume problem to the vendor problem. Jenny lays out the two-pronged defense every hiring team needs: work directly with your ATS vendor to ask how they're arming against prompt injection and how they red team their own technology, and separately, test your own process by building a candidate application specifically designed to break it. Julia and Jenny are direct about what happens next if that test reveals a real gap. It is not something to quietly patch. It is a conversation for legal and HR leadership. The back half of the episode turns to the human side of AI hiring fraud: candidates and employers misrepresenting themselves, deepfake interview avatars, a low-tech but effective way to catch one on a video call, and a real story about a former employee who got someone else to sit in for their interview. Julia and Jenny close with the harder truth underneath all of it: candidate behavior is going to keep evolving, and the organizations that fare best are the ones pressure testing their hiring process regularly instead of setting it once and walking away. The Missing Manual exists to name exactly this kind of unwritten rule before it costs you. Find The Missing Manual wherever you listen to podcasts.

Cognitive load—the amount of information your brain can track at once—is a real limiting factor in how much you can actually accomplish. When that load gets too high, you're not just tired; you're stuck. The Missing Manual walks you through how AI agents (systems built to handle specific tasks on your behalf) can reduce that load by doing the indexing work most people do manually. Julia and Jenny share three concrete examples from their own work. The first came from RecFest: Jamie Leonard posted a thread with 41 comments about conference fringe events, and a Claude agent pulled all that scattered information into one clean list organized by day. The second example is Julia's work launching Your Network Read, a LinkedIn analysis tool that produces 38-page reports—which she then optimized with AI to reduce duplication and improve readability for her users. The third is how agents can audit your existing presentations and documents to ensure they meet accessibility standards (contrast ratios, cognitive load, compliance) before you publish them. The key insight: these are exactly the right uses of AI. Not to replace thinking. Not to write your ideas for you. But to handle the cognitive work of indexing, organizing, and quality-checking so you can focus your actual brain on decisions only you can make. Find The Missing Manual wherever you listen to podcasts.

The fastest way to make AI agents useful in your organization is to map the work that never made it into a system in the first place. On this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas explain why every system leaves work behind, and why that leftover work, sitting in spreadsheets, inboxes, and people's heads, is exactly what has to get mapped before any agentic AI tool can do something real with it. Julia Levy and Jenny Cotie Kangas trace this problem across several real situations. Julia points to visa and mobility tracking, a process that in most organizations sits with a single person and carries legal and personal consequences if a step gets missed. She also describes mapping decades of undocumented process inside her family's chocolate business, using live interviews and AI transcription to pull knowledge out of long-tenured staff and onto paper for the first time. Jenny Cotie Kangas describes coaching a private insurance adjuster through three weeks of narrating his own judgment calls, work he found tedious, that let his team build an agent system able to label and file a hundred and forty four claim photos in four minutes instead of four to five hours. The Missing Manual keeps returning to the idea that the tool is never the first problem. Julia Levy and Jenny Cotie Kangas point to emerging technology, including audit tools built by Mike Hennessy's Grace Blocks and the experience layer approach from Matt Ekstrom's Sync to Hire, as evidence that more of the industry is waking up to this same gap. Both hosts agree that mapping shadow work is not glamorous, but it is the actual prerequisite for building AI that fits how an organization really operates, rather than forcing every process into a one size fits all system. This episode continues The Missing Manual's ongoing look at agentic work and AI strategy, the same territory that shapes the show's take on corporate navigation and workplace tactics for anyone building an executive career. Find The Missing Manual wherever you listen to podcasts.

Conference season arrives with more invitations than budget, and the decision most practitioners make by default is the one that costs them the most. Julia Levy and Jenny Cotie Kangas open this episode of The Missing Manual with the question that should come before any registration form: what problem are you trying to solve this year. Everything else follows from the answer. If the problem is vendor selection, the room you need looks nothing like the room you need when the problem is craft development or peer benchmarking. The field sorts into four buckets. Vendor user conferences run by the tools already in your stack. National industry events like the HR Technology Conference and UNLEASH, which carry the broadest and deepest vendor presence. State and regional gatherings such as SHRM Talent and the state SHRM chapters. And local or free options, including the events run by regional recruiting networks, that cost almost nothing beyond your time. Jenny makes the case that most practitioners skip the cheapest option available to them, because a customer of a vendor running a user conference can usually get a ticket at no cost, and sometimes travel, simply by asking the account rep who already has levers on the back end. Julia spent 25 years in Fortune 500 talent acquisition without attending a single SHRM conference, and she explains why. When she was coming up, the competency model did not include talent acquisition at all, which told her where she sat in the priority order. She also did not attend the HR Technology Conference until last year, because at her companies the HRIS team owned that trip. Both are examples of the same discipline: matching the room to the problem, rather than attending because everyone else is. Jenny adds a systems read on the physical environment itself, noting that an outdoor format like RecFest produces measurably different attendee behavior than a hotel ballroom where half the audience is still working the day job. The episode closes with the five checks Julia runs before booking anything. Name the problem you are solving. Confirm the vendors you need are actually on the floor. Confirm the sessions cover the part of the craft you are trying to build. Look at whether the speakers come from companies you would want to learn from. Then call two peers who have been and ask them straight. The Missing Manual exists to close the gap between knowing a decision matters and knowing how to make it, and a conference budget is one of the clearest places that gap shows up. Find The Missing Manual wherever you listen to podcasts.   [00:00] Conference season and the practitioner budget problem [00:34] Mugs, Ted Lasso, and meeting at UNLEASH Las Vegas [01:39] Why Julia skipped the LinkedIn and Indeed conferences [02:20] SHRM and the talent acquisition afterthought [03:31] The four conference buckets, vendor, national, state, local [03:50] How to get a free vendor conference ticket and travel covered [04:47] Local and free events worth tracking [05:35] RecFest and the Unplug stage [06:20] Why outdoor conferences change how people show up [07:45] Fresh voices versus the same speaker rotation [08:20] HR Tech and UNLEASH for vendor shopping [ 09:32] Evolve and the case for smaller practitioner rooms [10:15] The five questions to ask before booking

Most people run their job search the same way, opening a job board, typing in a title, and scrolling through hundreds of roles that almost fit. In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas show a different way to do it, using AI agents that search for roles by fit instead of by title and build a resume that is one size fits one for each posting they find. The heart of the episode is a principle Jenny keeps coming back to, that good is subjective to the individual person. Before any agent can help you, you have to define what good looks like for you, and most people never pause to do it. Jenny walks through the system she built to find applied AI roles, starting with an interview that draws out her version of good, then a grounding document, then a career blueprint that captures everything she has ever done, then a daily search that finds the roles and a running log that keeps her agents from surfacing the same one twice. Julia brings the buyer side view from 25 years leading talent acquisition inside Fortune 500 companies. She and Jenny spent their careers building these systems on the employer side, and this episode is the flip side, the same power handed to the person looking for their next role. Julia also adds the step she learned to rely on, naming the environments that are a hard no so the search filters them out before they ever reach her. Jenny productized her entire search into a free guide called the Builder's Playbook and put it on GitHub for anyone to use, because the job search can be a defeating process and everyone deserves a real shot at their next right thing. The link is with the episode. Find The Missing Manual wherever you listen to podcasts. Access Jenny's step by step process FREE here: Job Search Automation

The forward deployed engineer is the new and hot role in AI, and most job descriptions ask for eight to twelve years of software experience. Julia Levy and Jenny Cotie Kangas think that requirement is looking in the wrong place. In this episode of The Missing Manual, they make the case that the person best equipped to get a forward deployed engineer role right is often a great recruiter who has never written a line of code. A forward deployed engineer gets to know a specific user's problem in full, understands its one-size-fits-one nature, then reverse-engineers a build to solve it and ships it into that user's world. Jenny walks through the double diamond design model that sits underneath the work, where you define the right thing before you build the thing right. Her own aha moment is the heart of the episode. The eight to twelve years of experience she has for this role did not come from software. It came from talent acquisition, where you work with a hiring manager to define what right looks like, then go find that person in the wild. Julia adds the piece that makes or breaks it. Design bias is the wall. The people who have already decided how a problem should be solved cannot see the problem clearly enough to solve it, and a career insider who has done everything the same way for years can be the most stuck of all. The two of them name the recruiter traits that map directly onto the FDE skill set, from tactical empathy to building relationships across departments to deconstructing a role into the parts that actually matter. They point to sourcers like Shally Steckerl who were doing this work before the title existed. For HR and TA leaders, the takeaway is practical. Before you hire an engineer, look at the full-cycle recruiter or sourcer you already have, because the business to technical translation this role runs on is a skill your best people are already using. The Missing Manual exists to hand you the how that never makes it into the manual, and this episode gives you a clear way to find forward deployed engineer talent inside your own team. Find The Missing Manual wherever you listen to podcasts.

Job posting errors cost employers more than embarrassment. Missing salary data in transparency states, template instructions published by accident, and dropped EEO statements create legal exposure and send candidates a signal about how the organization runs. In a world where LLMs read and rank job content, those errors also make employers harder to discover. On this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas dig into why these errors are everywhere and what AI agents can now do about them. Jenny shares the story behind Rec Check, an agent she built after an industry friend asked whether AI could audit his company's public job postings. The agent pulls a public job feed, indexes every error, and returns a list with the requisition number, the problem, and a recommended fix. Her audit across 1,100 live postings at one organization surprised both of them, and the same concept worked when pointed at Ashby, Greenhouse, and iCIMS feeds. The bigger lesson comes from a principle Jenny learned from a former leader: lean teams cannot afford symptom mitigation alone. Many posting errors trace back to configuration issues upstream in the ATS, so the agent also flags the problems that can be fixed once at the source. Julia adds the talent acquisition leader's view from 25 years inside Fortune 500 organizations, including why candidates judge employers for posting errors the same way recruiters judge resumes, and where compliance mistakes turn into settlements. The Missing Manual is built for working professionals who want the practical how, not the theory. If you run a TA function and have never audited your live postings, this episode will change your Monday. Find The Missing Manual wherever you listen to podcasts.

How to write better AI prompts is less about memorizing a framework and more about learning to have a real conversation. Julia Levy and Jenny Cotie Kangas break down what actually makes a prompt work and why letting the AI help you build the prompt is one of the fastest ways to get there. Most people either type into AI like it's a Google search or freeze up worrying their prompt isn't good enough. This episode covers how to narrow the aperture, use constraints as a superpower, save your best prompts for reuse, and know when to bring in a different tool for a different job. Chapters [00:00] Why people have prompt anxiety and why it's fixable [00:33] Using AI to write your own prompts [01:14] How Julia started: chatting vs. prompting [03:16] Narrowing the aperture: the recruiting lens applied to AI [05:10] Real example: building LinkedIn carousels and switching tools for images [07:42] Constraints as a superpower: why AI likes guardrails [08:03] Ask the AI to interview you before you start [09:40] How to capture a great prompt so future you can use it again [10:34] Spreadsheets, projects, and gems: where to store what works [11:22] A note on sourcing and PII: what to keep out of your LLM [12:17] The one thing: choose to begin Hosts: Julia Levy (julia-levy.com) + Jenny Cotie Kangas | The Missing Manual Podcast Tags: prompt engineering, AI prompts, how to use AI, AI for HR, AI for recruiters, AI productivity, ChatGPT prompts, Claude AI, Gemini AI, LLM prompts, AI strategy, agentic AI, future of work, Julia Levy, Jenny Cotie Kangas, The Missing Manual podcast, AI tools, AI for professionals, workplace AI, AI tips

Your Network Read is a tool Julia Levy and Jenny Cotie Kangas built to help people show up correctly on LinkedIn — whether they're actively job searching, building a personal brand, or selling into their network. This episode of The Missing Manual is what happened when Jenny Cotie Kangas stopped building it and actually ran it on herself. The output was immediate and specific. Skills tagged as Microsoft Office that hadn't been relevant in years. An industry classification left over from a previous role. Gaps that were invisible until the tool named them. JCK walked away with a clearer LinkedIn and a sharper reminder of why they built Your Network Read in the first place: most people don't know what's working against them until something shows them. The tool shows them. Julia Levy and Jenny Cotie Kangas also talk through what it actually looks like to bring a product to market when it's just the two of you — no marketing team, no launch playbook, no blueprint to follow. The mindset that's making it work: stop asking what could go wrong and start asking what if it went right. Julia brings in a parallel reframe she used with job seekers in graduate school, and JCK shares the free two-part prompt she posted on LinkedIn this week to help people define their version of good before they start a search. It's been tested across industries and career levels, and the feedback has been consistent: people hadn't thought through this before. Life has also been a lot. Julia's dad had open heart surgery. The Missing Manual missed a week. Julia Levy and Jenny Cotie Kangas showed up anyway. Find Your Network Read and the free job seeker prompt on JCK's LinkedIn. Find The Missing Manual wherever you listen to podcasts.

When life moves fast and nothing goes according to plan, most people don't need another framework. They need a map for the moment the frameworks don't cover. That's what this episode of The Missing Manual is. Julia Levy and Jenny Cotie Kangas (JCK) are bringing you into a real week.  Julia traveled to Florida for a short trip to help a parent through knee surgery and ended up staying through an ICU stay and an upcoming surgical procedure. JCK stepped fully into her consulting company, Whiterock Road, after exiting her last role, and navigated what it looks like to move forward with clarity when the timing isn't clean. Both hosts missed a week of the show. Both kept going anyway. In this conversation, Julia and JCK talk through what actually helped: accepting support from people you didn't expect to show up, articulating what you need even when you're not sure, and finding the specific, personal version of good that regulates you when everything else feels uncertain. JCK's version involved a ten-dollar gallon of paint and a backyard she's been slowly reclaiming. Julia's involved hospital hallway walks, text threads, and a few minutes of sunshine between doctor updates. One size fits one. That's the through-line. They also talk about Julia's AI tool, Your Network Read, currently in final build-out with JCK's help, and what it looks like to hand a passion project to someone you trust when you don't have the headspace or time to carry it yourself. That's not failure. That's a pivot. Find The Missing Manual wherever you listen to podcasts.

What happens when you build something useful in AI and then life gets in the way for two weeks? Most people lose everything they built and start over. In this episode of The Missing Manual, Julia Levy and Jenny Cotie Kangas show you how to pick back up without losing momentum — using their own podcast production system as the case study. Julia and Jenny walk through re-grounding their Claude project, recovering prior work from across tools, and building a five-phase process map with a companion grounding document that will anchor every future session. They cover why you need two paired documents for any mapped process — a visual map and a context document that captures what the map cannot — and why those documents are what make automation possible later. Jenny's core principle throughout: if you don't collect the dots, you can't connect the dots. The episode closes on what Julia calls the most important document they produced all day: the handoff. When you are doing big thinking work in AI, the context window is limited, and compiling too much on top of itself leads to hallucinations. A clean handoff document at each stopping point is not overhead — it is the system that lets you come back. This applies to podcast production, client deliverables, hiring processes, or any repeated work effort where continuity matters. The Missing Manual exists because the how is missing everywhere. This episode is the how for anyone who has ever started something in AI, paused, and wondered how to find their way back in. Find The Missing Manual wherever you listen to podcasts.