Episode 116: From IKEA to AI Agents — Peter Grimvall, Ekona AI CEO

There's a lot of discussion in the industry about it that many predicted that everything is reaching a certain plateau and we are more and more seeing incremental improvements which maybe has been the thing actually the last couple of months but on the other hand I think we have had just this week Gemini 3 is maybe too early to say but so far what we have been testing it's actually definite workshop but actually what came the other day Nano Banana 2 that one for us it's actually solved some problem.

Hi, my name is Demetri Panici and I'm a content creator, agency owner, and AI enthusiast. You're listening to the AI Agents podcast brought to you by Jotform and featuring our very own CEO and founder, Aytekin Tank. This is the show where artificial intelligence meets innovation, productivity, and the tools shaping the future of work. Enjoy the show.

Hello and welcome back to another episode of the AI Agents Podcast. In this episode, we have Peter Grimald, the founder and co-founder, I should say, of Eona. How you doing today, Peter?

Yeah, very good. Thanks for inviting me. Great to be here.

Yeah, thanks for being on the show. Really appreciate it. Just to kind of kick things off, would love to know a little bit more about how you first got into AI and what led you to founding Eona.

Actually how I got into it was almost a decade ago and it was just a coincidence. You know, I moved countries many times with work and so on, worked along in Asia and then I came back to Europe and then after some moves to Germany, Sweden, I ended up in Switzerland.

The first thing you have to do is like you have to find a place to live and then if your work is far out yeah you need to have a car. So I actually bought a Tesla in 2016 with autopilot and that actually struck me and as I'm working in supply chain I immediately thought how can this type of technology actually be applied in supply chain.

So I actually started to study a bit just beside our work at MIT on this topic and then I think halfway into the studies I realized that yeah we have many application areas at my work and as I was already leading that type of topic at IKEA at that time, I actually pitched to IKEA let's start the first AI team and focus on supply chain and they gave me actually like two headcount so I could hire two people and then we actually started to build some prediction models to predict the future sales.

This was the first task that we went on but then I also realized that actually the same year when I had my parents over for Christmas and you know when you're a teenager you're not so interested in what your parents are doing but then I actually found out that my father was teaching in machine learning like in the 80s.

Yeah, exactly. So I found it out like in the 80s. That's crazy. Yeah, I think so. 80s or 90s. Now I don't recall. So that is actually the journey and then we actually just started those use cases and I had the opportunity that I could actually implement these use cases in my own organizations I could both develop it and also benefit it from myself so I didn't have to go and look for stakeholders or customers or anything like this.

Yeah, that's how I came into AI. Then to the second part of your question, how I came into Eona was that not sure if it was a midlife crisis, but after working like 20 years in corporate I have a lot of energy and it would be interesting to try something on your own.

What I actually discovered when I ventured into to start something on my own was actually the combination between actually knowing something plus knowing a bit about AI is actually a very nice combination. So I worked 20 years in supply chain and everything from procurement to manufacturing and logistics and also design and planning etc. And then also being early on to IKEA.

So that meant that when we are actually talking to our clients and working our projects, we can actually connect very quickly and also I think we can also avoid many of the simple mistakes when you actually don't fully understand the context of why we are building something.

That's when I got a call then from my co-founder that has actually like more or less identical background but from pharma instead. We said that okay pharma supply chain and then I have also worked a bit in finance the last year so we said okay pharma supply chain and finance that makes a good mix which is also a bit like the core industries here in Switzerland where we are based also.

Okay, very cool. Nice. I think that gives us a good kind of starting point with your whole story. So, what was kind of the turning point that made you realize there was a market need for what you were doing?

I think it was actually when we started to meet clients and when you have this connection and when clients are actually ready to shake hands almost like on the first or at most like the second meeting. So you know more or less when you know when people are ready to shake hands without knowing all the details. So we have established some type of trust and then we thought okay this is actually a very nice niche to work in and it's also very fun because it's sort of you know I enjoyed working in supply chain so I sort of stay working in supply chain but I also work in AI.

Gotcha. Yeah. No totally I agree. I think that's definitely yeah I think it's interesting kind of where this intersection of everything plays out because you know when it comes to your journey just to kind of get more in deep after the beginning of it AI is obviously a great timesaver it's a great expander of capacity right.

According to some of the research we did you guys managed to have really solid revenue and growth only with like a 15 person team, you know, what does it kind of look like to be a company that's AI first, obviously an AI product yourself and kind of manage to run such a lean tight ship with what you're doing with AI and what's that experience been like?

Yeah, I think first of all we have been super lucky with the timing because as you say to be AI first has more or less only been possible very very recently. Sort of means that everyone that started like 10 years ago they sit with a lot of legacy and probably a lot of legacy competence and resources in the organization.

Yeah, we were actually able to start very recent and then we can actually be AI first and actually having the approach on building products with AI but also developed with the help of AI. So now I think it's actually more or less pure luck that we got the right timing because today you can do so much.

A man makes his own luck sir. I'm just kidding. No, but I think the huge difference is I think if I just go back maybe like two or three years ago then maybe you could focus only on AI. You would do the AI part but you would be super dependent on having like another agency or another team doing the UI and the front end and so on. Now I sort of do the front end and it goes quite quick.

And as we have the industry experience is that to create the front end when you sit with the experience without having all this translation to like a UI expert software engineer etc. you can move very fast. So I think the first real product we built at IKEA was like a demand sensing system and rolled that out globally to 400 stores.

Sure. Yeah. Maybe that took like two years or something. Now we are talking maybe 2-3 months to build something similar. It's crazy and also with much fewer people also.

No, that's totally fair. And I think it's interesting from my perspective because like you do have like a 15 person team, right?

Yeah. No, we are about 20 people but...

Gotcha. Okay. What do you think about the ability for what you're doing to be kind of enhanced via having like a smaller team because for me it seems like the more lean you are and the more agile you are especially in this world of AI, you can really build the foundation with these AI tools a lot better as a company.

Kind of following up on that, I would love to hear more about like how that kind of fits into some of the philosophy that you have for your practical application into companies workflows themselves too.

Yeah. No, I think if you go back a decade or even just 5 years, I think you know you will win a lot of clients saying hey we are like 10,000 people or we are 20,000 people. We are very capable of doing things. Now I almost think that it's actually not helping these companies to be 10,000 or 20,000. They're simply too big, too slow.

So I think actually speed is a more strategic asset than size nowadays. So I think that is actually what we can say that we can work fast and we can be close to the development both from a subject matter expertise but also from AI expertise and then we can have quick and interesting developments.

No, totally. I think that's very fair because practically speaking, when you get to the size of a 20,000, 30,000 person company, I mean, I've been at decently sized companies of a couple hundred, 400, 500 people, even at that stage, there's this funny level of red tape that occurs. You're like, I just don't know why, right?

But the bigger you get, the worse it gets. The more approvals you have to go through, the more layers you have to go through where it's like if someone just implemented this without the quote risk, I think it would just go quicker and better.

Yeah, I think a good example is up in the Nordics where I come from is actually this is Lovable. I don't know how many they are, but I think they're just like 40 people.

No, shoot. I love Lovable. Big fan. And they are no, a super big company at least the revenue but not in terms of size and employees. Yeah. So I think they're on track for something in the realm of like 200 million ARR.

Yeah, I think I read something it was like came out two days ago. I had the opportunity I think it was more or less one year ago. I think it was one of the co-founders actually demoed the product for me, but then it was like super immature one year ago.

So, but it was I really hope that you know just from that stage to go to this big type of spread around the world.

No, absolutely. I totally agree. That's really cool. That by the way that he was able to chat with you about that and show you that. So, kudos.

Very cool. What I would say just kind of taking a look at it is you know you are kind of in an interesting position. I actually have a question for you about, you know, what you guys do just to dive into a little bit more.

What would you say Eona solves for your customers mainly and what are those types of industries? I know there was a little bit of pharma reference and other regulated industries that were mentioned on your website.

Yeah. Well, that is one thing that is important that you pick is like regulated industry actually tend to be a bit also our specialty because it's not only to develop the solution it to develop also the overall governance.

So like for example in pharma you deal with a lot of patients data and that you need to have a very rigorous governance and security around. Finance is more or less the same. It's just it's not about the weight and the diseases of a person if the credit card details of a person and that you have to take equally good care of you.

So I think that is where we're working on. But you can also divide in like in the technology I would say still maybe one third of our work is more of this what I would refer to this traditional machine learning where we build like forecasting models who are predicting different events.

We have also been active in account frauds and so on which is also traditional machine learning to the majority even though we are moving in a bit to hybrid in both of them.

So for example, what I mean with hybrid is like maybe we use gen AI to qualify some signals that can be used in features for machine learning models for example.

So for example, if you want to digest a lot of like social media signals, you can leverage Gen AI to actually digest that into something that you can use as a feature in the forecasting model.

But then the rest two thirds it's purely gen AI and of course a lot of agentic solutions.

Maybe you want some examples also then what we do or yeah no absolutely I think that would be a great follow. What are some examples?

So I think in if we take supply chain to start with we mentioned like the forecasting and so on and then if we move into more the agentic AI it's a lot of workflow automation and that could be anything from like how you manage orders, how you manage invoices, etc.

So typically where you already have a group of like five, 10 or 20 people doing a little bit the same thing. So we have like a defined process and we are actually more or less automating this type of process.

And it's also that when you have those larger groups of people, I think it's also easier for our clients to harvest the savings also. So when they are thinking about when people are leaving they can actually think okay do I need to replace or can we manage and scale better with the AI solutions.

That is one thing. In pharma it's a lot around there's a lot of work around compliance and there AI is actually very very good.

There's also a bit of workflow compliance. Typically you have like medical compliance, regulatory compliance, maybe legal compliance.

For example, what are you allowed to say about this product? How are you making some typical medical claims that you either use in your marketing, you use them in your packaging, etc.

So that is something that all pharma companies, medical device companies and also a bit more on consumer health companies are dealing with on a daily basis.

Typically like a very long troublesome process where we can help with automation but also pre-qualify. So that means avoid submitting material that will not pass.

Yeah, that is the worst thing. You actually create something but it will not pass but it will go through some of the reviews and then it will get stuck on the last review.

So with AI we can help them to be pre-qualified to a very high probability. So that means that this flow instead of taking like several weeks or several months can now run in a couple of days through the organization.

So that's a very interesting use case. Then another case that my co-founder has worked a lot in is also how to leverage clinical studies.

So you have done studies in the past but now you actually want to look at like selection. You have registered a lot of data in this study but now you want simply more or less ask another question.

In the past it was you know there was someone that had a question but could not code. So this person had to go to a data scientist and then this data scientist would retrieve the data, clean the data, organize it and so on and then deliver the insight back.

That is something that we are actually building a lot independent of industry is more or less this text to SQL. So with natural language you can ask questions to your data and not only get the answers back but also maybe with visualization maybe also some proof points so you actually believe in the answer.

I think that is also always a challenge for example if you use just chat GPT you just get an answer but you know no reference.

No, that makes a lot of sense to me. I think it's interesting kind of where this sits because I would imagine and correct me on this a little bit, but most companies that are in regulated industries are on the surface you'd think a little bit more apprehensive towards or cautious about implementing AI solutions right now because of security reasons. Is that a fair assessment?

I think we can say we are experienced like two sides of this. Pharma, they are very rigorous about the data security but they're also very pro but they're also very progressive like they want to do it and they are doing it.

When we work in finance many of them are still operating like purely on prem which is interesting today with the open source model and the open AI latest models for example.

Last week we were in a meeting with one of the big banks around here, one of the largest in Europe and we shut off the Wi-Fi and we demoed what and like just what we had on the MacBook what you can actually do today.

This is quite amazing development. So that I'm actually very interested to follow maybe in the future we will not ship a product maybe I'll ship my MacBook pre-installed with the software and then you can work offline if you want the ultimate security but I think in the end also financial institutions they are moving into the cloud.

But then you can imagine it's in Europe is also important that it should be like a European cloud. The data should stay in Europe and not go anywhere else etc. So there are many parameters to think about.

Yeah totally. There are a lot of parameters to think about with this and I actually my dad works in finance in the states and I think they're in a very funny position especially when it comes to security like anything I feel like that comes up in finance is regulated at this point. Everything is very regulated.

So I would say another question that is important to a lot of people is you work across building multi-agent workflows right? I think now we've kind of learned about orchestration agent sorry agents that orchestrate. There's a lot of infrastructure and strategy questions how do you kind of decide which part of that journey each client needs whether they just need some individual agents how do you determine and how to build multi-agent workflows. What's your approach for that?

Yeah, actually it starts a lot with if you want to really zoom out, I would say it's like no difference with AI compared to when you maybe 10 or 20 years ago wanted to digitalize your process in some way. You really have to understand the process. You have to make sure that the process is also followed to a high degree and then you also have to break down the process.

Because if you write this like long prompt that should cover many steps on the process you're likely to be correct is not so high. But if you break down the process and tell the agent to focus only on this small part, you have a much higher likelihood to succeed.

That is also a big work and then you talked about orchestration and so on. So there is always a question if the clients already have some infrastructure in place.

When it comes to AI most of our clients don't have anything in place. So then we typically build also like the observability so we can observe the performance over time of these agents and then it's also the traceability is also very important in finance that you can actually trace back every single prompt that those agents have done because if you are in a compliance case you need to be able to prove what actually happened what did this agent conclude and ship to the other agent etc.

So you can actually trace it back and we use it also for problem solving and bug fixing also. So it's not only for compliance actually we use it a lot for our own development also.

Because then you can kind of see where things can be not only just like you're saying it's not only always about compliance. Now compliance is definitely important, but it's definitely important to kind of note what improvements you can make and why where it went off the rails and why it went off the rails.

Yeah, a minor question I do have for you because working in this realm I think there's maybe some interesting thoughts and misconceptions that one could have about models and how they impact things. I'm not saying that models mean nothing. Obviously they mean a lot.

But at what level have you noticed the biggest changes in model capability impact things practically? And then where has maybe there been like a bit of diminishing return because I think 4.5 sonnet was amazing. I think Gemini 3 was amazing. It just came out.

But like 0.3 was such a big step in reasoning. Reasoning models were big. But kind of in the last couple months, I've sort of had this feeling where we're seeing marginal improvement in a lot of things. We're maybe not seeing the same massive kind of leaps we were seeing before.

From a practical standpoint, maybe coding agents are going to continue to blow our minds, but where is this kind of improvement in models helped you guys out? And how have you kind of felt that they've helped you out a lot? And more maybe have they kind of only helped you out in sort of a marginal sense because that's the things I'm asking some founders and I've gotten a lot of interesting different answers recently.

Yeah, no, it is a very interesting topic because it's a lot of discussion in the industry about it that many predicted that everything is reaching a certain plateau and we are more and more seeing incremental improvements which maybe has been the thing actually the last couple of months.

But on the other hand, I think we have had just this week a bit of I think Gemini 3 is maybe too early to say, but so far what we have been testing, it's actually definitely not sharp, but actually what came the other day Nano Banana 2 that one for us, it's actually solved some problem.

It was like what? So coming back to when we are generating marketing materials, I think Nano Banana was really good in generating draft material with the visualization and everything but was not so good in accuracy on the text.

So they would put the text but a lot of obvious spelling mistakes. Nano Banana 2 seems like okay we have just tested it for like 24 hours but it seems like a majority of these things are actually gone.

Now because marketing material is typically you maybe have some background or like a person you have some illustrations of the things that you want to promote or show how good things are and then you typically have text also.

If you want to build tools that are generating this for the creators and so one of our marketing campaigns then the combination of all these three are important and I would say Nano Banana was good at two of them but now Nano Banana 2 actually does all three of them.

Nano Banana, say that fast ten times. It's ridiculous.

No, but I had noticed that it was good in Nano Banana 1. I haven't checked out 2 recently. So, I do appreciate you calling that out and I don't know how I missed that, but I'm excited to test it out after this episode ends.

Yeah, do that because it can also understand very much the context very well. One of the team actually just linked their LinkedIn profile and then Nano Banana did a super nice illustration of this person's career step by step what they have done and so on with illustration, the year, the text, everything. Super cool.

It's available right now in API if I'm not wrong.

Right. It's not really like okay. Yeah, that's fair. Okay, so that's a good note for me. Thank you for that. And everyone, make sure to go check that out because it's pretty dope.

Speaking of the improvements that we're seeing in AI and the capabilities that it has, what are some of the really cool things that you think will come out of this from a job standpoint? Because I think a lot of people are definitely concerned or really excited about what it means for jobs.

I kind of want to get an opinion of yours to understand where you stand on the whole is it going to create jobs? Is it going to remove jobs? Is it going to make jobs just different? Where do you stand on this whole thing?

Yeah. Hopefully it does both. Otherwise it will be boring. But I have actually faced this question the last 10 years and most likely people that worked before me at the companies I worked for that worked with the digitalization and so on they probably faced the same question for another decade earlier than that.

What did I learn? I think if I look back it's like can you mention a profession that existed 50, 60 years ago and doesn't exist today? It's not that many.

Yeah. Not many. There are not many. But I think there is one that is totally gone and that is the elevator operator. That is very seldom you see today.

So that has been replaced by buttons with the number on and people can push themselves. But otherwise it's like you're replacing 10%, 50%, 80%, 90% of a job. So of course if you have a big mass of people doing the same thing you will find some improvements there but otherwise it's still very difficult to fully replace a job.

Even autonomous driving today is based a lot on having people in the back office. Of course, one person can deal with several vehicles at the same time, but it's not that one person totally disappears.

And then you should also add in the people that it takes to develop this and maintain this, etc. So I think yeah, I don't know if I want to give a number, but maybe it's plus minus zero.

Plus, minus zero. That's funny. You know, fair.

I think the elevator operator is a good example I might use moving forward because it illustrates the lack of who cares, right? Like it's like okay, there's no elevator operators. Who cares at this point?

It's so abundantly clear that it is. I'm trying to find a way to phrase it. Maybe you can help me. There's a difference between value additive jobs and then there's a difference between I don't want to call it keeping up with the Joneses because that's not the right phrase but basically like jobs that are functionally able to do a task that keeps the thing going but it doesn't require any actual mental or physical prowess.

I don't know what the word is like cog maybe just cog jobs. People always talk about it's like oh I don't want to be a cog in the machine you know in the modern workplace but then when maybe those types of jobs would be removed by AI they often are afraid of it and I find it a very funny cognitive dissonance that exists there.

Yeah maybe those that are more cog in the wheel I would say they are more likely to be replaced by robots without AI because if you're doing exactly the same thing over and over again you can have a robot.

I think if you go to any modern manufacturing plant today, there are robots. That has already happened.

Yeah, that's a good point. People don't really talk about that. People don't really talk about the fact there was an entire move to elevator operator. There was well that's just the smaller bunch of people but the main people being manufacturing work I think was decreased by these robots you're mentioning.

And to be fair, you know, obviously it did mean something, but practically I do think people adjusted, companies adjusted, we've continued to see economic growth and people taking advantage of it so yeah it's a good and interesting point.

But you can also take another angle saying that what will happen with companies that do not adopt AI? There is no guarantee for survival.

That's on them, I'm just kidding. Yeah exactly no it is kind of on them to a certain extent because I think practically you know we have a lot of opportunity here to continue to do what we're doing and it really positively impacts people across the board.

Sometimes it's good to force people to get into like a higher level of knowledge work and let's say for example that's not their stick. I do think there might be some level of personability that comes back to work in an ironic way when we remove all of the non as heady knowledge work.

We do a lot of like learning a craft. I don't know what I should recommend my kids to do but it's like learning a craft and that might be a very valuable skill in the future.

I totally agree. Physical crafts I think could come back because good knowledge work might be so commoditized like basic knowledge work.

I think premium strategy stuff will probably be human still because people can come up with stuff in their head that pattern recognition can never get to.

Jeffrey Hinton when he won the Nobel Prize last year in an interview he was asked and he recommended that you should become a plumber because that is very difficult to replace with AI because you will work in very uncomfortable positions and you will work with your hands and every house that needs to replace the water pipes and sewage pipes looks different.

That's a fair assessment. There's some definite difficulty in a lot of these jobs that people don't appreciate.

Probably one of the most lucrative things you can do right now would be taking a company that's more brick and mortar or more blue collar. This is apparently something people in their 30s with some capital are doing. They're buying brick and mortar companies or blue collar companies like plumbing companies and they're automating a lot of the work that's more knowledge work.

They're optimizing routes and from there all that together is giving them like a much more high profit margin blue collar business and they're making great money with it.

There's a lot of opportunity in that sense that I think people are maybe unaware of. Obviously buying the company is not on the table for a lot of people but you could build a company and subcontract a bunch of different plumbers and optimize it better than an older owned company would be.

Yeah. So that's something definitely I think that could change in the future.

What do you think is the most misunderstood thing about AI and business right now?

If you take really the business perspective I think the most misunderstood thing is when I hear people say I use chat GPT at work because then I don't feel that they have fully discovered maybe the full potential.

If they just respond with that I don't think they use AI much.

It's like to use very generic tools in your work. I don't think that will make you the market leader. I think you should more think that with AI you can actually build something that is super relevant for your business today.

I totally agree with that. I think my favorite thing to ask people is what's their favorite AI model. If somebody can't answer the question, that means they don't know Jack about AI.

It's a very easy vet. I'm not saying they'll know everything if they tell you Claude or Gemini 3.0 was a great release today. But point is I ask that question because it tells me that they know nothing or something beyond the basic hype of what's going on.

You have your Geminis, your Nano Banana, so many different tools out there. What do you think is the most valuable thing practically on a daily basis that companies can implement with AI right now?

I think most companies have it but I think just to have a very good search. I think that is something in bigger corporations you tend to have a lot of documents.

So to have a really good search I think it's like connected of course with an agent or like an LLM so like a RAG solution of any kind.

So I think that is something. That's a pretty good answer. I didn't consider that. So you think it's more if you have nothing, you should at least start something because it collects points in a certain dimension.

First of all, it's a very simple thing to put in place. The investment is extremely low. A couple of days work and you will have it up and running.

It's also a bit like democratizing because I think today you actually if you're running a company you want a bit about the awareness because probably the good ideas will come from your organization.

Because there are a lot of repetitive tasks that are being done very repetitively and so on. Might not be so easy for the suite to know all this.

But actually to enable the entire organization to get some knowledge on what is the art of the possible you know then you will actually get all ideas to improve and so on.

I think that will be an easy starting point and you can also imagine how long time people spend on where do I find this document, what did we agree one year ago, what did we say at this meeting or something like this.

So that I think is an easy thing. But otherwise what we typically do is we ask what is the thing that you like the least about your job. That can also be a very good starting point on finding opportunities. That's a very good starting point in my opinion.

I think that's a very good point. There's so much that people dislike that they can get rid of.

I had a conversation with a friend of mine a couple days ago who was like, I heard you're into AI and stuff and asked me questions about what can be done.

It was so funny. They were just focused on this very minute in setting up a new client, like just being able to have a templated Google Drive that has a bunch of PDFs.

I'm like, this is possible in 2017, right? Like this is not like AI. I'm like Integromat and Zapier have been around for a while sort of type conversation.

But then when I explained to her that you could actually create agents that are able to analyze floor plans and make assessments of how much to charge for the drywall work and have that be an auto response basically, I was like you had to spell it out for me.

You're like how long does it take for someone to make a floor plan? I don't know like four or five hours. Okay. Is it basically square footage and analysis of how many walls and stuff? Yes.

I'm like, okay. So it's pretty much like if this then that. Yes. I'm like, okay. AI can pretty much do anything with reason that has if this then that logic.

So how many proposals do you do a year? I think we do like 200, 300 a year. I'm like, okay. So the average person works 40 hours a week about 48 weeks a year. I'm like, so that's 19 thousand? That's 2,000 hours.

If you tell me to do like 200, 300 of those, you just replaced a third of somebody's job. They're like, what? It's crazy. People are not at that level yet. They don't like it's not very well known.

If you had to give one recommendation for a personal tool that saves you time, I always like asking this question to kind of close things off and that'll let you plug what you're doing to end the show.

Yeah. No, I think a personal tool is what I like is for example if you use just the normal chat GPT app, what I appreciate a lot is the memory it actually remembers because while listening I work on something in my head and then maybe I use chat GPT then next weekend I have some more time to think about the same problem or I have discovered something new during the week and I want to add that into it.

If I take a very simple example, during COVID I was working more or less 24/7 because supply chain and COVID was not a good combo but it was fun times working but it meant a lot of work sitting still a lot.

After one year sitting on a chair, I started running and then this evolved into trail running. This year I've done like four races in trail running and I'm starting to get better and better.

Trail running is typically long and has a lot of elevation. So it's not like if you just run flat, it's easy to compare but now you have to compare how technical the terrain is, how long the distance is, and how much elevation I need to climb in the race.

It's perfect because it remembers those and then it can more or less tell me that if you run this race in two months, you will finish around four and a half hours.

When I've done another race, I can add that. So if I'm improving then I say okay the estimation I did for this race now we can actually reduce that by 10 or 15 minutes. So the memory I think for me is very useful.

That's a very good point. Honestly, the best thing for me is I'm recently using Claude a lot. That's like my favorite model right now. Gemini 3.0 is really good too so it's kind of hard to know.

Textcore is a tool that allows you to make agents and personas and have models that you can switch between as web search and all that kind of stuff. So it kind of like sets the infrastructure for AI.

I know it seems like a lot of those tools might not be useful where you just like it's just like a model hub but this one does a really good job of having really good writing agents and stuff.

There's another tool I recommend to all business owners and people on the go with meetings. It's called Krisp AI. It's the first meeting notetaker I've seen that really has noise cancellation.

Say you have you're on a train, you're in your car, whatever it is, and you're taking a meeting. It has about like a half second or full second delay from when you speak but it noise cancels the background noise.

Maybe I'll try it out. We actually built maybe next time I'll demo that for you. Like a video editing tool but more for scientific videos because videos are used a lot for training materials for example for specialist doctors and so on.

There we built a tool that not only transcribes but also keeps the balance because like you say it's very important to be correct and regulatory.

If you have several speakers several doctors speaking about the topic, if they are speaking for one hour and the specialist doctors are always on the run so they will have a format that is five minutes and then we can edit down the video but keep the same ratio.

If Dr. A and Dr. B spoke 50/50 they also speak 50/50 in the edited video and then we use agents to do the fully correct translation by uploading the scientific papers so you actually know exactly the drug names and so on because otherwise it could be like blah blah on something very crucial.

Those transcription models are very generic. They work for the general but when it's specialist talks it could be something untrue.

That's very interesting. I've been looking into AI and how it works from the standpoint of video editing and where that can lead because I don't think that's something on the market right now that's well done outside of just repurposing it for video shorts.

I think it's a spot in the market a lot of people would probably benefit from. I'll send you a link you can try it out. I'd love that.

With that being said, Peter, where can everyone go to find you to check you guys out?

We are in the center of Basel in Switzerland next to the train station, next to Maral, which is like a big food court. I think you knock on the door. Today we had someone knocking on the door a couple of weeks ago. A client knocking on the door saying, hey, do you work with AI?

Our website is econom, e-k-o-n-a, I think is the easiest way to reach out to us. I didn't tell you the story about the name.

There are many companies coming and going in the AI world and we wanted to make it a bit more long term. We are not venture backed. We are a fully private company with two co-founders. The initials of our wives and kids make up Eona.

That's very nice. I wouldn't have guessed that. Very cool.

It's always good. You got to give them credit. Those are the people that make you do what you do, right? Get you out of bed in the morning. You got to grind as a founder.

Small kids take this job very seriously. Get you out in the morning. Yeah.

With that being said, everyone, please make sure to go check out what Peter's doing over at Eona. That's a really sweet way to end the episode.

Also leave a like, subscribe, comment, and do everything you can to help support not only our show but what they're doing over there at Eona. Thank you so much for watching this episode and we'll see you guys in the next one.

Thank you. Thank you.