All-in exploration of AI infrastructure and developer tooling with Samy Melaine, Founder and CPTO of Eden AI. As AI capabilities move from data scientists to developers, Samy shares how Eden AI is simplifying the integration of AI features for developers worldwide. From his journey as a software engineer to becoming CPTO, Samy provides fascinating insights into building a platform that helps developers navigate the complex landscape of AI models and providers.
Through candid discussions about product development, user experience, and technical decision-making, Samy reveals how Eden AI tackles challenges in model selection, workflow creation, and performance monitoring. His perspectives on the future of AI, particularly around reasoning capabilities and the importance of thoughtful AI implementation, offer valuable guidance for both technical and non-technical professionals looking to leverage AI effectively.
Disclosure: Eden AI is our client, as Jatin says when he introduces Samy (1:37). Our work on Eden AI's workflow creation is described below.
Chapters
- 0:00 Preview
- 1:09 Introduction: Samy Melaine and Eden AI
- 2:41 From software engineer to data scientist to founder
- 5:56 Playing both CTO and CPO
- 9:41 What Eden AI does
- 12:35 Who it is for: API first, no AI expertise needed
- 13:48 Impact: one use case becomes many
- 16:30 Tech first, then product design
- 20:59 When UX became a priority
- 22:02 Making model comparison visual
- 25:23 UX designers and ML engineers in the Tcules AI lab
- 28:36 How user feedback changes the roadmap
- 30:25 Paying and non-paying users
- 31:43 Self-serve versus sales-led roadmaps
- 33:52 Trust: observability over explainability
- 37:17 Samy's model picks by use case
- 39:38 From choosing models to recommendations
- 41:21 Being transparent about recommendations
- 42:01 Pricing: a licence plus usage at provider rates
- 44:31 Subscriptions versus paying for results
- 46:19 Growth since launch
- 47:22 Fast growth and too many requests
- 48:59 Advice for founders building with AI
- 50:27 The next wave: reasoning
- 52:38 What will change in the next 6 to 12 months
- 53:53 Advice for UX designers
- 55:20 Close
“We thought that indeed AI was going more and more from the hands of data scientist and AI scientist into the hands of developers, so we wanted to bet on that.” Samy Melaine, Founder and CPTO, Eden AI (4:19)
Now, what does this shift really mean?
According to Samy, you don’t need to be a data scientist (or a researcher, if we may add) to be able to build AI products or, for that matter, use AI to its fullest potential.
That’s when Samy co-founded Eden AI: A full-stack AI platform for developers to efficiently create, test, and deploy AI. Samy says the platform has “something like few thousand users” in production around the world (14:29), and that most clients arrive with one use case and go on to use it for several.
At Tcules, we spend a lot of time with teams building AI products in a space that is evolving faster than their decision-making frameworks.
Choosing an AI model sounds like a technical task until it runs into user expectations, cost constraints, workflow complexity, and the opacity of black-box systems. That is where product thinking and UX stop being layers and start becoming the system itself.
This episode looks at that intersection: how developers, founders, and designers can simplify AI complexity, make better model and workflow decisions, and build products that are not just powerful but usable, transparent, and trusted.
Where AI meets product, UX, and decision-making
In this interview, Samy Melaine, Founder and CPTO of Eden AI, discusses how their platform simplifies AI model selection and workflow creation for developers. He emphasises building AI products with users in mind rather than implementing AI for its own sake. The conversation highlights how Eden AI improved UX by creating visual model comparisons and streamlining workflow creation. Samy advises developers to understand client needs, automate strategically, and leverage different AI tools rather than rely on a single fully automated solution.
In the first episode of Beyond the Interface, Jatin Leuva of Tcules and Samy Melaine of Eden AI look at UI/UX’s impact on AI product development.
Given that the number of powerful AI models has exploded in the past decade, the real challenge to building these products is choosing the right ones for particular use cases, building the optimal workflows, and keeping it cost-effective.
That is exactly where Eden AI comes in.
In this Beyond the Interface episode, Jatin Leuva, Co-founder and CEO of Tcules, a digital product design studio, talks to Samy Melaine, Founder and CPTO of Eden AI. We uncover the role of product development and user experience in building the next generation of AI-powered products, challenges and solutions to AI model selection, building workflows, and monitoring performance, Samy’s take on the best AI models for different use cases, and more.
But, before we uncover all that, we want to tell you about how it all started!
Eden AI Product Philosophy
With so many AI models in the market, selecting the right one has been one of the biggest challenges for the users of AI products. As these models become increasingly specialised for specific functions, working with and integrating several of these into a single workflow also becomes a challenge.
This is why Samy and Eden AI are on a mission to simplify all aspects of application development, starting with model selection. “All around the world, people look for the best AI models for some task. They find Eden AI that's regrouping all the AI models, so they understand they don't need to make a choice for their model or their provider. They can just have everything in one place.” (16:10)
To improve accessibility to developers, Eden AI is essentially an API-first platform that “anyone that is familiar with the concept of API can use… and you don't need any AI expertise, that's for sure” (13:05).
Eden AI is, in fact, taking this even further. Instead of choosing their own AI models, users have been increasingly seeking recommendations for their use cases.
“We are building a recommendation system that, for each input you give, we'll select on the fly the best model to handle it,” he said (40:37), adding that they can even prioritise recommending the most cost-effective ones (if that’s a criteria) to get the job done.
This single-minded focus on lowering the barrier to entry for AI usage is paying off in a big way, as Samy mentions that many of his thousands of users who were testing the waters on a single use case are now expanding to build for many others with the platform.
Marrying tech and product: Bringing out the best of both worlds
When asked about Eden AI’s product development strategy, Samy spoke about how, in the initial days, ensuring the stability of the platform and bringing robustness was their top priority.
Given that Eden AI is a tool for developers, this puts the team’s developers in a unique position to understand their users’ needs well. This is why when creating a new product or feature, the first step is to check the feasibility with the developers and then move on to refining the UX aspect. That said, user feedback has been equally important.
“We do emphasise on the fact that developers have to do some support themselves, so they are interacting with the users,” he said (19:28).
As their tech stack evolved, Samy and the team began to focus on product development.
“We understood how complicated it might be for developers to understand some parts of AI since it's a new thing. We have to simplify it and find a very easy way to explain the value it can bring to users.” (17:12)
He elaborates on this with an example of how Eden AI revamped the model selection process from mathematical evaluations through visual representation.
“When we orchestrate different models, we always give you visual input about the output at the end. So whether it's some transcription of an audio, if you want to compare two models that transcribe your audio, you can see the differences between the transcription very visually, or if it's an image or video analysis task, we can actually go into your video and see the different things that were detected.” (24:42)
This approach significantly improved the UX, but also intuitively gives a snapshot of the tone and the quality type of the final output, which is very important as Jatin from Tcules notes, a lot of these AI models operate in a black box model, where there is not a lot of transparency on how these models function.
This is where the consistent observability of an AI model’s performance also plays a big role in fostering trust among Eden AI’s developers. “Now the focus is more on observability and seeing how the model is behaving in production,” Samy says (35:02). For a GenAI model that generates text, that includes showing users whether its output is biased, and “making it as clear as possible from week to week how the model behaved, if it shifted or not.” By constantly communicating this information, it becomes a powerful tool in enabling developers to make informed decisions while building their product on the platform.
Given that cost-effectiveness also plays a big role in model selection, the platform also prioritises showcasing the lowest-cost models that get the job done.
The role of UX in product development
Along their journey, Samy and the team have placed a lot of importance on user experience, and it was, in fact, Eden AI’s developers who advocated for it.
“It was some developers on our team that were saying, like, ‘Hey, we actually love robust product, but when we see beautiful products, it makes it better, like we trust the company more,’” Samy says (21:17). For Samy, the biggest insight was that an improved user experience, whether it is about the ease of building workflows, the simplicity with which they can compare different models or just improved aesthetics, all contributed to increased trust for the user as it is a clear indicator how the people behind the platform pay attention to the details.
The most prominent example is how Eden AI worked with us to reimagine their workflows. Earlier, their interface was fragmented, with as many as three different ways to create a workflow: templates, AI assistance, or starting from scratch.
With separate interfaces for building, testing, and configuration as well, it added to the complexity and cognitive load for Eden AI’s users, hindering their ability to use the platform to its fullest.
Rather than maintaining different interfaces for different actions, we helped create a single, intelligent entry point that adapts to user needs. The interface was revamped to bring more user-friendliness to the workflow creation process by:
- Providing a single, clear starting point to process.
- Enabling natural language search for templates.
- Offering AI assistance through mode switching.
- Maintaining all creation options while simplifying the interface.
Read also: Unifying workflow creation through intelligent search
Jatin also noted that there are some use cases within AI product development where UX professionals can also be natural allies without the need for any other intermediaries. He recounted how in our AI lab, we got a few Machine Learning (ML) engineers to collaborate with UX designers as an experiment. The logic being that the team knew the final output needed for the user, and given that the UX person is naturally placed to know their users’ expectations, the overall model-building process would be more efficient.
“But what other thing that we experienced, which was very interesting, is the UX person was able to collaborate at the technical level, where they were also able to help write better prompts in collaboration with the ML engineer, and it somehow reduced the number of iterations that were going into the R&D,” said Jatin (26:32).
Samy’s tips
Eden AI was not the only subject of this conversation. Samy believes that after the Gen AI wave, reasoning in AI models is the next frontier in landscape. “A lot of people are talking about agents now. Agents need reasoning, and if you want to have fully automated agents, we still need for reasoning to be fully handled.” (50:54)
For those interested in building AI-based applications, Samy’s advice is straightforward: understand what your clients want. “Don't do AI for AI's sake, but do it for your user's sake, and try to automate as many things as possible, because that's the main job of AI. It's not to replace people… it's just to automate tasks for you and for your customers to gain more time and get more value as fast as possible.” (49:32)
Till the time that reasoning in AI catches up, he also advises developers not to fully automate their work with one agent in the expectation it will handle everything itself. “Leverage different AI tools, still build the logic yourself, understand what you want to do and put AI in the right place.” (51:40) He also had some opinions on the best AI models for popular use cases.
“I think Google is doing actually pretty good with their generative AI models, especially the chat one. Then Gemini is surprisingly good, the latest version… But I also like Anthropic, as a lot of developers, because their models are way better at code editing and understanding, like if you compare it to GPT, for example. And I need to give a lot of credits to Amazon for their video analysis. They have some very good video analysis models… For speech, I think it's mainly ElevenLabs, like speech to text, understanding speech or speech synthesis, making robots talk. I think ElevenLabs is doing a great job at that.” Samy Melaine, speaking in late 2024 (37:47)
The conversation ended on a high note with Samy’s advice for UX designers. “My advice will be to not hesitate to ask GenAI models for ideas,” said Samy (54:18). “I've seen a lot of designers blocked with some tasks… and the current behaviour is just to check on Dribbble and some different ideas and try to get inspired from that. I think one important source of inspiration is GenAI… I really think that's something that should be done more frequently.”