Zkušení tvůrci.
Rychlejší díky AI.

We’re not saying we fired our Head of Finance, HR, or Admin. But we did give them AI-powered assistants that take care of repetitive work, catch mistakes before they happen, and keep everything moving behind the scenes.

This is how we actually use AI agents at Cleevio. No buzzwords, just real stuff that saves time and makes us better at what we do.

AI Head of Finance

Goal: Automate financial workflows, improve accuracy, and give us better control over company spending.

1. Payrolls Agent

We built a Payrolls Agent that makes sure everyone gets paid correctly and on time. It checks if contracts are valid, compares worklogs to recorded hours, keeps track of vacation balances, and categorizes expenses per project.

It doesn’t work in isolation, it talks to:

• Contracts Agent (HR) to confirm someone is eligible for payroll.
• Worklogs Agent (Admin) to validate hours worked.

The benefit: Accurate, on-time payroll with fewer errors and less back-and-forth between teams.

2. Invoices Agent

Our Invoices Agent handles both incoming and outgoing invoices. It issues them, tracks due dates, and sends alerts when something needs our attention. It also matches invoices to bank transactions and preps everything for our accountant.

It syncs with:

• Projects Agent (Admin) to assign costs to the right project.
• Reporting Agent to keep the books clean.

The benefit: Fewer missed invoices or mismatched payments as everything is organized and ready for accounting.

3. Reporting Agent

This one’s all about insights. The Reporting Agent generates dashboards, tracks recurring expenses like SaaS tools, and flags overspending.

It pulls data from:

• Payrolls and Invoices Agents
• And gives Admin a clear view of where budgets stand

The benefit: Fast, accurate financial overviews and proactive alerts when things start going off track.

‍

AI Head of HR

Goal: Automate people-related processes and make sure no one gets forgotten in a spreadsheet.

1. Contracts Agent

The Contracts Agent helps us stay on top of employee agreements. It alerts us when contracts are about to expire, recommends renewals, and checks if all the conditions are still valid.

It collaborates with:

• Payrolls Agent (Finance) to verify salary eligibility.

The benefit: No missed contract renewals or expired agreements slipping through unnoticed.

2. People Agent

This one supports the full employee journey from onboarding to offboarding. It walks new hires through checklists, runs performance review cycles, and handles exits smoothly.

It also uses data from:

• Worklogs Agent (Admin) to assess workload and contributions.

The benefit: A smoother employee experience with all key processes automated and on time.

AI Head of Admin

Goal: Keep approvals, budgets, and worklogs flowing smoothly without micromanagement.

1. Budgeting Agent

This agent approves expenses, keeps an eye on team budgets, and makes sure we don’t overspend.

It partners with:

• Invoices Agent (Finance) to assign expenses to the correct projects.

The benefit: More control over budgets and less delay in expense approvals.

2. Worklogs Agent

This one checks whether submitted worklogs are complete and correct. It tracks team statistics (like time in meetings), and ensures our tracking rules are followed.

It syncs with:

• Payrolls Agent (Finance) to confirm logged hours
• People Agent (HR) to help with performance reviews

The benefit: Reliable time tracking without micromanagement and better data for performance reviews.

‍

Why This Matters

This isn’t just about automation. It’s about giving our team more time to focus on high-impact work, strategy, people and relationships. The AI agents don’t replace decision-making; they make it easier and more informed.

We didn’t build a fleet of AI agents overnight. We started small, tested use cases, and connected tools step by step. The result? A system that supports our team without overwhelming it.

If you're curious about how we built them—or want to try something similar in your own company—let’s talk.

‍

Your app is growing. That’s the good news.
The bad news? So are the reviews, tickets, and unexpected bugs no one saw coming.

We needed a fast, affordable way to handle it all, so our team could focus on what truly matters: high-impact work.

29.4 hours later, we had a solution.

We call it UpRate — and now, anyone can use it.

What is UpRate?

UpRate is your AI support teammate.

It handles repetitive tasks that kill your team’s flow — like replying to store reviews and searching for the right info in your knowledge base.

No fluff. Just actual time saved.

How we built it (and what it actually does)

Two people on our team were constantly switching context to reply to app store reviews, dig through sheets for answers, and forward support requests to the right teammate. It wasn’t a full-time job — but it was eating up way too much of their time.

So we gave ourselves a challenge:
Can we automate this in a way that actually helps our team — and ship it fast?

Here’s how we approached it:

• Code: Jumped between Cursor and Claude’s code interpreter
• UI: Used v0.dev to generate more complex components
• Landing page: Sketched in Lovable, polished in Cursor
• Testing: Wrote proper tests — over 80% coverage
• LLM credits used: $32
• Dev time: 29.4 hours total

And yes — it works.
‍

The tool now:

• Replies to all app store reviews instantly, using your tone and policies
• Pulls from a shared, limitless knowledge base — even across multiple apps
• Understands and translates reviews in foreign languages
• Routes support issues to the right person when needed

We didn't over-engineer it. We built what we needed — fast.
Now that it’s saving us hours each week, we’re opening it up to everyone else too.

Why we’re sharing it now

• Less time on support = more time building.
• Happier users = better ratings.
• No more burnout over repetitive tasks.

Real talk:

We didn’t build UpRate because AI is cool.
We built it because support was dragging down our team’s productivity — and our ability to build.

Now, it’s doing the heavy lifting.
Our users get faster replies.
Our PMs get useful insights.
And our team gets to focus on what actually matters: building great products.

‍

If your team is still manually handling app support — stop.
Let UpRate take care of it. You’ve got better things to do.

Want to see it in action? Get in touch or book a demo.

As software development complexity is increasing, efficient and reliable testing are critical. Enter Maestro, a user-friendly development testing tool that streamlines testing processes, speeds up release cycles and enhances software quality.

This article explores our journey with Maestro, highlighting challenges, solutions, and benefits as we strive towards enhanced testing and continuous improvement.

Our main goal? To use testing time efficiently, moving repetitive tasks to automation, and freeing up engineering time for activities such as critical and manual testing of a new feature before they are automated or preparing automation for a new feature.

How do we do it?

We use Maestro to automate testing scenarios and flows in our mobile applications - this helps us bring on-demand test results faster, gives us a quick retest option, and saves time.

Even though initial setup and writing tests require time investment, while automation tests run, QA engineers can focus on tasks like manual testing of new features or preparing automation for new features.

Tests are written in YAML files in a semi-codeless manner, using commands like "tapOn" and "scroll". Tests can run on hardware devices or emulators/simulators, making them ideal for end-to-end smoke tests or regression tests during fresh releases.

‍

Time Savings with Automation

Example Scenario:

A hypothetical mobile app with login, logout, dashboard, 2 main features, and a user profile.

Manual Testing:

• Complete smoke test: 1 hour per device
• Development period: 6 months (18 sprints, 4 releases per sprint)
• 3 devices (current and 2 older OS versions)

Approach 1: Manual Testing (First Month)

• 3 sprints, 4 releases/sprint, 1 hour/release, 3 devices/release
• Total: 36 hours/month on manual smoke testing
• Remaining: 134 hours for other testing activities

Approach 2: Automated Testing (First Month)

• Initial setup: 4 hours, fixing: 3 hours
• 3 sprints, 4 releases/sprint, 45 minutes/release, 3 devices/release
• Automated testing time utilized for other activities
• Total: 7 hours (setup + fixing)
• Remaining: 163 hours for other testing activities
• Time saved: 19 hours (29 hours without buffer)

Simulating Growth (Sixth Month, Coefficient: 1.2 per month)

• Approach 1: Manual Testing
  • Total: 269.2 hours/month on manual smoke testing
  • Negative balance: -89.2 hours (not feasible)
• Approach 2: Automated Testing
  • Initial setup: 28.8 hours, fixing: 21.6 hours, writing: 28.8 hours
  • Total: 194.4 hours (automated testing time utilized for other activities)
  • Remaining: 119.6 hours for other testing activities
  • Time saved: 208.8 hours

Summary:

• First month: 19 hours saved with Maestro
• Sixth month: 208.8 hours saved with Maestro
• Automation maintains 100% test coverage and allows QA engineers to focus on critical tasks, ensuring product quality.

Maestro represents a solution to the often complex issue of mobile application automation testing, offering organizations the tools and capabilities needed to elevate their testing practices to new heights and deliver exceptional software products that exceed customer expectations.

TL;DR

As applications grow more complex, automation helps maintain comprehensive test coverage. Automation frees QA engineers to focus on tasks requiring human insight, ensuring quality doesn't suffer even with tight deadlines.

‍