An episode review and approval tool for a podcast agency, with quality checks before the client sees anything
Clients watch, comment on and approve every episode and asset in one place, with automatic quality checks first.
We built Fame a review tool where clients watch, comment on and approve each episode, clip and graphic, with automatic checks that catch common mistakes before a client sees them. Producers and editors get one place for feedback instead of chasing it. Main result so far: 1,314 automatic audio quality checks run before assets reached clients (to 7 October 2026).
Who we built it for
Fame is a B2B podcast agency that has been running for six years. Its team finds and books guests, produces episodes and promotes each show for around 100 clients, and Fame Crew finds local videographers for shoots and handles the editing. Team size: about 97 people (estimate), most of them freelancers and contractors. Fame is Forge's own sister company, so we built these tools for ourselves first and still run every one of them.
Who uses it: producers, editors, clients.
Feedback was scattered and nobody checked the basics twice
Every episode produces several assets: audio, video, clips, artwork, show notes. Feedback came back by email, in Drive comments and on calls, and producers stitched it together before editors could act. Approval was whatever the last email said.
Small mistakes, like a wrong name on artwork or the wrong audio file, were caught by people eyeballing them, if at all. Producers spent around 45 hours a week between them collecting and untangling feedback (estimate).
One review page per episode, with checks that run first
Timestamped comments
Clients comment at the exact moment in the audio or video, and editors jump straight to it.
Versions and approvals
Each new cut is a new version; the client approves a specific version, so there is no doubt what was signed off.
Automatic quality checks
Before a client sees an asset, AI checks transcripts, names and artwork for common mistakes and holds anything that fails. A person reviews every flag.
Hooked into the team's tools
Approvals and comments post to the team's Trello cards and Slack, so nobody has to go looking.
What the producers and editors used before
Feedback by email, Drive comments and calls, stitched together by producers; approvals confirmed by email.
Monthly cost of what came before: £120 a month (estimate)
What changed for the producers and editors
How we look after the asset review and approval tool
Forge built this for Fame and looks after it: errors are reported automatically to an error tracker, and anything that stops someone doing their job is fixed the same day.
The quality checks are tuned as real mistakes turn up: when one slips through, we work out why and change the check, then say what we changed.
What broke, and how we fixed it
- September to October 2026: The wrong episode audio was published to one show's podcast page. The upload to the podcast host happens outside the review tool, and the check meant to confirm the audio matched the episode almost never finished in time, so it was quietly skipped. We added a retry so the audio check runs once the video arrives, made every dismissed warning require a written reason, made wrong names on artwork block the asset, and added an audit log of what each client saw. We then built a separate feed watcher that checks what actually went live.
What it's built with
- Next.js
- Vercel
- Upstash Redis
- Mux
- AssemblyAI
- AI vision models
- Trello API
- Slack API
- Google Drive API
Connects to: Mux, AssemblyAI, Trello, Slack, Google Drive.
What it would cost a client today
Start with the 2-week ops audit ($2,500 / £2,000, credited to your first month). A tool like this then fits the embedded plan at $7,500 / £6,000 a month, with this as the first build included. A review tool with video, transcripts and AI checks becomes part of how every piece of work ships, so it fits embedded, with a continuous backlog and same or next-day turnaround on changes.
Plans have a 3-month minimum. AI usage is passed on at cost, and the tool runs on your own accounts, so you own it. See pricing for the full breakdown.
Would this work for your firm?
If your clients sign off creative work - video, audio, design, copy - and feedback arrives from everywhere, a review tool gives your producers that time back. It suits most creative and content agencies.
See what we build for agencies, or read about our AI implementation work.
Questions about building a asset review and approval tool
Why build an approval tool instead of using an off-the-shelf one?
Off-the-shelf tools handle comments and versions. Fame's also runs its own quality checks and posts to the team's Trello and Slack, which is where most of the time is saved.
Do the AI quality checks make the final call?
No. AI drafts, people decide: the checks flag and hold, and a person reviews every flag. Dismissing a warning needs a written reason.
What happens when a check misses something?
We treat it as a bug in the check, find out why, fix it and add a guard. The incident above is a real example.
Who owns the tool once it's built?
You do. It runs on your own accounts and you pay those tool costs directly; we monitor it, fix it and keep improving it on the monthly plan.
Want a asset review and approval tool shaped to your firm?
Start with a 2-week ops audit - $2,500 / £2,000, credited to your first month.