Webinar: Cadeon AI Connect Interoperability Between Spotfire, Snowflake, Databricks, and Power BI

Cadeon AI Connect: Connecting Spotfire, Snowflake, Databricks, and the Future of Power BI

Modern data teams have invested heavily in analytics platforms.

Many organizations already use Spotfire. Many have also invested in Snowflake, Databricks, Microsoft Power BI, SQL Server, Oracle, Postgres, and other enterprise data systems. Each platform has its own strengths, but the real challenge is often not whether the tools are powerful enough.

The challenge is getting them to work together in a way that helps teams move faster.

In Cadeon’s webinar, Cadeon AI Connect,  Come See the Interoperability Between Spotfire, Snowflake, Databricks, and Power BI, Amanda Summers and James Louie introduced Cadeon AI Connect and demonstrated how it helps reduce friction between data platforms, visualization tools, and AI-enabled workflows.

The session focused on one practical goal: helping organizations move from data to insights with less manual effort.

The Problem: Powerful Tools, Disconnected Workflows

Many companies have already made major investments in platforms like Spotfire, Snowflake, and Databricks.

These tools are powerful, but value can be difficult to unlock when users still need to manually connect tables, build relationships, write custom expressions, manage calculations, move data between systems, and rebuild similar workflows across dashboards.

That friction slows teams down.

Instead of spending time analyzing data, users spend time preparing it. Instead of quickly building dashboards, they deal with joins, calculations, field usage checks, data lineage questions, and platform-specific steps.

Cadeon AI Connect was built to reduce that friction.

Amanda described AI Connect as a capability rather than a traditional product. The point is not simply to add another tool to the stack. The point is to help organizations get more value from the tools they already use by connecting analytics, AI, and modern data platforms more effectively.

What Is Cadeon AI Connect?

Cadeon AI Connect is a capability that connects Spotfire with AI-enabled workflows and enterprise data platforms such as Snowflake and Databricks.

It is designed to help users work more naturally across dashboards, data tables, semantic layers, and modern cloud data environments.

In the webinar, James explained that AI Connect is deployed as a Spotfire SPK package and configured to use an organization’s chosen large language model. That could include Azure OpenAI, AWS Bedrock, OpenAI, Claude, or another approved model depending on the organization’s environment and governance requirements.

AI Connect can also connect to modern data platforms using the user’s existing credentials. This allows organizations to preserve governance and access controls while still making data easier to discover, query, and use.

The result is a more connected analytics experience inside Spotfire.

How AI Connect Differs From Spotfire Copilot

The webinar also clarified how Cadeon AI Connect relates to Spotfire Copilot.

Spotfire Copilot provides natural language querying and AI-assisted capabilities within Spotfire. It can help users ask questions, create visuals, generate data functions, and work with certain platform features.

Cadeon AI Connect extends the idea further by focusing on interoperability and workflow acceleration.

AI Connect supports capabilities such as:

• Dashboard and mod authoring
• Writebacks to databases
• Companion tools for lineage and field usage
• Custom expression generation
• Fit-for-purpose workflows
• Connections to Databricks Genie and supervisor agents
• Connections to Snowflake Cortex
• Interaction with structured, semi-structured, and unstructured data
• Support for traditional enterprise databases such as Oracle, SQL Server, and Postgres

Spotfire Copilot and Cadeon AI Connect can work together, but they do not have to. They can also operate separately depending on the organization’s needs, architecture, and preferred AI workflow.

Moving From Data to Insights Without Friction

A major theme of the webinar was “data to insights without friction.”

In many Spotfire environments, users start with data tables that are not fully ready for visualization. They may need to join tables, create calculations, build relationships, design visuals, create custom expressions, and configure interactive controls before the dashboard becomes useful.

That work is important, but it can take time.

AI Connect helps accelerate those steps by using AI-assisted tools that understand the data environment and support common dashboard-building tasks.

James demonstrated several ways AI Connect can help users move faster inside Spotfire.

Relationship Builder: Faster Table Relationships

One of the first companion tools shown in the demo was the relationship builder.

When users bring multiple data tables into Spotfire, they often need to define relationships between them before dashboards and markings work properly. AI Connect can review the available tables and suggest relationships based not only on column names, but also on the underlying sample data.

That makes it easier to understand how tables connect and how they should behave across visualizations.

For teams working with multiple data sources, this can reduce setup time and improve consistency.

Extracting Calculations for Better Performance

Spotfire dashboards can become heavy over time, especially when they include many over expressions, calculated columns, and increasingly large data sets.

James showed how AI Connect can extract calculations from a Spotfire file so teams can better understand what logic exists inside the dashboard.

This matters because some calculations may be better handled at the data warehouse level instead of inside the Spotfire file. Pushing logic down to Snowflake, Databricks, or another backend platform can improve performance, reduce dashboard load time, and make calculations more reusable across the organization.

In other words, AI Connect can help teams identify where work is happening and where it may be better placed.

Field Usage and Data Lineage

Another key feature demonstrated was field usage and lineage.

AI Connect can help users understand which fields are being used in calculations, relationships, visualizations, and other parts of a Spotfire file. It can also extract metadata about data sources, data functions, pages, visualizations, joins, and table structures.

This is useful for teams that need to optimize an existing Spotfire environment.

If a dashboard has grown over time, it may contain unused fields, old calculations, unclear relationships, or logic that no one fully understands. AI Connect helps surface that information so teams can clean up files, improve performance, and make migration planning easier.

This is especially valuable for organizations moving toward modern platforms like Snowflake, Databricks, Microsoft Fabric, or other cloud data environments.

Natural Language Querying Inside Spotfire

AI Connect also supports natural language querying inside Spotfire.

In the demo, James showed how a user could ask a question about the data, such as how many wells are suspended, and AI Connect could interpret the request by understanding the available data tables and relationships.

This is important because the answer may not live in one obvious table. The relevant data may come from a status table, a details table, or another related source. AI Connect can use the defined relationships to help find and return the relevant answer.

For business users, this can make Spotfire easier to explore.

Instead of needing to know the exact table, field name, or filter logic, users can ask a question in plain language and use AI Connect to help surface the answer.

Dashboard Mode: Building a First Pass Faster

The webinar also demonstrated dashboard mode.

Dashboard mode helps create an initial version of a dashboard from a natural language request. For example, James asked AI Connect to generate a map containing wells and the year they were spudded.

AI Connect created a first-pass dashboard, including visuals, dropdowns, filters, and a text area.

This does not replace good dashboard design, governance, or human review. But it can dramatically reduce the time needed to get started.

James also explained that dashboard generation can be configured to reflect the organization’s preferred templates, color schemes, layout rules, and governance standards. That makes it possible to accelerate dashboard creation while still respecting internal design and reporting practices.

Interoperability With Databricks and Snowflake

One of the most important parts of the webinar was the demonstration of how AI Connect works with Databricks and Snowflake.

AI Connect can connect to these platforms and use their existing semantic layers, governance, and AI agents.

On the Databricks side, AI Connect can work with Genie and related agent capabilities. On the Snowflake side, it can connect with Cortex. This allows users to ask questions, discover relevant tables, preview results, and bring data back into Spotfire without manually navigating every connection step.

James demonstrated how AI Connect could ask Databricks for available data tables, preview the result, and then add the selected data directly into Spotfire through the existing connection.

This creates a smoother experience for users who need to explore data from modern platforms but still want to work inside Spotfire.

Working With Structured and Unstructured Data

The webinar also touched on structured and unstructured data.

Structured data might include database tables, production data, well data, completion costs, or other organized sources. Unstructured data might include PDFs, daily drilling reports, safety incident reports, land agreements, joint venture documents, or other files.

James explained that when unstructured data is placed into platforms like Snowflake or Databricks and vectorized properly, AI Connect can help surface that information through the chat interface and connect it back to the analytics workflow.

This is where modern data platforms and AI-enabled analytics become especially powerful.

Organizations can begin to connect dashboard data, structured records, and document-based knowledge in a more usable way.

Writeback Capabilities

AI Connect is not only about reading data.

It can also support writeback workflows.

James demonstrated the ability to copy a table from Spotfire into Snowflake. This could be useful when a user has curated a valuable data set inside Spotfire and wants to make it available in a database so other users, dashboards, or tools can access it.

The same concept can apply to Databricks, Postgres, Oracle, SQL Server, and other supported databases, depending on the organization’s environment.

This opens up practical workflows, such as:

• Copying curated public data into a governed database
• Sharing useful Spotfire-prepared data sets with other teams
• Moving data into sandbox environments for further engineering work
• Writing back notes, commentary, or analysis outputs
• Supporting semantic data products that can be reused across reports and tools

Permissioning still matters. James noted that writeback can be governed based on user permissions and can be directed to production or sandbox environments depending on the organization’s data governance model.

Building Semantic Layers and Data Dictionaries

Another useful capability discussed during the Q&A was the creation of semantic data products and business-friendly metadata.

AI Connect can support cataloging by reviewing tables and data values, then generating metadata and business descriptions. This can help teams create a more usable data dictionary and improve understanding of what fields mean.

That matters because enterprise data often contains cryptic field names, unclear codes, or tables that only a few people understand.

By using AI to support cataloging and metadata creation, organizations can make their data more accessible to analysts, business users, and downstream tools.

AI Mods and Fit-for-Purpose Workflows

The webinar also showed how AI Connect can support custom Spotfire mods.

James demonstrated examples where marked data in Spotfire could be sent to an LLM and summarized inside a mod. For example, a user could select a completion job and receive a quick analysis of actuals versus estimates, job summary, or common issues.

This creates a more guided analytics workflow.

Instead of moving data out of Spotfire into a separate AI tool, users can interact with AI directly inside the dashboard context. They can mark data, trigger analysis, review summaries, and potentially write notes back to a database.

This kind of workflow can support use cases such as:

• Well lookbacks
• Completion cost reviews
• Downtime analysis
• Engineering notes
• Operational summaries
• Root-cause review workflows
• Performance monitoring

The key value is that AI becomes part of the analytics workflow instead of a separate tool outside it.

Custom Visualizations Beyond Out-of-the-Box Spotfire

Another question from the audience asked whether AI Connect could help visualize data in ways that go beyond what comes out of the box with Spotfire.

James explained that custom mods can support visualizations that are not native to Spotfire, such as specialized charts, odometer-style visuals, 3D surface charts, combo charts, and tabular views with grouping, collapse, and expand functionality.

This is especially helpful for teams that are used to specific visual formats in Excel or other reporting tools and want to bring similar views into Spotfire.

Custom mods can help create more fit-for-purpose analytics experiences for the way teams actually work.

Legacy Systems Still Matter

The webinar also made an important point: not every organization is fully on Snowflake or Databricks.

Many still rely on Oracle, SQL Server, Postgres, legacy databases, and existing Spotfire DXP files.

AI Connect is designed to work in that reality.

James explained that even if an organization is not currently using Snowflake or Databricks, AI Connect can still help with Spotfire workflows, natural language querying, dashboard acceleration, metadata extraction, and integration with existing enterprise systems.

This matters because most organizations do not modernize everything at once. They need tools that can work across current systems while helping them move toward modern platforms over time.

Power BI Is on the Roadmap

The webinar also addressed Power BI.

Amanda noted that many organizations use both Spotfire and Power BI. Cadeon has Power BI support on the AI Connect roadmap, with development planned to begin in Q3 and expected to be finalized in Q4.

That means the long-term vision for AI Connect is not limited to one visualization platform.

The broader goal is interoperability across analytics tools, AI capabilities, and enterprise data platforms.

Why This Matters

The real value of Cadeon AI Connect is not just that it adds AI to analytics.

The value is that it helps remove friction from the work teams already do.

• It helps users understand data lineage.
• It helps identify field usage.
• It helps build first-pass dashboards.
• It helps query data in natural language.
• It helps connect Spotfire with Snowflake and Databricks.
• It helps write curated data back to databases.
• It helps create custom mods and fit-for-purpose workflows.
• It helps organizations use modern data platforms without forcing every user to become a platform expert.

For organizations that have already invested in Spotfire, Snowflake, Databricks, and other enterprise data systems, that can be a major accelerator.

Final Thoughts

Cadeon AI Connect is designed to help organizations get more value from the analytics and data platforms they already have.

The webinar showed how AI Connect can reduce manual work, connect Spotfire with modern data platforms, support natural language querying, generate first-pass dashboards, surface lineage, build custom mods, and enable writeback workflows.

It also showed that interoperability is becoming increasingly important.

Modern analytics does not happen in one tool. It happens across dashboards, cloud platforms, databases, semantic layers, AI agents, and business workflows. The organizations that get the most value from their data are the ones that make those systems work together.

Cadeon AI Connect is built around that idea.

It helps teams move from data to insights with less friction, stronger interoperability, and more practical AI support inside the tools they already use.

Ready to Explore Cadeon AI Connect?

Talk to Cadeon about how AI Connect can help your organization connect Spotfire, Snowflake, Databricks, and future Power BI workflows into a more seamless analytics experience.

Whether you are modernizing your data platform, improving Spotfire workflows, building AI-assisted dashboards, or looking for better interoperability across your analytics stack, Cadeon can help you explore what is possible.