Filip Schouwenaars

DataLab — Go from data to insights with the help of AI

Featured
30
DataLab is a data notebook that (1) smartly leverages generative AI technology so you can ‘chat with your data’, (2) features a powerful IDE to review, tweak and run your analysis, and (3) seamlessly turns your work into an beautiful, shareable report.

Add a comment

Replies
Best
Filip Schouwenaars
Hey all! I'm Filip, leading the development of DataLab at DataCamp, and I'm super excited to show you what we've built in the past months and to hear your feedback. The next iteration of DataCamp Workspace, DataLab is an AI-powered data notebook to go from data to insights by chatting in a ChatGPT-like interface. Because Generative AI can still make mistakes, DataLab's AI assistant writes and runs code that you can seamlessly review, tweak and share, without leaving the tool. That way, you can fully trust the insights you're uncovering. DataLab can connect to any data, wherever it lives: CSV files, Google sheets, common data warehouses and databases are all supported. Finally, DataLab also has built-in collaboration and reporting capabilities, so you can go from data, to insight, to shared understanding in a matter of minutes. Give it a spin (for free!) and let us know what you think and how we can improve! https://www.datacamp.com/datalab Cheers, Filip
Filip Schouwenaars
@max_savonin1 All great questions, let me answer them one by one > Can DataLab's AI assistant handle complex data transformations and preprocessing tasks within the chat interface? If you have a good idea of what transformations and preprocessing you want to do, I suggest you switch to DataLab's "Code View", which is a fully-featured notebook editor. It has an AI code generator built in to write code from scratch or extend some code you already wrote. > How does DataLab ensure the explainability and trustworthiness of the insights generated by the AI assistant? All the code that the AI Assistant in the chat generates, is being added to a corresponding notebook. Users can seamlessly switch to this code and review, tweak, run and share it. Hope this answers your question! Any shares in your network are greatly appreciated!
Oh wow, the video demo looks really great! ❤️ I think it's smart that you provide familiar UI to the users. It lowers friction. I can see that even non-technical people might try and generate reports themselves. Do you see non-technical users as a target audience for DataLab? All the best with the launch team DataLab 🚀
Filip Schouwenaars
@jgani Thanks for your message! We're at this journey for quite a while already. We started out with a code-first data notebook, but were always looking for ways to make it more accessible and easier to use, so that anyone, regardless of technical skill, could get insights from their data. The rise of generative AI has provided a new way of going about this challenge, allowing users to describe in plain English what insight they want. The quality of large language models (LLMs) is not (yet!) at the level where you can just throw any data warehouse at it and expect it to give accurate answers in all cases, but it still unlocks a great analytics experience: > Before, without AI: Analyst spends hours building a dashboard that can answer every possible question colleagues might possibly have. Colleague with a question needs to dig through a bunch of filters to get the insight they need. > With DataLab: Analyst on the team prepares a clean dataset with all the required properties and data slices, and makes this available through DataLab. Colleague starts a DataLab chat, ask what they need, e.g. ‘how many subscriptions did we sell in the past 30 days in France’. DataLab generates and runs code in the background, and answers the question on the spot. The generated to answer the question can be easily inspected, adjusted and re-run in DataLab’s fully-featured data notebook. LLMs will get more powerful, and DataLab will become increasingly smart about how to get the best results (leveraging past interaction data, previous data queries, company documentation, etc), making life easier for the analyst and getting insights significantly less frustrating for less technical folks. This answer turned out longer than expected, but I'm pretty passionate about all this, hope you don't mind!
@filipsch I'm all too familiar with the 'before AI' world. We had to build a custom solution for non technical people, literally like you described it. DataLab is very well positioned to take advantage of the AI revolution. Congrats FIlip!
Aman Wen
Just hit the upvote 'cause what you've got here sounds like a game changer. Chatting with data that's cool and kind of sci-fi. Plus, the collab IDE and snazzy report sharing sounds like you're making data talk turkey and look good doing it. Got a burning question though. How user-friendly is this for folks not super tech-savvy? Can a regular Joe get good stuff from this without a tech dictionary? Keep rocking it. Cheers!
Filip Schouwenaars
@aman_wen Great question! In the "AI Chat" mode the user is not exposed to any code at all. Instead they just pop in a dataset and start asking questions. In the background, the AI is writing code to answer the question, but the user doesn't see this unless they want to. If the user decides to go to the "Code" mode, they're met with a clean, slick, yet powerful notebook editor with all the necessary features to delve deeper into the code, should they want to. Regardless of the mode that users are in, we're obsessed with keeping the UI and UX super simple and accessible, also for not super tech-savvy folks. Hope this answers your question!
Bart
Just tried it out and I must say that I’m really impressed with the AI chat. I don‘t normally comment on these kinds of posts, but was compelled to create an account to send a big congrats to the team. The interface looks slick. You guys really hit it out of the park. Is this a steak? Because it’s both rare and well done!!!
German Syroezhkin
> DataLab can connect to any data, wherever it lives: CSV files, Google sheets, common data warehouses and databases are all supported. Hey @filipsch :wave: Can I connect it to my Mongo DB? How easy the integration is?
Aaliya Shah
This is a must-have tool for any data enthusiast! 🚀
Iting
Congrats on the launch!!!✨
Richard Cotton
Finally notebooks have matured from those-awful-Jupyter-things-I-have-to-use to a product I want to use. The AI assistance makes tasks like exploratory data analysis dramatically faster, and the ease of sharing workbooks makes collaboration idiotproof.
Germán Merlo
Wow Filip! You did it. Turning data into insights sounds obvious but actually it isn't, I know it. Happy to see you helping on that and wishing you all the best on this journey!
Sergey Solovev
I just got a case to try DataLab with, going to check out its analytics capabilities. Congrats on the release!
Jesus Vazquez
I’m glad to see you guys on PH. I have followed the product for a while now. Congratulations on your launch.
Adri Duch
Looks slick! I like the simplicity of it. Very easy to get started. Congrats!
Jeremie Roblin
Very impressive demo, congrats on the launch
Anand Reddy KS
Looks interesting. Can user ask a followup question as well ?
Emily Willis
Great tech!
Tiep Vu
Congrats on your launch! I'm impressed with the demo. Love to explore products that enhance the work with data like this. Upvoted! Btw, my new product AppAlloy is also about working with data. It transforms datasheets into mobile apps for a more intuitive and friendly work experience with data. Love to hear your opinion about it Appreciated!
Albert
congrats on the launch, filip and team! datalab sounds like a powerful tool for data analysis and collaboration. i'm curious to know, how does datalab ensure data security and privacy when connecting to various data sources? looking forward to exploring it further!
Filip Schouwenaars
Hi @mashy! Excellent question! You can see an overview of security measures we take here: https://www.datacamp.com/datalab...
Yuvraj Dagur
Congratulations on the launch Filip. DataLab looks like a great addition to any tech or non tech person who wants to get some insights out of their data without the hassle of writing code themselves. What usecase do you see for Startups and small businesses for this? are you also targeting to cater that user persona?
Filip Schouwenaars
@yuvraj_dagur Imagine a startup building an offering online AI courses; to power their website and their product, they'll have a database (e.g. PostgreSQL), with different data models (courses, exercises, AI prompts, user feedback, etc). With DataLab, you can hook up to that PostgreSQL database in a matter of minutes, and ask the AI questions like "how many courses were started in week 20 of 2024". The AI knows about the database schema and will write and run SQL code (and maybe Python code after that) to answer your question and present it to you. All this to say: yes, startups and small businesses can definitely use this!
Alex Dulub
Hey Filip! The concept of 'chatting with data' sounds fascinating, especially with the added layer of AI assistance. The ability to run, review, and tweak code directly within DataLab seems like a powerful feature for data professionals. Curious to know, how does the AI handle more complex data queries or analysis? Going to check it out!
Filip Schouwenaars
Hey @alex_dulub sorry for the late reply. We don't treat complex data queries differently from simpler data queries, but it's true that quality can suffer at some point (if the question is poorly defined, if the connected data source has a massive schema of 100s of tables, etc). LLMs will get more powerful, however, and we're constantly working to make DataLab increasingly smart about how to get the best results (leveraging past interaction data, previous data queries, company documentation, etc), making life easier for the analyst and getting insights significantly less frustrating for less technical folks.
Syed Mehmud
Upvoted. Looks great! Is this product only SaaS based or can it also run locally on my hardware?