The algorithm is not providing a simple recommendation, it's providing you the complete and transparent answer. The decisions our algorithm makes is easily understandable by humans. You can see exactly why each segment was excluded. No magical thinking or confusing blackbox AI.
"DataGPT has made our analyst team 10x more efficient. We can stay on top of inbound requests with no querying, which frees us up to do more important but less urgent analysis that was never previously prioritized."
Diego Alonso Delgado Cáceres
Data Lead at Mino Games
"DataGPT has totally transformed our analytics. We’re able to get answers instantly, that would take weeks of work from our BI tools. Almost everyone on the team uses it every day."
CEO & Founder of Wombo
DataGPT’s algorithm removes 99% of the noise from your data and automatically surfaces the important insights you need to see: the factors that had a meaningful impact on your key metrics.
DataGPT has designed and developed a highly optimized data cache that allows for querying billions of rows of data in fractions of a second. This innovation takes hours of query time down while saving costs. Never wait for results again.
Using a single dashboard you can analyze your data with just a few clicks. View your key metrics’ performance and continuously drill down to investigate the details of what changed and why.
No more querying, complex formulas, weird terminology, or deep stats required. Any person on any team in your company can use DataGPT.
DataGPT analyzes all of your data so that nothing is missed. Every segment, every metric, and every user is explored to dynamically partition segments that most accurately represent the changes in your data.
BI tools are search-driven dashboarding tools - you have to know where to look and what to ask. DataGPT delivers true analytics.
You don’t need to know where to look, or the right question to ask. The key insights that explain the “why” behind changes are automatically surfaced.
or with Traditional BI (Tableau & Mode)
First, you go to your team of analysts or data scientists, if you have them, and they are already backlogged with a list of reports and tasks.
Access your DataGPT reports immediately, and click on the metrics you need to investigate.
Look through all of your dashboards, and if you have analysts, they hypothesize the main drivers and run SQL to validate or rule out each hypothesis.
You instantly see all the factors contributing to the change in the metric uncovered for you.
Check that each analysis was valuable - that it was statistically significant, there were no outliers, it wasn’t just correlation, and the query was bug free.
DataGPT validates every segment as part of the algorithm, so every insight is trustable.
How is this different than using ChatGPT’s Code Interpreter?
When it comes to performing data analysis, Code Interpreter has significant limitations.
DataGPT solves these limitations.
The result: users don’t need technical expertise or SQL experience to ask any type of question in natural language and have their data analyzed using DataGPT’s advanced analysis algorithms
Help me understand a bit more about how it works behind the scenes?
Customers use our schema builder where they define which tables, dimensions and metrics to focus on. After these definitions are set, we automatically generate an ETL to pull the relevant data. The data is then stored in our “lightning cache” format which is specifically designed and optimized over several years by our team of data scientists. This enables DataGPT to process millions of data points in seconds and simultaneously cuts costs. What would cost tens of thousands a month is now just a few dollars.
How long does it take to set up?
Typically it only takes a day to complete the one-time schema setup.However we find depending on your data maturity some customers may require a few iterations to the schema to optimize the value and capabilities of DataGPT. An assigned data consultant will provide that support and guidance during onboarding. The long-term benefit of that effort is streamlined data management and consistent definitions across all of your organization.
How much maintenance is involved?
None! Once the schema is defined it’s rare a customer needs to go make adjustments.
How does it handle metrics or dimensions that are not well defined in our existing tables?
If you have definitions in your database, we look at those definitions directly. If you don’t, when setting up the schema you can add SQL to fine-tune dimensions or create new ones. This also allows you to define the appropriate way to handle legacy data or missing entries. For example, if you wanted to track Daily Active Users, you can instruct the schema to look at the login event and count the unique users.
Is the analysis happening in real-time?
Yes. As users ask questions, DataGPT analyzes your data in real-time so you always see the latest results. This allows users to ask any question and always get an answer right away.However, note that the data analyzed by DataGPT is updated based on when customer’s data is fully updated in their data platform. Usually customer’s data collection is completed at certain time, so we define that time in the schema and have our ETL run at that time each day so that the analysis is accurate.
How can I trust the analysis?
We utilize an in-memory C++ database that has been finely tuned for data analysis over several years. This enables us to handle the most complex queries you might have, from auto-segmentation to the examination of literally every possible variable combination, to determine which factors are relevant, trustworthy, or outliers that should be ignored. This means each analysis is not just accurate but also highly transparent—each result can be independently verified or replicated with your own queries.
Can we train the AI models?
The analysis itself is performed by our core analytics engine and the AI translates that analysis in to the everyday language in DataGPT’s chat interface. Therefore there is no need to train the analysis itself, but the algorithms used can be customized or fine tuned as required. This fine tuning is completed during the schema setup process. Additionally, you can provide feedback on answers provided by DataGPT which allows us to continually fine tune how the results are presented.
What kind of questions can I ask? And what kind of analysis can DataGPT perform?
DataGPT supports key metric analysis, root-cause analysis, segment impact analysis, historical comparative analysis, and trend analysis. It can answer simple questions like “Which customers contributed the most to revenue this week” or “How did my campaign perform across each source” and complex questions like “Why did Conversions drop this week?”
It does not yet support forecasting or simulation (what-if scenarios), but that is a key part of the next iteration of the product pending customer feedback and requests.
How are the visualizations generated?
With each DataGPT response a matching visualization is provided to support the response. The visualization is generated based on the data used to generate the response and displayed as a time series, stacked chart, 100% stacked chart, bar chart, or line chart.
Tell me about your data security?