My previous memory systems failed because they required too much manual maintenance—Notion's agentic search was effortful, and my Capacities 'blips' system couldn't scale as topics proliferated.

The author tried two approaches to managing long-term story context—Notion's agent search and a 'blips' system in Capacities—but both required too much manual effort to maintain as his research expanded. ✦ AI generated

Casey Newton · Platformer · 2026-08-19 · original ↗

It worked well enough, but I couldn't turn it into a habit. The search feature in the database itself is a simple keyword-based search; agentic search takes place on one of the app's many other surfaces; and the agent often failed to cite its sources without additional prompting. It worked, but it was effortful. Ultimately, though, even this system asked a bit too much of me. As the number of blips proliferated, my ability to consistently track stories across all of them waned. This, in turn, made me more reluctant to create new blips.

Read full article ↗excerpt · fair-use quotation