Pendo’s Agent Analytics is Now GA, Helping Companies See and Optimise How Users Interact With Agents

Pendo, the world’s first software experience management platform, announced the general availability of Agent Analytics, expanding access to the only solution in the market for measuring the performance, usage, and business impact of AI agents across the enterprise. Pendo has made Agent Analytics free to get started, empowering every customer to build and deploy successful agents.

During its early access period, Agent Analytics helped dozens of organisations understand how users interact with their AI agents, measure the quality of agent outputs, and identify where agent behaviour supports or hinders user productivity. One early adopter, Pushpay, leveraged Agent Analytics during the beta of its new conversational agent, uncovering prompt trends and user frustration signals that informed improvements to the experience prior to launch.

“Companies are launching agents faster than ever, but they’re relying on a simple thumbs-up or thumbs-down to gauge their success which is insufficient,” said Todd Olson, CEO and co-founder of Pendo. “Agent Analytics fills that gap, giving teams a reliable way to monitor usage, detect friction, and improve the user experience, ensuring their investment in AI delivers meaningful business value.”

Customer proof: Pushpay’s story

Pushpay, the leading payments and engagement solutions provider for more than 14,000 mission-driven organisations globally, deployed Pendo Agent Analytics to monitor a new AI search agent where church leaders can instantly query their membership and donation data using natural language.

“We started noticing users were prompting only three or four times, then quitting. Agent Analytics made that pattern obvious, so we could pinpoint and target exactly where users were getting stuck. Now we can get them past that drop-off point and into real value,” said Paul Frank, staff product manager at Pushpay.

“Every day we’re learning something new with AI. Agent Analytics helps us understand what our customers want to know—which has informed how we prioritise prompt inferences, fine-tuning, filter enhancements, and experience redesigns based on real usage, not assumptions.”

What Agent Analytics delivers

Agent Analytics shows how agents perform once they’re in real use – how people interact with them, where they help, and where they fall short. While eval tools support pre-launch testing, Agent Analytics reveals what happens in real workflows. With Pendo’s enterprise-grade monitoring and governance controls, teams can improve and optimise their agents and understand the value their AI investments deliver.

Core functionality includes:

• Tracking hybrid workflows across both agents and traditional software to show how users move between tools and where agents fit in.
• Surfacing patterns in what people do before, during, and after interacting with an agent, and seeing it firsthand through visual replays.
• Analysing conversations to identify prompt themes and emerging use cases, so teams know where to optimise the agent. Then track whether those updates lead to better results.
• Surfacing “rage prompts” and alerting teams of issues that cause frustration, or impact trust and performance.
• Flagging “off-script” behaviour, hallucinations, or inabilities to respond so teams can quickly take action to fix any issues.
• Embedding guidance and surveys inside the agent interface to help users find success and capture their feedback.
• Mapping agent activity to task completion and overall platform engagement to assess ROI and performance.