Startup Flip AI has built a custom LLM to run its observability platform. Observability is the act of monitoring corporate IT systems, ferreting out issues or identifying potential problems before they occur. It’s a 24/7 process, and can slow down sites or apps, sometimes causing crashes. Not to be confused with the PDF reader app, Flip AI has trained an LLM specifically to monitor new and emerging challenges. Concurrently, Flip AI has announced $6.5 million in seed funding led by Factory with participation from Morgan Stanley Next Level Fund and GTM Capital.

Noting that “observability is a bit of a buzz word in IT circles these days,” TechCrunch quotes Flip AI CEO and co-founder Corey Harrison saying that despite the important role the process plays it is still largely manual and kluged together to track data among multiple systems.

“Large enterprises are using [multiple] tools, yet still have difficulty when it comes time to actually troubleshoot incidents,” Harrison told TechCrunch, explaining that the problem is often bigger in large organizations where tools and data are frequently housed in disparate systems, making problems difficult to isolate without a lot of manual queries.

Harrison teamed with co-founders Sunil Mallya, now Flip AI’s CTO, and Deap Ubhi, chief product officer, to tackle the challenge, using AI and automation to increase uptime and effect speedier troubleshooting and problem resolution.

Flip trained its own LLM using “over 100 billion tokens of DevOps-specific data like logs, metrics, trace data, configuration files, etc,” Harrison told TechCrunch, noting “it can then rationalize the same way humans were meant to query between systems.”

The resulting tool “analyzes the data across systems and generates a root cause analysis in less than a minute, and typically just a few seconds, according to Harrison,” writes TechCrunch, explaining the system leaves the data in place, “requiring just read access to complete the analysis.”

In the company’s news announcement, Harrison explained the team hopes to make Flip “the ‘holy grail’ of observability.” “When enterprise software doesn’t perform as intended, it directly impacts customer experience and revenue,” he said. Developers and operators currently spend “hours, sometimes days, poring through data and debugging incidents” that Flip can parse in a fraction of the time.

“At Flip AI, we think about observability data differently: as a unique, semantic language,” the company explains in a blog post, adding that “observability is the language that your systems and applications use to communicate, but all too often, engineers aren’t able to fully understand what these systems are saying.”