Key Takeaways
- Daniel Blum runs 70 to 80 percent of his computer time through Cowork and Claude, shrinking five days of product management administrative work into one.
- Notion serves purely as a read-only dashboard: Blum views priorities there but never edits boards or cards manually during the week.
- The setup pulls context directly from Slack, emails, calendar invites, and meeting transcripts to build automated daily briefs.
- The system rewrites its own instruction files over time, automatically learning company acronyms and project details without manual prompt tuning.
The Method
Most product managers spend their days typing updates into project boards, copying action items from transcripts, and hunting down status reports in Slack. Daniel Blum, a product manager at Melio, stopped doing that work manually.
“Today, I say I manage about 70 to 80% of my time in front of the computer with co-work alone,” Blum said. Instead of treating software tools as places to do manual data entry, he turned his stack into an automated loop with three distinct parts.
First, he automated data ingestion. Every Sunday, an automated preparation script gathers upcoming calendar events, unread emails, and recent Slack threads. Every morning, a daily brief compiles recent transcripts and messages into a prioritized summary of what needs his attention.
Second, he separated the interface from the execution. “The main idea is that notion is almost a read only for me,” Blum said. “I look at the notion to get my focus to remind me of my top of mind to remind me of my priorities and focus this week.” Cowork writes all the updates to Notion in the background. Blum checks Notion only to orient his day, not to manage tasks.
Third, he built self-improving instructions. “I think the real importance is for a system to a be able to rewrite its own core files and that means that it keeps on improving and b just have connections and integrations to as much of your tools,” Blum noted. When the AI hits unknown company jargon or changes in team structure, it updates its own background reference documents so future summaries stay accurate.
“I cannot describe how powerful it is,” Blum said. “I'm really able to do in a day now what used to take me a week and I stand behind that.”
Where This Breaks Down
This method requires clean digital exhaust. If your team makes decisions in informal hallway chats, unrecorded Zoom rooms, or private notebooks, the AI receives no signal. The system only works when project reality matches what happens across connected tools.
There is also real setup pain. Switching to an AI-driven workflow slows you down before it speeds you up. As Claire Vo pointed out during the conversation: “You got to go through the pain of switching your systems and it's not going to be as efficient. And yes, of course, the old way will be faster because it's muscle memory, but if you get to the next level, not only will you have a system that works better for you, but everybody will have more skills.”
If you abandon the setup during the first two weeks of clumsy output, you get zero return on your time.
What to Do With This
Pick one repetitive tracking document you update manually every Friday. Stop typing in it. Connect an AI prompt to your calendar and email inbox this week, have it draft the update automatically, and restrict yourself to reviewing the output rather than creating it from scratch.