Trusting AI Extraction - Confidence Scores, Governance and Human in the Loop Design

Register now

* All fields are required

Available live times (choose one)*:

First name*

Error: Please enter your first name.

Last name*

Error: Please enter your last name.

Business email*

Error: Please enter your email.

Phone number*

This fields is required

Job title*

This fields is required

Company*

This fields is required

Company size*

This fields is required

Country*

This fields is required

Attendees are encouraged to bring one extraction challenge (a document type where accuracy is below expectations) for live troubleshooting. Anything else you’d like covered in this roundtable?

This field is required.

Would you like to speak at a future community roundtable?

This field is required.

The number one barrier to AI adoption is not technology -- it is trust. When extracted data feeds into compliance workflows, financial systems, or regulated processes, "mostly accurate" is not good enough. This roundtable tackles the trust problem head-on, exploring Box Extract's new confidence scoring system, governance controls, and design patterns for human-in-the-loop validation. We will examine how enterprises are building extraction workflows where AI handles the high-confidence cases automatically while routing uncertain results to human reviewers. This session provides a practical framework for deploying AI extraction with high trust.

Topics we'll cover:

How Box Extract confidence scores work (aggregated LLM responses, decimal percentages, Low/Medium/High labels) and how to set thresholds for your use case
Design patterns for human-in-the-loop workflows and the Accuracy / Automation curve
How Box's native governance model (permissions, classification, audit trails) provides trust infrastructure
Practical governance policies for AI extraction: who can configure agents, which folders are in scope, how to audit extraction results
Regulatory considerations: HIPAA, GDPR, and industry-specific requirements for AI-processed content

Speakers

Jack Robbins

Product Manager, Metadata Extract, Box
Scott Picanco

Senior Product Marketing Manager,
Box