Aneta Kahleová

AI Tech Lead · Contractor

I love helping people move forward.

Aneta Kahleová

I build production chatbots and autonomous AI agents for teams that need more than a demo - context engineering, end to end.

Why chatbots

The answer is already there. It’s just hard to find.

A production chatbot isn’t a widget on your homepage - it’s an assistant that knows your material, cites its sources, and gives people their time back. Here’s what that looked like across 8 million articles and 60,000 teachers.

Teachers were spending more time searching for materials than preparing lessons. ScioBot changed that - 8 million articles, one question away.

ScioBot - the AI core I co-developed for Czech teachers.

8M

articles

60,000

teachers

3,000

schools

AI Awards

2024

What chatbots solve, and how I build them

What I do

Need a production chatbot?

I design, build, and deploy custom AI assistants - grounded in your data, with evals, guardrails, and a path to production. Not a slide deck. A bot that runs.

Custom AI agents

Workflow bots and customer-facing assistants that plan, route, and execute - with human gates where it matters.

Enterprise RAG

Hybrid retrieval at scale. Chunking, citation, judge loops - so answers stay honest in production.

Data extraction

Playwright pipelines and clean hand-offs into your knowledge base - the layer your bot actually needs.

Live demo

See what a production assistant feels like.

Ask about custom chatbots, enterprise RAG, or what it would take to ship one for your team - then compare it to the slide deck you have today.

Open the demo

Latest writing

Eval as an Input, Not a Dashboard: Building Self-Healing LLM Systems

Most teams treat evaluation as a scoreboard - a number you glance at and feel good or bad about. The frontier idea is to wire the eval back into the system as an input that rewrites it: traces go to independent judges, fixes get proposed automatically, and one human approves. It's AI all the way down, with a single gate that isn't.

Maximum Recall: Why Your Retriever Should Cast Three Nets, Not One

You compressed your knowledge into clean indexes. Now comes the moment everything hinges on: given a question, can the bot actually find the handful of tables it needs among a thousand? Miss the right one and nothing downstream can save you - so at the retrieval step, recall beats precision.

All insights

Testimonials

What colleagues say about me

Reviews and recommendations from people I’ve had the pleasure of working with.

Aneta’s progress over the past year has been incredible. On a personal level, she leads people well on the projects she’s entrusted with and mentors newcomers - and I appreciate that she can objectively evaluate a newcomer’s quality and isn’t afraid to say they’re not good enough, which not everyone can do. Professionally she keeps moving forward too - actively seeking out new information and going to seminars on her own - and that progress is visible in the Agentic Search she implemented into our chatbots, which I consider a top achievement that pushes our chatbots ahead of the competition. Let’s not just praise ourselves - we didn’t quite nail the timing and pull-request reviews on one of the projects. But making mistakes is completely normal, we all make them, and what matters is learning from them and coming back stronger. She has enormous talent that just needs nurturing, and a good inner compass. A great future ahead of her. It’s a great honor to work with her.
Jiří SzewieczekEngineering Manager · OKlab (OKsystem)
I’ve been working with Aneta for nearly a year, primarily on chatbot projects and related technologies. From the start she came across as someone who knows exactly what she’s doing - she can get her bearings quickly even in a complex problem and find a solution that’s technically solid, thoughtful, and sustainable long-term. What I value most is her thoroughness and high quality bar: she won’t settle for something that merely works. She looks for a way to do it right, efficiently, and with the project’s future development in mind. Her implementations are often a reference point I build from - and I regularly learn from them, because they combine deep expertise with practical experience and a genuine understanding of software development. Aneta also has a clear impact on how the whole team works. She can quickly identify the essence of a problem, separate the important tasks from the unnecessary ones, and set a clear next step. Thanks to that, work doesn’t stall in long debates but moves efficiently forward. Even in situations that would normally require extensive project changes, she’s able to propose and carry out major adjustments in a short time without compromising on quality. Collaboration with her is at the same time very pleasant and natural. She communicates openly, friendly, and without unnecessary formality, yet always to the point and professionally. She’s willing to advise, explain her perspective, and provides concrete, constructive feedback that genuinely moves you forward. Even though we don’t meet in person often due to distance, on a human level Aneta is a great partner you feel good working with - not only on work matters. I’d recommend Aneta without hesitation to any team or organization looking for a reliable expert able to take ownership, solve hard problems, and deliver at an exceptionally high level.
Matěj TeplýAI Developer · OKlab
I took Aneta on at SCIO as a junior fullstack developer with an ML focus - and within months she was handling tasks I’d normally hand to a senior. Hybrid dense-sparse retrieval over 8 million articles, the RAG optimizer, a crowdsourced-annotation processing system, GPT finetuning, and cost optimization. She’s not just technically strong; she ships, end to end, from research to commercial release. In a five-person team ScioBot reached 60,000 users and 3,000 schools, and won AI Awards 2024. She’s moved on from us now, but if I were building the team again, I’d take Aneta in a heartbeat.
Matěj ŠtáglTech Lead · SCIO (ScioBot)
I see my collaboration with Aneta as one of those where you don’t have to be afraid to ask about anything. We’ve been working together on internal company projects for nearly a year: she builds chatbots as tech lead, hands me the API, and I wire it into the frontend on our internal website. What I value most about her is her speed and willingness to respond. When something isn’t working on the chatbot or I’m missing some information, I reach out and I get an answer practically right away, along with a solution. I don’t have to wait days for someone to get to it. You can simply rely on her part of the work, so I can focus on mine in peace. I’d recommend Aneta to anyone who needs a colleague you can always count on.
Petr KoukalFrontend Developer · OKsystem

Let’s build something.

Book a free 30-minute scoping call - or email anytime.

aneta.kahleova@gmail.com