Configure a podcast output

Last updated: July 12, 2026

Use a podcast when the result should be consumed as an audio briefing, recap, or narrated explanation.

Choose the output type

Open the Output step in the agent builder and choose the artifact the agent should produce every run.

The audience will listen while travelling, preparing for a meeting, or catching up asynchronously.
The output needs a spoken structure with signposting and concise takeaways.
A narrative recap is more useful than a dense written report.

Choose Podcast in the output type menu.
Specify the listener, target duration, tone, and whether it should be a solo briefing or conversational recap.
Ask the agent to avoid long tables and to summarise source-backed evidence in spoken language.

Add a short output instruction to the agent instructions or the relevant skill so the agent knows what good looks like.

Create a five-minute audio briefing script with opening context, key findings, evidence highlights, risks, recommendation, and closing recap.

The audience and use case are clear.
The output format is selected before testing.
The agent instructions describe the expected sections, fields, or scenes.
Important claims include evidence or source links.
The output can be reviewed without guessing what each field or section means.
If another system consumes the result, the schema and allowed values are stable.