Replit Agent builds a podcast companion site
Warwick Brown reports building and deploying The KAM Club podcast site with Replit Agent, including RSS imports and episode companion features refined over a weekend.
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Build a podcast companion site from this authorized RSS feed. Import episodes, prepare source-linked companion content and keep chat within episode themes. Deploy a preview and list unverified integrations for my review.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source author
- Warwick Brown / warwickabrown
- Original account
- Read the source ↗
- Published
- 22 Jul 2025
- Source link checked
- 15 Oct 2026
- Reported result
- Warwick Brown reports building and deploying The KAM Club podcast site with Replit Agent, including RSS imports and episode companion features refined over a weekend.
- Human involvement
- Brown directs revisions and tests the deployed experience. Most architectural detail is a published agent briefing, not an independently audited implementation.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Brown briefs Replit Agent on a podcast companion website and iterates over a weekend.
- The project imports RSS episodes and prepares transcript and companion-content features.
- Brown asks the agent to restrict episode chat to related themes.
Warwick Brown built and deployed a website for The KAM Club podcast with Replit Agent. He describes a weekend of back-and-forth revisions before the result matched what he wanted, and links the working site from his forum account.
The published agent briefing describes a React frontend, an Express backend and a PostgreSQL database. The site imports episodes from the podcast RSS feed and prepares companion material such as transcripts, tags and show notes. The briefing names AWS Transcribe and different OpenAI models for analysis and episode chat, but its performance and cost claims are not independently verified results.
A follow-up comment supplies a concrete design correction. Brown asks Replit to keep episode chat focused on episode-related themes rather than answering arbitrary requests. He also reports that the site can email a formatted transcript of the conversation with a link to the source episode.
The useful outcome is a deployed podcast companion site with owner-directed refinement and a visible discussion of scope control. The article does not prove that every listed integration, access-control claim or compliance statement works as described. The long agent-generated feature list should be read as the builder's supplied project briefing, not an external security or production audit.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: replit.discourse.group · Warwick Brown / warwickabrown
Frequently asked questions
Was the site built in one pass?
No. Brown reports a weekend of back-and-forth revisions.
How was chat scope limited?
He asked Replit to answer episode-related questions while refusing unrelated topics.
Are the supplied cost and security claims independently checked?
No. They appear in the published agent briefing and are not an external audit.
More details
Remaining steps
- He reports a deployed site and formatted chat-email output linking back to the source episode.
About this account
Replit Agent built the podcast site and implemented owner-requested changes to episode-focused chat and transcript email formatting.
Firsthand account opened and read. Outcome is source-reported, not independently reproduced. Suggested prompt written by Agents In Use. Human-confirmed deployed site; agent-generated feature briefing does not verify cost, security or compliance claims.
Credit: Warwick Brown / warwickabrown
Source published 22 Jul 2025
Source checked 15 Oct 2026
Tools and topics
Replit Agent · React · Express · PostgreSQL
Replit Agent · React · Express
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.