Ned FriendGuest
I'll type, "You are a new staff onboarding agent to help answer questions about business processes, how to perform common tasks, and provide answers to product or service questions.

Answer using information in these locations and files." I want to give the agent access to the specific knowledge to inform its responses.

I can either hit the plus sign or use a forward slash to reference content for this agent to use as it answers questions, so I'll use the forward slash and use this SharePoint site where we already store official documents and files.

Now we'll use the plus sign to add more content, such as files, meetings, chats, and more.

Now the site and file will be the only information used for the agent's responses, and when I hit send, this will take a moment to run, but what's impressive is Agent Builder interprets my intent, and it automatically generates an agent name, description, and detailed instructions for how the agent should behave.

It also added skills, knowledge, and suggested prompts that I'll cover in a minute.

So right now, the agent can answer questions in chat with defined and approved expert knowledge.

I'll type, "You are a new staff onboarding agent to help answer questions about business processes, how to perform common tasks, and provide answers to product or service questions.

Answer using information in these locations and files." I want to give the agent access to the specific knowledge to inform its responses.

I can either hit the plus sign or use a forward slash to reference content for this agent to use as it answers questions, so I'll use the forward slash and use this SharePoint site where we already store official documents and files.

Now we'll use the plus sign to add more content, such as files, meetings, chats, and more.

Now the site and file will be the only information used for the agent's responses, and when I hit send, this will take a moment to run, but what's impressive is Agent Builder interprets my intent, and it automatically generates an agent name, description, and detailed instructions for how the agent should behave.

It also added skills, knowledge, and suggested prompts that I'll cover in a minute.

So right now, the agent can answer questions in chat with defined and approved expert knowledge.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.