Speakers: Darshana Nair (CLA, CliftonLarsonAllen, a leading accounting and professional services firm) and Michelle JanneyCoyle (Databricks)
If you have built and deployed an AI agent or an AI solution, you will have asked: how do I know if this actually works? At CLA, every audit engagement produces a large number of complex reports. Multiplied by every client, every engagement and every audit cycle, collectively an enormous amount of time is spent extracting data from these complex unstructured reports by hand. LLMs and document AI can help, but how do you trust the process, and how do you verify and measure quality when an LLM extracts that much data at scale? The talk shows how the team stopped guessing whether the extraction pipeline does a good job and started scoring, measuring and continuously improving. The structure: business context, a short application demo, technical architecture, evaluation strategy, takeaways.
Google or a one-time email code. No password.