Agent memory isn't one thing: sessions, wiki, procedural, and the forgotten 'judgment' layer

sujingshen · x · 2026-09-16

Responding to Pat Erichsen's article on the "memory trifecta" for personal agents, the author argues that saying "I added memory to my agent" is meaningless without specifying the layer:

Most products lump all three into one toggle. The author adds a fourth layer most people miss: judgment memory — why you rejected a proposal, what counts as "good enough." Systems often stuff this into chat summaries, and once summaries compress, the judgment is gone.

Self-check: run the same scenario (e.g., prepping a meeting) against all four layers; missing one means it isn't a real personal AI.

Original post →

More from coding & agent

coding & agent channel →