Original content, integrations and a site the client runs
Store AI summaries, display feeds
- Problem
- The site needs fresh content every day across 32 sports with no editors, and importing third-party feeds would create duplicate content at scale (200K+ posts in three months).
- Decision
- AI-written sports summaries are stored and indexed; third-party video and news feeds are displayed but not stored, and open in pop-ups so viewers stay on the site.
- Trade-off
- Feeds add freshness but no search value; AI summaries need prompt tuning.
- Said no to
- Importing every feed item as a post.
- Worth it because
- Original summaries build search presence while feeds keep the site current.
Using existing tools for streaming and listings
- Problem
- A 24/7 channel, live listings and video on a five-week clock.
- Decision
- The channel runs on an existing stream with its TV programme guide, plus YouTube live and playlists and a third-party TV-listings widget.
- Trade-off
- Dependence on outside providers.
- Said no to
- Custom streaming infrastructure.
- Worth it because
- Live in five weeks, on proven tools.
Built for the client to run
- Problem
- The client wanted to manage the site himself after launch.
- Decision
- A visual page builder instead of a custom-coded theme, and one master sport-page template (20 sports pages that differ only by their banner), plus training and video walkthroughs.
- Trade-off
- Less design freedom than custom code.
- Said no to
- A custom theme only developers can change.
- Worth it because
- The client adds and updates sports pages without us.
Planned for eight weeks, live in five
We kicked off on 16 October 2025 against an eight-week plan and went live in five weeks. We didn't cut scope to get there. The time came from a strong delivery team, AI-assisted development, and using existing tools for streaming and listings. The homepage leads with the 24/7 live player and the channel's programme schedule.
How the AI news reaches the site
We built a review panel for the client's team. Every AI sports summary arrives there first, and at launch the team reviewed each one before publishing it. How many arrive each day depends on how much sports news there is. After we tuned the AI on the client's feedback, the team told us they no longer need to check each summary before it goes live.
Live in five weeks and run by the client
- Live in five weeks, against an eight-week plan.
- A 24/7 live channel and sports news across 32 sports.
- 20 sports pages from one master template.
- Handed over: the client manages the site on his own.
- SportsOnTV now reports 200+ broadcast partners and 1M+ monthly viewers.
Partner and viewer numbers as reported by the client.
After launch: what we changed
- Feedback
- The client wanted the AI sports news to read better.
- Change
- When we shared the first AI summaries, the client said they weren't what he was looking for. I went through the AI's guidelines and instructions and shared what needed to change; the team made the changes, and the client approved the new output.
- Why it mattered
- Better summaries are what bring visitors back and build search traffic.
Set traffic goals at kickoff
Success was defined as “looks established” and “the client can run it himself”, and both were met. I'd also agree measurable targets at kickoff (sessions, time on site, returning visitors), so the next round of work is driven by data.