Suggestions

The suggestions tab enables you to continually improve the performance of your AI agents over time.

As you build and deploy AI agents, their interactions with users will scale beyond a level that humans can monitor on their own. To solve this challenge, Wayfound provides an automatic assessment of your AI agents using its AI Manager Agent, which continually monitors and evaluates your agents' interactions. It provides you with insights about your agents, serving as your interface with AI agents at scale.

Suggestions components

Suggested behaviors are recommendations to improve the quality of an agent's interactions. These recommendations are written as prompts using principles fromBehavior. They can be pasted directly into an agent'sBehavior tab.

Suggested knowledge identifies gaps in knowledge that, when filled, can enhance the agent's performance. We recommend that you consider each gap and the possible sources of information that can be used to fill them. You can track your progress against each gap by marking filled gaps as added on the right-hand side.

Suggestion views

You can customize the suggestions displayed by the Wayfound manager using the drop-down menus at the top-right corner of the window:

Agent Selection: Select which agent to analyze. You can choose from any agent in your current organization.

Time Range: Choose the time period for the data you want included in the assessment, from the past 24 hours to all time.

Recording types: Select which interactions are included in the assessment. You can choose between "Preview," which analyzes interactions using the agents tab (see Test your agents), or "Published," which analyzes interactions using the published agent interface.