Editorial research, delivered to Slack
I designed the selection algorithm and built the complete Apify Actor in TypeScript. It researches 20+ entertainment websites and delivers the top 10 stories from the past 24 hours directly to Slack.
The editorial team uses it daily, saving time on research and story selection.
Workflow
Gather news
Collect recent entertainment coverage from the source websites.
Rank the candidates
Evaluate relevance, group related coverage and remove duplicates.
Prepare research briefs
Draft Czech summaries and suggested headlines, preserving links to the original reporting.
Send to Slack
Deliver the shortlist and research briefs in one consolidated card.
These are research briefs, not published articles; editors control story selection, writing and publication.
The brief
Netflixer.cz covers streaming and entertainment for Czech readers. This project runs independently of Glow. A GitHub pipeline triggers the containerized Apify Actor daily, using Gemini for AI evaluation.
Algorithm and operation
- Layered selection
- I designed the algorithm around semantic analysis, AI evaluation, grouping, clustering and deduplication, incorporating the editorial team's domain knowledge. I continue to iterate on and optimize it.
- Daily operation
- It currently requires no routine manual maintenance. I continue to improve the algorithm separately from its daily operation.
- Reader relevance
- Ranking favors streaming updates and Czech relevance, while downranking corporate and political news outside the editorial focus.
Let's talk about what you are building.
Have a question about Glow, a workflow you want to discuss, or a product engineering opportunity? Tell me what you have in mind.
The hello is written. The rest is yours.
hozaksebastian@gmail.com
Webmail may ask you to sign in. Mail app requires a configured email application.