Personal agents all feel the same; the moat is learned judgment, not connectors

sujingshen · x · 2026-09-29

Reviewing openclaw, Poke, Manus, Grok bot, Instinct and Town, @zwayai finds personal agents highly commoditized: all are scheduled tasks + connectors around email summaries, calendar management, meeting notes and weekly reports — with four agents now summarizing the same Gmail daily. The four ingredients for a good personal agent: long-term memory, rich context, personality, and proactivity — with proactivity the hardest and currently unsolved. Reposter sujingshen adds that connectors will become utilities; the real differentiator is the judgment an assistant accrues over time (which emails not to answer, which payments not to make) and whether it can migrate between products.

Original post →

More from coding & agent

coding & agent channel →