We began by addressing a specific operational challenge: every time a Pressure Safety Valve lifted, the event was detected in PI AF and visualized in existing tools, but all follow-up actions required users to manually collect operational and data, among other sources. This manual process delayed troubleshooting and increased operational risk.

To solve this, we first enabled users to generate structured reports from databases, and then evolved to AI powered agents capable of producing ad-hoc insights using PI Historian/AF, Connect and Databricks. This evolution drove a paradigm shift: from people searching for data to AI agents autonomously integrating structured & unstructured data and proactively delivering event reports the moment anomalies occur.

We call this shift “from data access to data delivery”.