Agentic HR Playbook

How HR leaders build with AI, step by step

At the 2026 Charter Workplace Summit in New York, Clara Shih shared that she believes the HR team will be the most critical team for AI transformation in the coming years. A big statement, and one I stand behind wholeheartedly. Yet so many messages to HR right now feel diminutive: implement AI, so you can do more with less.

We think about things differently at Leapsome. We believe in unleashing HR teams from the administration and bureaucracy, and enabling our expertise to thrive in Talent Management, Recruitment Strategy, and Organizational Design work. Agentic HR means handing the repeatable parts of HR work to AI agents (the policy questions, the document chasing, the workflows that just need to run) so your time goes to the work that genuinely needs a person: judgment, relationships, the hard conversations.

This playbook shows you what Agentic HR looks like in practice: real builds from HR leaders using AI in their daily work right now, broken down step by step. What they built, why they built it, and exactly how, so you can take any one of these and run it yourself this week.

And that's my one ask of you: play. The only way to learn this is by doing it. Don't overthink your first attempts to learn, and don't worry about getting it wrong. Nobody is really an expert in this yet (truly, nobody), so the advantage goes to the people willing to try, fail, and try again. Start somewhere imperfect. Enjoy your work. It's why we love what we do so much.

Featuring

Emily MabieEmily Mabie
Melanie NaranjoMelanie Naranjo
Sonja GrabnerSonja Grabner
Coming soon
Adam HorneAdam Horne
Paulina Sophie AugustinPaulina Sophie Augustin
Jonathan Durnford-SmithJonathan Durnford-Smith

Agentic HR Playbook

Arbeitet mit KI wie führende HR-Profis

Auf dem Charter Workplace Summit 2026 in New York teilte Clara Shih ihre Überzeugung, dass HR-Teams in den nächsten Jahren die wichtigste Rolle bei der KI-Transformation spielen werden. Eine große Ansage, und da stimme ich voll zu. Trotzdem wird HR in vielen Botschaften gerade kleingeredet. Meist heißt es nur: Führt KI ein, damit ihr mit weniger Leuten mehr schafft.

Bei Leapsome sehen wir das anders. Wir wollen HR von Admin und Bürokratie befreien, damit ihr eure Stärken in Talentmanagement, Recruiting-Strategie und Organisationsentwicklung ausspielen könnt. Genau das heißt Agentic HR. Die KI beantwortet Fragen zu Urlaub oder Spesen, fordert fehlende Unterlagen an und wickelt Prozesse ab, die immer gleich laufen. So bleibt eure Zeit für Entscheidungen, Beziehungen und schwierige Gespräche – die Arbeit, für die es Menschen braucht.

In diesem Playbook erklären euch HR-Profis Schritt für Schritt, wie sie heute schon mit KI einen Unterschied machen. Ihr seht, welche Prozesse sie automatisiert haben, warum und wie genau. So könnt ihr jedes dieser Beispiele direkt selbst ausprobieren.

Darum bitte ich euch nur um eins. Probiert es aus! Lernen klappt hier nur durchs Machen. Denkt bei den ersten Versuchen nicht zu lange nach und habt keine Angst vor Fehlern. Weil die Technologie so neu ist, lernen gerade alle noch. Im Vorteil ist, wer ausprobiert, scheitert und es noch mal versucht. Fangt irgendwo an, auch wenn es nicht perfekt ist. Und habt Spaß dabei, denn genau deshalb lieben wir unseren Job.

Mit Beiträgen von

Emily MabieEmily Mabie
Melanie NaranjoMelanie Naranjo
Sonja GrabnerSonja Grabner
Demnächst
Adam HorneAdam Horne
Paulina Sophie AugustinPaulina Sophie Augustin
Jonathan Durnford-SmithJonathan Durnford-Smith
From the 2027 Workforce Trends Report
81%of HR job postings already expect an AI skill
72%of open HR roles are talent work, not admin
53employees per HR person (median)

→ read the full report

Automation

Agentic People Ops

Featuring Emily Mabie (Zapier), Melanie Naranjo (Ethena) & Sonja Grabner (BEAT81)

Emily MabieMelanie NaranjoSonja Grabner
Chapter 2

People Analytics

Featuring Jessica Zwaan (Leapsome), Adam Horne (Open Org) & Paulina Sophie Augustin (Kayzen)

Jessica ZwaanAdam HornePaulina Sophie Augustin
Analytics

Predictive People Insights

Featuring Adam Horne (Open Org), Jessica Zwaan (Leapsome) & Paulina Sophie Augustin (Kayzen)

Adam HorneJessica ZwaanPaulina Sophie Augustin Coming soon
Hiring

Future-Proof Recruiting

Featuring Jonathan Durnford-Smith (Synthesia)

Jonathan Durnford-Smith Coming soon
Aus dem 2027 Workforce Trends Report
81 %erwarten bereits KI-Kompetenzen im HR
72 %aller offenen HR-Stellen fokussieren sich auf Talentstrategie statt Administratives
53Mitarbeitende betreut eine HR-Kraft im Median

→ Report lesen

Automatisierung

Agentic People Ops

Mit Emily Mabie (Zapier), Melanie Naranjo (Ethena) und Sonja Grabner (BEAT81)

Emily MabieMelanie NaranjoSonja Grabner
Kapitel 2

People Analytics

Mit Adam Horne (Open Org), Jessica Zwaan (Leapsome) und Paulina Sophie Augustin (Kayzen)

Adam HorneJessica ZwaanPaulina Sophie Augustin Demnächst
Recruiting

Future-Proof Recruiting

Mit Jonathan Durnford-Smith (Synthesia)

Jonathan Durnford-Smith Demnächst

Automation

Agentic People Ops

You've explained the PTO carryover policy to the 77th person this year. You've copy-pasted the same onboarding contract into Gmail eighteen times this week. Somewhere in there, you were supposed to find an hour to hash out a new comp philosophy with your CEO. Instead, you spent it on admin a system could have handled without you.

That's the whole premise behind Agentic People Ops: agents handle the stuff that just needs to run (onboarding, document chasing, the same three questions on repeat), so the people team is left with the parts only a person can do. "Agents," "MCPs," "agentic AI-powered automations," the vocabulary feels like it was built for engineers, not HR. The idea underneath is simpler: the busywork moves onto autopilot.

In this chapter, three HR leaders show you exactly how they build with AI: a Slack helpdesk that answers HR questions on its own, a custom bot that stops vague performance reviews before they go out, and an onboarding workflow in Leapsome that runs with no manual setup.

From the 2027 Workforce Trends Report
72%of open HR roles are talent work, not admin
28%of open People roles are still administrative work

→ read the full report

1. Build an HR helpdesk that answers all the small questions (so you don't have to)

Meet Emily, AI Innovation Lead for People at Zapier.

Emily is arguably the queen of HR automations, heading up this topic at Zapier (a platform that is literally all about automation). Emily's perspective is that anyone can be technical, even if they don't write code, and she really earned her AI chops by trying stuff out, experimenting, getting stuff wrong, and sharing what she learned. So we could think of no better person to speak to for our first AI build. Here we'll talk you through an automation she set up for recurring HR requests in Slack.

Emily Mabie
“The person who feels the pain of their unique circumstance every day is going to build the best solution. The heart of that is customization. If I have a chair that's customized for me, it's going to be more comfortable and meet my needs better than a chair built for anyone.”

You might have the most up-to-date and in-depth HR policy document in the world, but surely all your employees have not read that 15-page document, nor have they memorized it. So when an HR question comes up, be it on parental leave or development budget, the same questions will pop up again and again. To take this off her team's plate, Emily created a virtual HR helper with Slack (but you can apply this same setup wherever your HR questions live) and Zapier. Here's how to build it.

Read transcript

Picking and testing the trigger

"When a new message comes in in our Slack channel, then I want those people to get their needs met. So the trigger is the 'when' part of the sentence. And if you're thinking, 'Emily, we don't use Slack, we use something else,' great news, Zapier has over 9,000 different apps to choose from. I'm choosing Slack, but you could explore a different app your team uses. I'll say: new message posted to channel. This will wake up our automation whenever there's a new message posted in that channel. For you guys, I'm using the test webinar channel, but if I were to turn this on internally, I'd use the HR channel, wherever most people ask their questions."

Writing the prompt

"Our trigger wakes up the automation, and then any actions we put after it are going to do the things I want in order to meet the goal. I'm using this thing called AI by Zapier. At the top, it has a prompt, instructions we write for AI to take action. In this case, we're going to give it tools so it can go do things we want. Number one, I want it to read the whole thread of messages, because at Zapier a lot of times there'll be seven or eight messages of people adding context and I don't want it to just read the top message. I want it to use knowledge sources, because we've got documentation in HR, our problem isn't needing more documentation, it's needing people to get what they need out of it. I want it to give the actual answer if it's in the documentation. I don't want it to guess or overwhelm the user. If something is sensitive, somebody comes into the channel and says 'my colleague punched me at an offsite, what should I do?' that doesn't belong in the channel. I want to reroute them to the right person. And if they have an answer, put it in the Slack thread, don't make the channel messy."

Adding the tools

"The last thing you need to know about using this tool is it cannot do any of those things unless we add in the tools to allow it to reach into our apps. I asked it to read the whole thread of Slack messages, we didn't give it a tool for that, so we have to give it the Slack tool. We also have to give it knowledge sources, wherever we've documented our HR policies. And I also need to give it the ability to reply in Slack. Just because we gave it permission to read a thread doesn't mean it has permission to send a message, and vice versa. The last thing I want to do is make sure it has access to our HR documentation, I'm not going to add one more tool, I'm going to add a knowledge source, point the agent at wherever I keep my documentation."

The live test

"I'll go ahead and choose our laptop provisioning guide, point it there, and click preview to see it work. Remember, I posted in the Slack channel: 'Hey, I'm a new hire, my laptop hasn't arrived yet, is there something I should be doing?' My agent build is kicking off, reading the whole thread, searching our knowledge source. [Result shown:] 'Hey Emily, great question. You're in the UK. It usually takes up to two weeks to get your laptop. In the meantime, please don't use your personal computer for work. If it's been more than two weeks, let us know.' It's not that I'm replacing an HR team, we never had a whole HR team whose only job was to monitor Slack. This just augments their time so they have more time to do the human stuff. We're not replacing, we're just augmenting."

  1. Start where the repeat questions already live

    Wherever the requests are landing, whether it's a Slack channel, an email chain, or a Notion request board, this should be your starting point. For Emily, that's the Slack channel where HR questions pile up, so in this use case, she used the "new message posted to channel" trigger and pointed it there. Zapier integrates with a ton of different platforms, so you can be pretty flexible here.

  2. Add an AI step that checks your policy docs before it answers

    Right after the trigger, add an AI step, and tell it what to check before it replies: read the full thread for context, then check it against your HR policy documentation, wherever that lives, Notion, Google Drive, an internal wiki. If the answer is already written down, it answers directly. If the question touches something that needs a judgment call, like a specific leave situation or a performance issue, it skips answering and routes it to a person instead.

  3. Give it permission to do something

    Right now the AI step can think, but it can't act. In Zapier, add three connections: one that lets it read the Slack thread, one that lets it reply in the thread, and a knowledge source pointing at your HR documentation (for Emily, a laptop provisioning guide). Skip any of these and it can draft a perfectly good answer that never reaches anyone.

  4. Test it on the question you're dreading, not a fake one

    Emily tested hers on a real question already sitting in the queue: a new hire asking where their laptop was. The bot pulled the answer from the provisioning guide, replied correctly, and held up on a follow-up without losing the thread. Don't test yours on something you already know the answer to. Point it at whatever's unresolved right now.

Context is what makes this work, Emily says: the AI only answers as well as the documentation it's pointed at. "We're not replacing," she says, "we're just augmenting." The hours that used to go into finding and re-sharing the same links now go back to the team.

How to do this in Leapsome

The same answers, already inside Leapsome

Emily built her helpdesk because the answers lived in a policy doc nobody opened. Leapsome's HR Helpdesk Agent does the same job, built in: load your carry-over rules, parental leave policy, and expense guidelines into the Knowledge hub once, and when someone asks Leapsome AI how many days they can carry over, the answer comes from what's written down, inside the platform they already use. Anything that needs a judgment call goes to a person.

Read transcript

One extra day every week

"What would your HR team do with one extra day every week? For most teams, that day disappears into admin work, summarizing survey comments, chasing review drafts, writing meeting notes, and building development plans one person at a time. That's what Leapsome's AI agents take off your plate. They work across the entire platform: in surveys, goals, meetings, reviews, and everything in between. In this walkthrough, I'll show you how."

One connected data model

"An AI agent is only as good as what it knows. Most HR AI data sits on top of a single tool and sees a single slice of your people. Leapsome agents work on one connected data model, HRIS, recruitment, performance, engagement, goals, learning, and compensation. So when an agent drafts a review, suggests a goal, or builds a learning path, it already has the full picture. Access rights and anonymity stay in place the whole time."

Engagement survey

"To show you what it looks like, let's follow one quarter in the life of an HR team. We can start with our latest engagement survey. I've got dozens of comments and a leadership meeting on Thursday. I do not have time to read them all. Thankfully, the assistant does it for me. It can group my comments by themes, show where sentiment shifted since the last survey, and point to the teams that need special attention. It also suggests what to do next, which topics managers should raise with their team, and where HR should step in."

Turning it into a goal

"The survey told us where to focus. Now let's turn that into a goal for the next quarter. The assistant drafts the goal and the key results. From there, I'm able to edit the goal so it perfectly fits my needs."

The weekly one-on-one

"Next up, the weekly one-on-one. Before the meeting, the assistant suggested talking points based on goals, recent feedback, and past meetings. I'm able to pick up the conversation exactly where the last one ended. Because I'm transcribing within Leapsome and taking notes, afterwards I'll get a summary giving me insights into how the conversation went and how I can improve for next time. It'll also pull out various action items or other things that need to be done in Leapsome automatically. Because the agent serves as both an assistant and a coach, I can ensure that my one-on-one meetings are more effective moving forward."

Review time

"It's now the end of the cycle, which means review time. This is where managers often get stuck. The review assistant pulls in context from the whole quarter: goal progress, feedback, and meeting notes. It helps phrase observations with concrete examples and suggests growth-oriented next steps, and the manager stays in charge. The assistant suggests, and you ultimately decide what goes into the review."

From feedback to a learning path

"The review is done, and now let's turn that feedback into growth. Based on the review, the assistant suggests a learning path, with content, milestones, and timing. I can discard the content that doesn't work for me or ask it to regenerate. Progress is tracked automatically and feeds straight into the next review."

One connected loop, then workflows

"Surveys, goals, one-on-ones, reviews, and learning paths. One quarter, one connected loop. At every step, an agent did the heavy lifting while people made the decisions. And because every agent works in the same data, you can take it one step further. With workflows, all this context starts working on its own. A review closes and a learning path is assigned automatically. Engagement drops on a team, and the manager gets a one-on-one talking point and a check-in task. I can upload documentation I've already built to the workflow assistant, and it will build out the baseline for me. Like everything else, I can always go in and adjust the steps to perfectly fit my needs."

A dashboard for leadership

"And when leadership asks how the company is really doing, you don't need to spend a week pulling reports. Describe what you need, and Leapsome builds a dashboard in seconds. Survey themes, goal progress, review results, and learning activity all in one view. CEO-ready, filterable, and linked back to the underlying data."

Wrap-up

"That's a look at agentic HR with Leapsome, AI agents that work as an extension of your HR team across the entire employee lifecycle. Human review by default, clear permissions, and outputs you can track back to data. Your agents draft, summarize, and suggest, so you have the capacity to lead. Thank you so much."

2. Create a reviews GPT that asks for the receipts

Meet Melanie, Chief People Officer at Ethena.

Melanie heads up the People org at Ethena, a compliance and ethics software company.

Melanie's issue was that she had a streamlined performance review process that was carefully thought out and implemented, yet she was finding that managers were often showing up with vague and ineffective feedback in review cycles. Without good feedback, the whole effort was essentially pointless. It was not scalable to have HR manually check and review feedback, so they needed a scalable way to increase the standard across the board. So Melanie built a custom GPT to handle this.

Melanie Naranjo
“I think sometimes managers struggle with, 'I don't know where to start. I know what I have to say, but I don't know how to say it, I don't know how to format it.' The reality is, it doesn't matter to me if you're a good writer or good at putting things into a template. What matters is whether you're providing the important substance.”

To build something similar, here's how.

Read transcript

Live demo

"This is a custom GPT that I built for performance reviews, you'll see I put in just the worst possible prompt so you can see the power. I said: 'My direct report is struggling to meet their deadlines and isn't a great communicator, can you help me start drafting their performance review?' And rightfully, it said, 'Please provide me the job description before I begin,' because it knows you can't give good feedback if you don't know what metrics you're measuring. I copied and pasted one, and it said, 'Thanks for providing the job description and the salary band, since we are missing several critical details required by the performance review standards, I've set up the official template layout below with the necessary placeholders.' I think sometimes managers struggle with, 'I don't know where to start, I know what I have to say but I don't know how to say it, I don't know how to format it.' The reality is, it doesn't matter to me if you're a good writer or good at putting things into a template, what matters is whether you're providing the important substance. It will ask you for things that are missing: can you provide two to three specific instances where a deadline was missed, because this happens a lot with managers, they'll say 'you're missing deadlines,' and the honest answer when pushed is often 'well, not really.' This just helps them really think. All of this is taking it off my plate so they don't have to talk to me."

Full session only

"Nobody's an AI expert"

"Don't be scared, don't be intimidated, just open up an app and start asking questions, you will be surprised at how easy it is."

  1. Set up a saved assistant, not a one-off prompt

    Build it once, with its own instructions, so you or your managers can reopen and reuse it every time instead of re-explaining what you want from scratch. Melanie built hers as a custom GPT in ChatGPT, but most AI tools let you save an assistant like this. Give it a name like "Review Assistant," and you're ready to add instructions. With the Leapsome MCP connected, you can set this up in any LLM that supports MCP and let it pull the employee's details from Leapsome instead of pasting them in (there is also an AI review assistant baked directly into the Leapsome platform).

  2. Set it up to ask for the job description first

    In your assistant's instructions, tell it not to draft anything until it has the employee's job description. Feed it a complaint with no context, and it should stop you before it drafts anything real.

  3. Have it build the review template and flag the gaps

    Once it has the job description, tell it to build out your official review template around it, and flag anything missing, accomplishments, a salary band evaluation, whatever your template requires. Try testing it with a deliberately thin prompt, something like "My direct report is struggling to meet their deadlines and isn't a great communicator, can you help me start drafting their performance review?" Even with next to nothing to go on, it should catch exactly what's missing before it lets you move on.

  4. Have it push back on vague feedback

    A complaint about missed deadlines isn't specific enough for a review, and managers know it when they're pushed on it: ask for an example of a missed deadline, and the honest answer is often "well, not really." Tell your assistant to ask for two or three concrete instances instead, the same follow-up question a manager should ask themselves, and to coach toward what better looks like instead of just naming what's wrong.

  5. Reuse it every review cycle

    Once it's built, managers just describe the issue in plain language, even a rough voice memo works, Melanie says, and the same assistant handles the formatting and the follow-up questions every time, for every review.

Melanie Naranjo
“Nobody's an AI expert, because even if you're an expert today, what you know is outdated tomorrow. Don't be scared, don't be intimidated. Just open up an app and start asking questions.”

How to do this in Leapsome

AI review assistant in Leapsome that has all the context

Melanie's GPT won't write a word until it has the job description. Leapsome's AI Review Assistant starts from the same rule, without the setup: it already knows the employee's role, level, the competencies they're assessed on, and their goal progress and feedback from the cycle. Hit Start, answer its questions by typing or talking, and it pushes back when an answer is vague or doesn't match what's expected at that level, helping managers write better feedback at scale. Every manager gets a draft to edit and confirm, nothing is submitted automatically.

Read transcript

Shared expectations

"Strong performance starts with shared expectations. In Leapsome, competencies define what success looks like across roles and levels, and then reviews turn those expectations into structured, useful conversations."

Drafting a competency framework

"Let's begin with a competency framework. Instead of starting with a blank page, you can describe your organization, roles, values, and behaviors that you want to see from your team. Leapsome AI then drafts a complete framework that fits that context."

Building the review process

"Once the framework is in place, you can bring the same expectations directly into performance reviews in addition to any other questions you might be looking to add. From there, you can then build the process that your organization really needs, whether that's simply a manager review or a full 360. Leapsome Reviews are highly customizable to ensure that you're getting the perfect fit for your organization."

AI help while writing the review

"During the review, AI helps managers turn their observations into clear, constructive feedback. The review assistant can improve phrasing, strengthen examples, and help the reviewer check whether the feedback is both specific and actionable. They can also use relevant Leapsome context, such as goals and previous feedback, to ensure that the manager is including everything in the current scope of the review. The manager still reviews and edits every suggestion before submitting it, but these AI tools really help to keep the conversation on track."

Analysis and calibration

"After assessments are complete, Leapsome brings the results together for analysis and for calibration. AI-generated calibration pre-reads compare the rating in your reviews alongside goals, feedback, competencies, and historical context before the calibration meeting begins. The pre-read flags can be worth discussing, including managers who consistently rate higher or lower than their peers, or ratings that don't seem to align with feedback that the employee was given. These all allow for prompts for better conversation and ultimately give managers and calibration committees the power to be making the best-informed decision about their teams."

From feedback to growth

"That process doesn't end when the review is shared. Leapsome can turn feedback into suggested next steps, including personalized learning paths that help employees act on development priorities noted in their review. With competencies, reviews, goals, and learning all connected, performance management becomes a continuous system. People know what's expected, managers get better context, and HR can support fair decisions at scale. I hope you enjoyed this look into the Leapsome Reviews module today. If you'd like to see more, we'd love to show you. Bye-bye."

3. Set up an onboarding workflow that runs itself in Leapsome

Meet Sonja, People & Culture Lead at BEAT81.

BEAT81 is a Berlin-based fitness company that runs high-intensity workouts in studios across Germany.

Sonja and her team need to onboard over 15 new freelance workout trainers per week across fitness studios in Germany. That's a lot of new people to process. It meant she and her team were bogged down with a ton of repetitive work: sending out contracts and getting people set up on the system, over and over, studio by studio. Sonja worked directly in Leapsome, BEAT81's HRIS, to set up an automated onboarding process instead.

Sonja Grabner
“It's probably a minimum of 10 hours a month that we save due to having those workflows set up in Leapsome.”

Hear Sonja's story

Read transcript

One tool for HRIS, feedback and reviews

"Because we already had Leapsome in place for feedback and development talks, we decided to, instead of launching a third or fourth tool, move our HRIS to Leapsome as well. And now we have that in one tool. Having feedback and the HRIS part connected allows us to automate certain kickoffs. So for example, now that Leapsome basically knows when this person joined and has their contract information in the HRIS part, the review part knows when to set up a new cycle."

Migration and time saved

"The data migration itself was only around three days, so that was actually super quick. It's probably a minimum of 10 hours a month that we save due to having those workflows set up."

Advice to other leaders

"I would tell other leaders to not be scared of it. It was easier than I thought."

  1. Build the track once per role

    Onboarding tracks combine checklists, tasks, and learning modules, and you set them up per role or department instead of rebuilding one from scratch for every hire. Sonja set hers up so a new coach and a new payroll hire get genuinely different onboarding, not the same generic form.

  2. Let the system assign the work, not you

    Tasks get assigned automatically to whoever owns them, the manager, IT, HR, with reminders going out to keep things on schedule. That's the part that used to mean chasing someone down in Slack.

  3. Start before day one

    Pre-boarding shares welcome messages, documents, and role-specific info before the start date, so new hires show up already oriented instead of filling out paperwork on day one.

  4. Check that it's working

    Dynamic onboarding surveys measure how each path is landing, the real version of what Sonja called a pulse check, a real signal three months in, not just a guess.

How to do this in Leapsome

Describe the workflow. Leapsome builds it.

Sonja set up BEAT81's onboarding tracks step by step. Leapsome's PeopleOps Partner Agent can do that groundwork for you: describe the process instead, something like "Onboard a new coach. Contract before day one, studio intro in week one, feedback talk at day 30," and it drafts the steps, owners, reminders, and approval gates, then lays them out on a timeline you can edit. Nothing runs until you switch it on, and every task lands with the right person, so nobody is chasing anyone in Slack.

Read transcript

From admin to building

"Where does your HR team actually spend its time? For a lot of teams, it's still chasing task owners, copying data between tools, and managing processes that could run themselves. That's what Leapsome Workflows fixes. The best companies expect their people teams to build with AI. They've shifted their people work from admin to strategic talent work. With Workflows, teams working with Leapsome make exactly that shift. They can describe the process they're looking to build in plain language, review the draft, and let it run. HR builds instead of administering. Here's an example."

Uploading an existing onboarding checklist

"Let's say you recently moved to a new HR platform like Leapsome. You can take a look at our recommended best practice library built by HR leaders just like you. Or if you have your own best practices or processes that have worked well for you before, you can upload those directly into Leapsome. I've got an onboarding checklist for our marketing team that I want to move over, so we'll do that together now. All I need to do is upload my existing PDF, and Leapsome's workflow assistant will take care of the rest. And here we are. If we accept these settings and zoom in, we can see what needs to happen both before and after the employee's first day."

Reaching the whole employee lifecycle

"Workflows are only as good as what they can reach. Leapsome's Workflows reach the entire employee lifecycle because the platform covers it in such depth. So I can assign my new hire their first learning path on first steps with Leapsome, update employee data, generate the contract, and create an IT ticket to order all of their new equipment. In a fragmented stack, that would take at least four tools and a spreadsheet keeping track of all of them. You review every step, adjust what you want, and activate it once it's ready. Your next HR workflow really is one upload or even just one sentence away."

Beyond onboarding

"You can do so much more than just onboarding with Workflows. You can do offboarding, policy rollouts, probation period conversations, absence follow-up, you name it. Since Workflows are connected to the entire employee lifecycle, all it takes is one click to have a more connected and cohesive employee journey. Thanks for taking the time to watch today, and if you're interested in learning more about Leapsome's Workflows, please don't hesitate to reach out to us. Bye-bye."

10+ hrs

reclaimed a month once onboarding moved into automated workflows in Leapsome, Sonja Grabner, People & Culture Lead, BEAT81

Automatisierung

Agentic People Ops

Ihr habt die Regeln zum Resturlaub dieses Jahr schon 77-mal erklärt. Diese Woche habt ihr denselben Arbeitsvertrag achtzehnmal per E-Mail verschickt. Und irgendwo dazwischen wolltet ihr eigentlich eine Stunde finden, um mit der Geschäftsführung das neue Vergütungsmodell zu besprechen. Stattdessen ging die Zeit für administrativen Kleinkram drauf, den ein System auch ohne euch erledigt hätte.

Genau hier setzt Agentic People Ops an. Die KI übernimmt Aufgaben, die immer nach demselben Muster ablaufen. Sie stößt Onboarding-Schritte an, fordert fehlende Unterlagen an und beantwortet die immer gleichen drei Fragen. Dem HR-Team bleibt die Arbeit, für die es Menschen braucht. „Agents“, „MCP“, „agentische KI-Automatisierung“ – solche Begriffe klingen nach IT, nicht nach HR. Die Idee dahinter ist einfacher. Die Fleißarbeit erledigt sich von selbst, und ihr behaltet den Überblick.

In diesem Kapitel zeigen euch drei HR-Profis, wie sie mit KI arbeiten. Ein Helpdesk in Slack beantwortet HR-Fragen selbstständig. Ein eigener Assistent stoppt vages Feedback, bevor Reviews rausgehen. Und ein Onboarding-Prozess auf Leapsome läuft ohne manuelles Set-up.

Aus dem 2027 Workforce Trends Report
72 %aller offenen HR-Stellen fokussieren sich auf Talentstrategie statt Administratives
28 %der offenen HR-Stellen drehen sich noch um Administratives

→ Report lesen

1. Ein HR-Helpdesk, der euch die kleinen Fragen abnimmt

Das ist Emily, Leiterin KI-Innovation für HR bei Zapier.

Wenn es um HR-Automatisierung geht, macht Emily so schnell niemand etwas vor. Sie verantwortet das Thema bei Zapier, einer Plattform, bei der sich alles um Automatisierung dreht. Ihr Motto? Alle können technikaffin werden, auch ohne Erfahrung mit Code. Ihr KI-Wissen hat sie sich selbst erarbeitet. Sie hat ausprobiert, experimentiert, Fehler gemacht und ihr Wissen geteilt. Für unsere erste KI-Lösung konnten wir uns also niemand Besseren vorstellen. Hier zeigen wir euch, wie sie wiederkehrende HR-Anfragen in Slack automatisiert hat.

Emily Mabie
„Wer jeden Tag mit dem eigenen Problem kämpft, baut am Ende die beste Lösung. Entscheidend ist, dass sie maßgeschneidert ist. Ein Stuhl, der für mich gemacht wurde, ist bequemer als einer von der Stange.“

Vielleicht habt ihr das aktuellste und ausführlichste HR-Handbuch der Welt. Gelesen haben das 15-seitige Dokument aber sicher nicht alle, und auswendig kennt es niemand. Deshalb kommen dieselben Fragen immer wieder, ob zur Elternzeit oder zum Weiterbildungsbudget. Um ihr Team zu entlasten, hat Emily mit Slack und Zapier eine virtuelle HR-Hilfe gebaut. Das funktioniert aber auch überall sonst, wo euch Fragen gestellt werden. So geht’s.

Transkript lesen

Picking and testing the trigger

"When a new message comes in in our Slack channel, then I want those people to get their needs met. So the trigger is the 'when' part of the sentence. And if you're thinking, 'Emily, we don't use Slack, we use something else,' great news, Zapier has over 9,000 different apps to choose from. I'm choosing Slack, but you could explore a different app your team uses. I'll say: new message posted to channel. This will wake up our automation whenever there's a new message posted in that channel. For you guys, I'm using the test webinar channel, but if I were to turn this on internally, I'd use the HR channel, wherever most people ask their questions."

Writing the prompt

"Our trigger wakes up the automation, and then any actions we put after it are going to do the things I want in order to meet the goal. I'm using this thing called AI by Zapier. At the top, it has a prompt, instructions we write for AI to take action. In this case, we're going to give it tools so it can go do things we want. Number one, I want it to read the whole thread of messages, because at Zapier a lot of times there'll be seven or eight messages of people adding context and I don't want it to just read the top message. I want it to use knowledge sources, because we've got documentation in HR, our problem isn't needing more documentation, it's needing people to get what they need out of it. I want it to give the actual answer if it's in the documentation. I don't want it to guess or overwhelm the user. If something is sensitive, somebody comes into the channel and says 'my colleague punched me at an offsite, what should I do?' that doesn't belong in the channel. I want to reroute them to the right person. And if they have an answer, put it in the Slack thread, don't make the channel messy."

Adding the tools

"The last thing you need to know about using this tool is it cannot do any of those things unless we add in the tools to allow it to reach into our apps. I asked it to read the whole thread of Slack messages, we didn't give it a tool for that, so we have to give it the Slack tool. We also have to give it knowledge sources, wherever we've documented our HR policies. And I also need to give it the ability to reply in Slack. Just because we gave it permission to read a thread doesn't mean it has permission to send a message, and vice versa. The last thing I want to do is make sure it has access to our HR documentation, I'm not going to add one more tool, I'm going to add a knowledge source, point the agent at wherever I keep my documentation."

The live test

"I'll go ahead and choose our laptop provisioning guide, point it there, and click preview to see it work. Remember, I posted in the Slack channel: 'Hey, I'm a new hire, my laptop hasn't arrived yet, is there something I should be doing?' My agent build is kicking off, reading the whole thread, searching our knowledge source. [Result shown:] 'Hey Emily, great question. You're in the UK. It usually takes up to two weeks to get your laptop. In the meantime, please don't use your personal computer for work. If it's been more than two weeks, let us know.' It's not that I'm replacing an HR team, we never had a whole HR team whose only job was to monitor Slack. This just augments their time so they have more time to do the human stuff. We're not replacing, we're just augmenting."

  1. Startet dort, wo die Fragen reinkommen

    Euer Startpunkt ist der Ort, an dem die meisten Anfragen eingehen, etwa ein Slack-Kanal, ein E-Mail-Postfach oder Notion. Bei Emily ist das ein Kanal, in dem sich HR-Fragen stapeln. Deshalb hat sie den Auslöser „Neue Nachricht im Kanal“ gewählt. Zapier lässt sich mit sehr vielen Plattformen verbinden, ihr seid hier also flexibel.

  2. KI prüft zuerst eure Richtlinien

    Direkt nach dem Auslöser folgt ein KI-Schritt. Legt fest, was die KI vor jeder Antwort prüft. Zuerst den ganzen Chatverlauf lesen, dann mit euren HR-Policies abgleichen, egal ob die in Notion, Google Drive oder einem internen Wiki liegen. Steht die Antwort schon irgendwo, kommt sie direkt zurück. Braucht eine Frage eine Einschätzung, etwa beim Sonderurlaub oder vor einem schwierigen Mitarbeitergespräch, geht sie an einen Menschen.

  3. Bestimmt, worauf die KI zugreifen darf

    Bis jetzt kann die KI denken, aber nicht handeln. Richtet in Zapier deshalb drei Verbindungen ein. Eine zum Lesen des Slack-Chats, eine zum Antworten im selben Thread und eine Wissensquelle mit eurer HR-Dokumentation. Bei Emily ist das ein Leitfaden zur Laptop-Ausgabe. Fehlt eine Verbindung, entsteht vielleicht eine perfekte Antwort, die aber nie ankommt.

  4. Testet mit echten Fragen

    Emily hat ihren Helpdesk mit einer Frage getestet, die schon länger unbeantwortet im Kanal stand. Eine neue Mitarbeiterin wollte wissen, wo ihr Laptop bleibt. Der Bot fand die Lösung im Leitfaden, reagierte richtig und blieb auch bei der Rückfrage beim Thema. Testet euren Ablauf also nicht mit etwas, das ihr längst wisst. Nehmt eine Frage, die gerade offen ist.

Entscheidend ist der Kontext, sagt Emily. Die Antworten sind nur so gut wie die Dokumentation dahinter. „Wir schaufeln Zeit und Kapazität frei“, sagt sie. Die Stunden, die früher fürs Suchen und Weiterschicken derselben Links draufgingen, hat das Team jetzt wieder für sich.

So geht’s mit Leapsome

Dieselben Antworten direkt in Leapsome

Emily hat ihren Helpdesk gebaut, weil die Antworten in einem Dokument standen, das niemand öffnete. In Leapsome ist genau das schon eingebaut: Hinterlegt eure Regeln zu Resturlaub, Elternzeit und Spesen einmal im Knowledge Hub. Fragt dann jemand Leapy, wie viele Urlaubstage ins nächste Jahr mitgehen, kommt die Antwort aus euren eigenen Unterlagen – direkt in der Plattform, die alle schon nutzen. Alles, was eine Einschätzung braucht, geht an einen Menschen.

2. Ein Review-Assistent, der Beispiele sehen will

Das ist Melanie, Personalchefin bei Ethena.

Melanie leitet das HR-Team bei Ethena, einem Softwareunternehmen für Compliance Trainings.

Melanie hatte einen durchdachten Review-Prozess eingeführt. Trotzdem kamen viele Führungskräfte mit vagem, wenig hilfreichem Feedback in die Beurteilungsrunde. Ohne gutes Feedback war der ganze Aufwand aber umsonst. Dass HR jede Rückmeldung von Hand prüft, war bei der Unternehmensgröße von Ethena keine Option. Ein neuer Weg musste her, um die Qualität der Rückmeldungen zu verbessern. Genau dafür hat Melanie ein eigenes GPT gebaut.

Melanie Naranjo
„Viele Führungskräfte kämpfen damit: ‚Ich weiß nicht, wo ich anfangen soll. Ich weiß, was ich sagen will, aber nicht, wie ich es formulieren oder aufbauen soll.‘ Ehrlich gesagt ist mir egal, ob jemand gut schreiben oder Dinge in eine Vorlage packen kann. Wichtig ist, ob die Substanz stimmt.“

So baut ihr etwas Ähnliches:

Transkript lesen

Live demo

"This is a custom GPT that I built for performance reviews, you'll see I put in just the worst possible prompt so you can see the power. I said: 'My direct report is struggling to meet their deadlines and isn't a great communicator, can you help me start drafting their performance review?' And rightfully, it said, 'Please provide me the job description before I begin,' because it knows you can't give good feedback if you don't know what metrics you're measuring. I copied and pasted one, and it said, 'Thanks for providing the job description and the salary band, since we are missing several critical details required by the performance review standards, I've set up the official template layout below with the necessary placeholders.' I think sometimes managers struggle with, 'I don't know where to start, I know what I have to say but I don't know how to say it, I don't know how to format it.' The reality is, it doesn't matter to me if you're a good writer or good at putting things into a template, what matters is whether you're providing the important substance. It will ask you for things that are missing: can you provide two to three specific instances where a deadline was missed, because this happens a lot with managers, they'll say 'you're missing deadlines,' and the honest answer when pushed is often 'well, not really.' This just helps them really think. All of this is taking it off my plate so they don't have to talk to me."

Full session only

"Nobody's an AI expert"

"Don't be scared, don't be intimidated, just open up an app and start asking questions, you will be surprised at how easy it is."

  1. Speichert eure Anweisungen, statt neu zu prompten

    Richtet eure Anweisungen einmal ein. So könnt ihr und eure Führungskräfte den Assistenten jederzeit wieder öffnen, ohne jedes Mal von vorn zu erklären, was ihr braucht. Melanie hat dafür ein eigenes GPT in ChatGPT angelegt. Die meisten KI-Tools können solche Assistenten aber speichern. Vergebt einen Namen wie „Review-Assistent“ und ergänzt die Anweisungen. Verbindet ihr Leapsome per MCP, funktioniert das in jedem Sprachmodell mit MCP-Unterstützung. Die Daten zur Person kommen dann direkt aus Leapsome, statt dass ihr sie reinkopiert. In der Plattform selbst gibt es außerdem schon einen eingebauten Bewertungsassistenten.

  2. Fragt zuerst nach der Stellenbeschreibung

    Schreibt in die Anweisungen, dass ohne Stellenbeschreibung kein Entwurf entsteht. Kommt nur eine Beschwerde ohne Kontext, stoppt der Assistent, bevor etwas geschrieben wird.

  3. Vorlage aufbauen und Lücken zeigen

    Mit der Stellenbeschreibung baut der Assistent eure offizielle Review-Vorlage auf und markiert, was noch fehlt. Das können Erfolge sein, die Einordnung ins Gehaltsband oder was eure Vorlage sonst verlangt. Testet das ruhig mit einem miesen Prompt, etwa „Meine Mitarbeiterin schafft ihre Deadlines nicht und kommuniziert schlecht. Hilfst du mir beim Entwurf ihres Reviews?“ Auch mit so wenig Input sollte genau erkannt werden, was fehlt.

  4. Bei vagem Feedback nachhaken

    „Hält Deadlines nicht ein“ reicht für eine Beurteilung nicht. Das merken Führungskräfte selbst, sobald jemand nachfragt. Wer nach einem konkreten Beispiel fragt, geht oft leer aus. Der Assistent soll deshalb zwei, drei konkrete Situationen einfordern. Genau diese Frage sollten sich Führungskräfte auch selbst stellen. Und statt nur Fehler zu benennen, zeigt die KI, wie es besser geht.

  5. Für jede Review-Runde wieder nutzen

    Ist der Assistent einmal eingerichtet, beschreiben Führungskräfte das Thema in eigenen Worten. Laut Melanie reicht sogar eine kurze Sprachnachricht. Formatierung und Nachfragen übernimmt jedes Mal dieselbe KI, für jede Beurteilung.

Melanie Naranjo
„Niemand ist ein KI-Experte. Selbst wer es heute ist, weiß morgen schon nicht mehr genug. Habt keine Angst und lasst euch nicht einschüchtern. Öffnet einfach ein KI-Tool und fangt an, Fragen zu stellen.“

So geht’s mit Leapsome

Der Bewertungsassistent in Leapsome kennt schon den ganzen Kontext

Melanies GPT schreibt kein Wort, solange die Stellenbeschreibung fehlt. Der Bewertungsassistent in Leapsome folgt derselben Regel, ohne dass ihr danach fragen müsst. Rolle und Position der Person sind bekannt, ebenso die Kompetenzen für die Beurteilung, der Stand der Ziele und das Feedback aus der Review-Runde. Startet das Gespräch und beantwortet die Fragen per Text oder Sprachnotiz. Ist eine Antwort vage oder passt nicht zur Erfahrungsstufe, hakt die KI nach. So schreiben alle Führungskräfte besseres Feedback. Alle Vorgesetzten bekommen einen Entwurf zum Bearbeiten und Bestätigen. Eingereicht wird erst mit eurer Freigabe.

3. Ein Onboarding-Prozess, der von selbst läuft

Das ist Sonja, Leiterin People & Culture bei BEAT81.

BEAT81 ist ein Fitnessunternehmen aus Berlin mit High-Intensity-Workouts und Studios in ganz Deutschland.

Sonja und ihr Team holen jede Woche mehr als 15 neue freiberufliche Trainerinnen und Trainer an Bord, verteilt auf alle Standorte. Das sind viele neue Menschen – und für das Team hieß das jede Menge Wiederholung: Verträge rausschicken, Zugänge einrichten, immer wieder, Studio für Studio. Deshalb hat Sonja das Onboarding direkt in Leapsome automatisiert, der HR-Software von BEAT81.

Sonja Grabner
„Durch die Workflows in Leapsome sparen wir bestimmt mindestens zehn Stunden im Monat.“

Sonjas Geschichte

Transkript lesen

One tool for HRIS, feedback and reviews

"Because we already had Leapsome in place for feedback and development talks, we decided to, instead of launching a third or fourth tool, move our HRIS to Leapsome as well. And now we have that in one tool. Having feedback and the HRIS part connected allows us to automate certain kickoffs. So for example, now that Leapsome basically knows when this person joined and has their contract information in the HRIS part, the review part knows when to set up a new cycle."

Migration and time saved

"The data migration itself was only around three days, so that was actually super quick. It's probably a minimum of 10 hours a month that we save due to having those workflows set up."

Advice to other leaders

"I would tell other leaders to not be scared of it. It was easier than I thought."

  1. Baut den Ablauf einmal pro Rolle

    Im Onboarding-Prozess könnt ihr Checklisten, Aufgaben und Lernmodule kombinieren. Das Ganze legt ihr einmal pro Rolle oder Abteilung an, statt für jede Einstellung von vorn zu beginnen. Bei Sonja bekommen ein neuer Coach und eine neue Person in der Lohnabrechnung ein wirklich unterschiedliches Onboarding – nicht dasselbe Standardformular.

  2. Lasst das System die Aufgaben verteilen

    Die einzelnen Schritte und Aufgaben beim Onboarding gehen automatisch an die richtige Abteilung, etwa an Führungskraft, IT oder HR. Erinnerungen sorgen dafür, dass alles im Zeitplan bleibt. Früher musste man dafür in Slack jemandem hinterherlaufen.

  3. Fangt vor dem ersten Tag an

    Im Preboarding bekommen neue Mitarbeitende schon vor dem Start Willkommensnachrichten, Dokumente und Infos zur Rolle. So kommen sie gut vorbereitet an, statt am ersten Tag Papierkram auszufüllen.

  4. Prüft, ob es funktioniert

    Onboarding-Umfragen zeigen, wie gut jeder Ablauf ankommt. So habt ihr nach drei Monaten echte Daten und Feedback statt nur ein Bauchgefühl. Damit könnt ihr das Onboarding gezielt verbessern.

So geht’s mit Leapsome

Beschreibt den Prozess. Leapsome erledigt den Rest.

Sonja hat die Onboarding-Abläufe von BEAT81 Schritt für Schritt eingerichtet. Diese Vorarbeit übernimmt jetzt die KI in Leapsome. Ein Satz genügt:

„Erstelle mir einen Prozess fürs Onboarding eines Coaches. Vertrag muss vor dem ersten Tag raus, Studio-Einführung in Woche eins planen, Feedbackgespräch nach 30 Tagen in den Kalender packen.“

Der Assistent legt Schritte, Zuständigkeiten, Erinnerungen und Freigaben fest. Die Aufgaben könnt ihr dann auf einer Zeitleiste bearbeiten. Der Workflow läuft erst, wenn ihr ihn aktiviert. Dann aber landet jede Aufgabe automatisch bei der richtigen Person – ohne Nachfragen.

10+ Std.

mehr Zeit pro Monat, seit das Onboarding auf Leapsome automatisiert läuft – Sonja Grabner, Leiterin People & Culture, BEAT81

Chapter 2

People Analytics

From “something’s off” to “here’s the fix”

43%of HR leaders go on gut feel when asked about their share of top performers
40%could answer with real numbers

Source: live audience poll, Leapsome AI Live Build session, September 2026

Your CEO has questions in a leadership meeting. Is engineering a bigger flight risk than it was last year? What share of the company can we count as high performers? Which of our global offices is driving the best business outcomes? All three are answerable. You have dashboards set up for exactly this.

The hard part comes next. Which specific engineers are a flight risk, and what’s the signal? How many of those top performers sit in Berlin, and how many in New York? The office that’s performing best, why is that? Is it the infrastructure, the setup, or the talent pool?

Every answer opens another question, and this is where you get stuck in a wormhole of new reports. Until recently it meant pulling in an analyst, or whoever in the business could help you untangle the ball of string.

Jessica Zwaan
“I’ve had my CFO or my CEO come to me and say, I need to understand this very specific cut of information, or ask me a very strategic question that I would then have to go away and do a pretty large analysis to figure out how to answer. And more and more I’m able to just do it live in a session now.”

That’s what AI has changed. You can vibe-code almost any dashboard you want, as long as the data underneath it is in order, and ask your questions in plain language instead of translating them into something technical first.

HR initiatives get cut when they arrive as a conviction with nothing underneath. Show which three teams are affected, what it correlates with, and how you compare to companies your size, and you’re arguing on the same footing as finance.

In this chapter, three HR leaders show you what they built: a culture diagnostic that ranks which problem to fix first, a talent density dashboard that flags where it’s slipping, and a peer review dashboard that caught a workload imbalance nobody knew was there. Each one is written as a step-by-step guide, so you can follow along and build your own version.

1. Answer the talent density question before your CEO asks you about it

Meet Jessie, VP of People Strategy and Operations at Leapsome.

Jessie runs the People side of the business at Leapsome and works alongside the product team on the platform itself.

Talent density isn’t new. Netflix made the case back in 2009, in a culture deck arguing that a small team of exceptional people outperforms a large team of good ones. The phrase itself came later, through Reed Hastings’ writing, but the idea has been around for well over a decade.

AI brought it back into the spotlight, because it changed the math. When everyone on your team is working with tools that extend what they can get done, the relationship between headcount and output shifts, and who you have starts to matter more than how many.

Jessica Zwaan
“This is one of the first times in my career where CEOs and boards are really pushing people questions to their people leaders, sometimes before people teams have had a chance to develop their own philosophy around it. In the past, the people team pushed those initiatives and the board would say, okay, let’s think about it. Now it’s coming the other way.”

It’s top of mind for leadership right now. Talent density used to be an HR term. Increasingly it’s something founders, CEOs, and boards ask about directly, and a gut-feel answer won’t survive the room. You need the number, broken down by team, with the risks attached.

  1. Decide which metrics define talent density at your company

    This looks different at every company. Two companies can both say they track talent density and be measuring completely different things. Jessie frames it as output relative to headcount, measured as ARR per employee, shipping cadence, or coverage across critical roles. ARR per employee is the one that tends to land hardest with a board. Her dashboard measures it by team using three fields the HRIS already holds: review score, goal achievement, and engagement. Pick three or four you can get reliably and write the definition down before you build anything.

  2. Build the view using the metrics you’ve decided on

    Use whatever your setup allows: your HRIS, an MCP connection into Claude, or a spreadsheet export. Write the prompt the way you’d brief an analyst. Give it your definition from step one, say you want it measured by team, and ask for the distribution across the company. In Leapsome this is a Vibe Dashboard.

  3. Split it four ways

    Ask for all four cuts in the same view, because each one answers a different question.

    • By team, as a heat map. Ranks your teams against each other and shows where the spread is widest.
    • By tenure band. Tells you whether density drops off after a certain point, which is usually a hiring bar question or an onboarding one.
    • By location. Worth doing if you’re multi-site or hybrid, where one office can drift without anyone noticing.
    • Against a distribution curve for the whole company. The company-wide number is what your board asks for. The curve tells you whether that number comes from a strong middle or from a few outliers carrying everyone else.
  4. Add a risk layer with a second prompt

    Open modify with AI and ask for the patterns that would put your definition under threat. Jessie asked for the first two below. The rest are worth adding.

    Prompt
    Add a risk view to this dashboard. Flag:
    - People whose review scores have declined over the last two cycles while their goal load has stayed the same
    - People who have missed their goals for two consecutive quarters on a team that hasn't grown
    - Top-rated people with no promotion or level change in the last twelve months
    - Teams where the highest performers score lowest on engagement
    - Roles where only one person could do the job

The first prompt gives you the number your CEO asked for. The second gives you a list of names and teams with a reason attached to each one. Jessie got from one to the other with a single extra instruction.

How to do this in Leapsome

All your people data, already connected

Leapsome holds HRIS records, performance reviews, engagement surveys, goals, learning, and compensation in one place. A talent density question spans at least three of those, so answering one doesn’t start with three exports.

Two things matter for this build. Resilience Signals reads HRIS and survey data together and surfaces team-level patterns on your home dashboard. Turnover Prediction Analysis identifies retention risk and the factors driving it, which does a version of the risk layer above with a trained model behind it.

2. Build a culture diagnostic that tells you what to fix first

Meet Adam, co-founder of Open Org.

Open Org is a two-person company building tools and shared resources for startup and scale-up People teams.

Culture is the hardest thing in HR to point at. You can feel that something is off and still not be able to name it. Is it one manager, the way decisions get made, the fact that nobody knows what good looks like at the next level? Everything looks urgent and nothing looks biggest, so you end up putting out whichever fire is loudest that week.

Adam Horne
“They normally know that there’s something wrong. They have the data to show where it’s wrong. But then they hit a couple of hurdles. They don’t know what to prioritize, and they don’t always know what the best solution is. We’ve got multiple ways we could fix this. I don’t really know where to start. What does good look like?”

The problem compounds because you’re standing inside it. You’re part of the culture you’re being asked to assess, which makes it hard to separate a real pattern from your own bad month.

A culture diagnostic gets you far enough out to see the forest for the trees. Built well, it shows you where the problems are and ranks them, so you come away with a prioritized list of things to do.

  1. Decide how you’ll measure culture

    For example, Adam’s diagnostic rates the following: communication, meeting effectiveness, hiring process, onboarding, decision-making process, and offboarding and firing. We suggest starting with these six as a culture baseline, then adding others in if you’d like. Eight areas is probably a good maximum, or survey completion rates will go right down.

  2. Create a survey that asks people to rate these on a scale

    Each area gets a score from one to five and one sentence explaining it. Make sure you answer it yourself too, and don’t look at the team’s scores first in case it biases your answer.

    Pick where you run it with the dashboard in mind, since it needs these scores sitting alongside your other people data:

    • A survey in your HRIS, like Leapsome’s, keeps results next to engagement, retention, and exit data with nothing to export
    • Open Org’s culture heatmap is already built and arrives with the benchmark attached
    • A standalone form works if you want to run it this week and handle the export later

    Decide on anonymity before you send it. People score offboarding and firing differently when their name is on the answer.

  3. Add your existing people data and your company goals

    Bring in engagement and pulse scores, exit reasons, retention by team, and average tenure. If you ran the survey in your HRIS, most of this already sits beside it.

    Then add your OKRs. They let you rank problems by what each one is costing the business this quarter, which is the ranking leadership acts on.

  4. Build the view

    In Leapsome, describe what you want in a vibe-coded dashboard. Outside it, Claude or Lovable will do the same job against a spreadsheet of your results. Either way, give it something like this:

    Prompt
    Build a culture diagnostic dashboard from the data attached. Show me:
    - A heatmap scoring each culture area, with my score and the team average side by side
    - The areas with the widest gap between my score and the team average
    - Every weak area cross-referenced against engagement scores, exit reasons, and retention for the teams affected
    - A ranked list of the top five problems, ordered by their impact on the company goals below
    - One line for each explaining why it ranks where it does
  5. Benchmark before you act

    A score of three out of five means nothing until you know what three looks like elsewhere. Get a comparison for your weakest two or three areas, whether from an industry report, a peer network, or a crowdsourced set like Open Org’s, which covers 19 people metrics from around 700 startups and scale-ups. Then let it move your ranking. A low score that’s normal at your size can wait. An average one your peers have already fixed usually can’t.

Run this once and you have a snapshot. Run it each quarter and you have a trend, which is the version that lets you show a leadership team that something is moving. Adam’s own advice for anyone staring at a blank page: open Claude, describe what you want, and ask it to walk you through the steps.

How to do this in Leapsome

Describe the dashboard. Leapsome builds it.

In Leapsome, coming up with a new dashboard is as simple as describing in your own words the view you’d like to see.

Go to Analytics > Dashboards. Start from scratch with New Dashboard > Vibe dashboard, which opens blank, or use Create from vibe template to build on one of our community templates from customers and other HR leaders. Name it, set visibility, then describe what you want in the chat panel. Follow-ups edit the dashboard instead of starting over.

Because Leapsome covers the entire employee lifecycle, from hiring through to offboarding, you have a complete picture of your people data. Use it as your data layer, ask for the view you want, and it’s all in one place. You won’t need to splice together any spreadsheets, because it’s all living in one HRIS.

3. Create a dashboard that stops the same few people reviewing everyone

Meet Paulina, People & Culture Manager at Kayzen.

Kayzen is a Berlin software company that helps mobile marketing teams run programmatic advertising in-house.

At Kayzen, 360-degree feedback runs year-round, and employees nominate the peers who review them. What the People team noticed was that certain well-liked, well-connected colleagues were being chosen over and over again. That created a bottleneck in capacity, and a question about bias in who was doing the reviewing. The most-nominated people were writing six to eight peer reviews in a single cycle while others wrote none.

Paulina Sophie Augustin
“With AI dashboards, we build views on our platform data for what we need. Our peer review overview shows who was nominated as a peer and whether reviews were completed. Managers can see where their team stands. Our management team, with many indirect reports, has that view across their whole organization, with all the data and reviews in one place.”

The second gap sat next to it. Peer feedback that never arrived, and reflection meetings that never happened, tended to surface after the cycle had closed, when there was nothing left to do about it.

Kayzen felt both of these harder than most companies, because reviews were tied to each person’s hire date. There was no review season and no single moment when everyone was at the same stage, so it wasn’t something they could spot all at once.

  1. Count nominations across the whole organization

    One person’s nominations look fine. Four reasonable names, nobody doing anything wrong. Run the count across the whole company and the pattern shows up immediately: the same handful of names appearing on list after list.

  2. Set a cap and let the system enforce it

    Decide how many peer reviews one person can write properly in a cycle. Kayzen’s most-nominated people were carrying six to eight. Set that number as a limit in your platform so anyone at the cap stops appearing as an available reviewer while nominations are still open. Enforcing it in the software means nobody has to police it by hand.

  3. Capture declines with a reason attached

    When someone turns down a peer review request, record why. A decline with no reason is a hole you find at the end. A decline with a reason is something your team can act on the same week, by finding a replacement or by following up with the person directly.

  4. Build the view

    In Leapsome, describe the dashboard you want and let it build against your live review data. Something like this:

    Prompt
    Build a peer review dashboard from our review data. Show me:
    - How many times each person has been nominated as a peer reviewer this cycle, ranked highest to lowest
    - Anyone nominated more than [your cap] times, flagged while nominations are still open
    - Which teams nominate outside their own team and which only nominate internally
    - Every peer review request that was declined, with the reason given
    - Which requested reviews are still outstanding, and how long they have been open
  5. Extend it from nominations to completion

    The same view answers the harder question: did the feedback arrive, and did the conversation happen. Kayzen gives managers the dashboard for their own teams and the management team the version across the whole organization. The next build is a quarterly dashboard per manager covering reviews completed, development goals in use, peer nominations, how often praise and feedback get exchanged, and which raises and promotions went through, so every quarterly conversation starts with the picture already in front of them.

A process tied to hire dates never closes, and nobody is ever at the same stage as anyone else. That’s what made the imbalance invisible for as long as it was, and it’s why the dashboard found something a review season would have hidden.

Coming soon

Chapter 3: Future-Proof Recruiting

Featuring Jonathan Durnford-Smith (Synthesia)

Jonathan Durnford-Smith
Coming soon

Chapter 2: Predictive People Insights

Featuring Adam Horne (Open Org), Jessica Zwaan (Leapsome) & Paulina Sophie Augustin (Kayzen)

Adam HorneJessica ZwaanPaulina Sophie Augustin
Demnächst

Kapitel 2: People Analytics

Mit Adam Horne (Open Org), Jessica Zwaan (Leapsome) und Paulina Sophie Augustin (Kayzen)

Adam HorneJessica ZwaanPaulina Sophie Augustin

Who's behind this

About the contributors

The HR leaders featured in this playbook, in their own words and their own builds.

Jessica Zwaan

Jessica Zwaan

VP People Strategy and Operations, Leapsome

Jessica Zwaan is VP People Strategy and Operations at Leapsome. She's spent her career in senior people and talent roles, including COO at Talentful and Whereby, and is the author of two books on people strategy, Built for People and Purpose and Work.

Emily Mabie

Emily Mabie

AI Innovation Lead for People, Zapier

Emily Mabie is AI Innovation Lead for People at Zapier, where she was the company's first AI automation engineer hired specifically for HR. She builds AI-powered automations and agents for Zapier's own HR team, including the helpdesk build featured in this chapter.

Melanie Naranjo

Melanie Naranjo

Chief People Officer, Ethena

Melanie Naranjo is Chief People Officer at Ethena, where she's worked since 2021. Before Ethena, she led People & Culture at Insider Inc., and she writes and speaks regularly on HR leadership, including for TroopHR and the Future of HR podcast.

Sonja Grabner

Sonja Grabner

People & Culture Lead, BEAT81

Sonja Grabner is People & Culture Lead at BEAT81, the Berlin-based fitness company behind its high-intensity training studios across Germany. She's worked in People & Culture at BEAT81 since 2022, and is a certified mediator through the Institut Berlin Mediation.

FAQ

Agentic HR, answered

What is Agentic HR?

Agentic HR means handing the repeatable parts of HR work, like policy questions, document chasing, and workflows that just need to run, to AI agents, so HR teams can focus on judgment, relationships, and the hard conversations: the work that actually needs a person. Agents handle the busywork. People handle everything else.

How is Agentic HR different from automation?

Automation moves data from one app to another on fixed rules a person sets up ahead of time. Agentic AI goes a step further: you give it a goal, and it works out which steps and tools get you there. Most of what gets called "agentic" in HR today sits somewhere on that spectrum, and the builds in this playbook show both ends of it.

Do you need to be technical to build these?

No. None of the builds in this playbook require code. Every one comes with exact, step-by-step instructions, and the HR leaders who built them did it without a technical background.

What's an example of Agentic HR in practice?

A Slack bot that answers policy questions directly from your HR documentation instead of routing every question to a person. A custom AI reviewer that won't let a manager submit vague performance feedback. An onboarding workflow that assigns tasks, sends reminders, and tracks progress with no manual setup. All three are covered step by step in this playbook.

What's the Leapsome Agentic HR Accelerator?

A six-month guided program led by Jessica Zwaan, VP People Strategy and Operations at Leapsome. Over 12 weeks, a cohort builds agentic workflows and their own people analytics dashboards, plus one more use case suited to their business, on Leapsome's full platform.

Do you need to switch to Leapsome to use the ideas in this playbook?

No. Every build here works with tools you already use: Slack, ChatGPT, Zapier, whatever your HR team runs on. Leapsome has AI Agents built directly into the platform too (see the "How to do this in Leapsome" sections throughout), but nothing here requires switching platforms first.

Unsere Expert:innen

Die Köpfe hinter den Praxisbeispielen

Die HR-Profis aus diesem Playbook, mit ihren eigenen Worten und Lösungen.

Jessica Zwaan

Jessica Zwaan

VP Personalstrategie und -organisation, Leapsome

Jessica Zwaan ist VP Personalstrategie und -organisation bei Leapsome. In ihrer Karriere hatte sie leitende HR- und People-Positionen, unter anderem als COO bei Talentful und Whereby. Außerdem hat sie zwei Bücher über HR-Strategie geschrieben, „Built for People“ und „Purpose and Work“.

Emily Mabie

Emily Mabie

Leiterin KI-Innovation für HR, Zapier

Emily Mabie leitet bei Zapier die KI-Innovation im HR. Sie war dort die erste Expertin für KI-Automatisierung, die gezielt für HR eingestellt wurde. Für das eigene HR-Team baut sie KI-gestützte Abläufe und Assistenten, darunter den Helpdesk aus diesem Kapitel.

Melanie Naranjo

Melanie Naranjo

Personalchefin, Ethena

Melanie Naranjo ist seit 2021 Personalchefin bei Ethena. Davor leitete sie People & Culture bei Insider Inc. Sie schreibt und spricht regelmäßig über HR-Führung, unter anderem für TroopHR und den Podcast „Future of HR“.

Sonja Grabner

Sonja Grabner

Leiterin People & Culture, BEAT81

Sonja Grabner leitet People & Culture bei BEAT81, dem Berliner Fitnessunternehmen mit High-Intensity-Studios in ganz Deutschland. Sie ist seit 2022 bei BEAT81 und zertifizierte Mediatorin (Institut Berlin Mediation).

FAQ

Eure Fragen zu Agentic HR

Was ist Agentic HR?

Bei Agentic HR beantwortet die KI Fragen zu Urlaub oder Spesen, fordert fehlende Unterlagen an und wickelt Prozesse ab, die immer gleich laufen. So kann sich das HR-Team auf Entscheidungen, Beziehungen und schwierige Gespräche konzentrieren. Also auf die Arbeit, für die es wirklich Menschen braucht. Die KI erledigt die Fleißarbeit, alles andere bleibt bei euch.

Was unterscheidet Agentic HR von Automatisierung?

Automatisierung schiebt Daten nach festen Regeln von einer App in die nächste. Diese Regeln hat vorher jemand eingerichtet. Agentische KI geht einen Schritt weiter. Ihr gebt ein Ziel vor, und die KI findet selbst heraus, mit welchen Schritten und Tools es sich erreichen lässt. Das meiste, was im HR heute „agentisch“ heißt, liegt irgendwo dazwischen. Die Beispiele in diesem Playbook zeigen beide Extreme.

Brauchen wir technisches Know-how, um so etwas zu bauen?

Nein. Keine der Lösungen in diesem Playbook braucht Code. Zu jeder gibt es eine genaue Schritt-für-Schritt-Anleitung, und die HR-Profis dahinter haben sie ohne technischen Hintergrund gebaut.

Wie sieht Agentic HR im Alltag aus?

Ein Slack-Bot, der Fragen zu Richtlinien direkt aus eurer HR-Dokumentation beantwortet, statt sie an einen Menschen weiterzugeben. Ein KI-Assistent, der bei vagem Feedback von Führungskräften nachhakt, bevor es eingereicht wird. Ein Onboarding-Prozess, der Aufgaben verteilt, Erinnerungen schickt und den Fortschritt verfolgt, ohne manuelles Set-up. Alle drei erklären wir in diesem Playbook Schritt für Schritt.

Was ist der Agentic HR Accelerator von Leapsome?

Ein Programm über sechs Monate, geleitet von Jessica Zwaan, VP Personalstrategie und -organisation bei Leapsome. In zwölf Wochen baut ihr automatisierte Workflows und eigene Dashboards für Personaldaten. Dazu kommt ein weiterer Anwendungsfall, der zum eigenen Unternehmen passt. Alles läuft auf der HR-Plattform von Leapsome.

Müssen wir zu Leapsome wechseln, um die Ideen aus dem Playbook zu nutzen?

Nein. Jede Lösung funktioniert mit Tools, die ihr schon nutzt, etwa Slack, ChatGPT, Zapier oder was bei eurem HR-Team im Einsatz ist. In Leapsome ist die KI zusätzlich direkt eingebaut, siehe die Abschnitte „So geht’s mit Leapsome“. Ein Wechsel ist aber keine Voraussetzung.

Dürfen wir KI im HR überhaupt nutzen?

Ja, wenn ihr ein paar Regeln beachtet. In Europa setzen die DSGVO und der EU AI Act den Rahmen: Für Personaldaten braucht es eine Rechtsgrundlage, Mitarbeitende sollten wissen, wo KI im Einsatz ist, und bei Entscheidungen über Mitarbeitende hat immer ein Mensch das letzte Wort. Gibt es bei euch einen Betriebsrat, holt ihn früh ins Boot. Wie Leapsome das umsetzt, lest ihr auf unserer Seite zu KI-Sicherheit. Und alles Weitere klären wir im Webinar „Ist KI im HR jetzt verboten?“.

KI-sicher einsetzen

Darf KI an Personaldaten? Ja, mit klaren Regeln.

Wer mit Personaldaten arbeitet, braucht Vertrauen vom Team, von der Geschäftsführung und vom Betriebsrat. Deshalb gelten bei Leapsome vier Grundsätze.

Ihr entscheidet.

Die KI macht Vorschläge und Entwürfe, ohne eure Freigabe passiert nichts.

Eure Daten bleiben bei euch.

Gehostet in Deutschland, kein Training mit euren Informationen.

Geprüfte Sicherheit.

DSGVO-konform, ISO 27001, SOC 2 Type II, bereit für den EU AI Act.

Klare Rechte.

Alle sehen nur, was sie sehen dürfen.

The Agentic HR Accelerator

A six-month program for HR teams putting AI agents to work

Everything in this playbook is free. The accelerator is the guided version: Jessica Zwaan leads a cohort through 12 weeks of content, building agentic workflows and your own people analytics dashboards, plus one more use case that fits your business. It runs on Leapsome HRIS, with a CSM team managing onboarding and migration alongside you.

2,000+companies already running on Leapsome
6months, January to June 2027
12weeks of guided cohort content
3agentic HR use cases, live in Leapsome by the end of your cohort

Three phases: prep with your cohort and CSM team in January, 12 weeks of guided content from February, then a managed Slack community from May. Certification lands the week of June 28, 2027. Per month, it takes about an hour of recorded video, a two-hour workshop, and 30 minutes of CSM office hours, plus two optional 1-hour AMAs a month.

ISO 27001SOC 2GDPREU AI Act ready

Der Agentic HR Accelerator

Bereit für KI im HR? Wir begleiten euch sechs Monate.

Alles in diesem Playbook ist allgemein gehalten und kostenlos. Im Accelerator geht es um euer Unternehmen. Jessica Zwaan führt eure Gruppe durch zwölf Wochen mit Videos und Workshops. Ihr baut automatisierte Workflows und eigene Dashboards für Personaldaten. Dazu kommt ein Anwendungsfall, der genau zu eurem Geschäft passt. Das Programm läuft auf Leapsome HRIS. Unsere Kundenbetreuung kümmert sich mit euch um Onboarding und Datenübernahme.

2.000+Unternehmen arbeiten schon mit Leapsome
6Monate, Januar bis Juni 2027
12Wochen Programm in der Gruppe
3Agentic-HR-Anwendungsfälle, live auf Leapsome bis zum Programmende

Drei Phasen. Im Januar bereitet ihr euch mit eurer Gruppe und der Kundenbetreuung vor. Ab Februar folgen zwölf Wochen Programm, ab Mai eine betreute Slack-Community. Die Zertifizierung gibt es in der Woche ab dem 28. Juni 2027. Pro Monat rechnet ihr mit etwa einer Stunde Video, einem zweistündigen Workshop und 30 Minuten Sprechstunde. Dazu kommen zwei freiwillige Fragerunden à eine Stunde.

ISO 27001SOC 2DSGVOBereit für den EU AI Act