All insights
AI Product Building AI Agents Future of AI

Personal software grows through relationship, not configuration

Unlike traditional SaaS where users adapt to the tool, personal software agents grow personality and skills in response to their user through ongoing interaction

@danshipper (Dan Shipper) — 'What personal software actually is' (tweet thread) · · 4 connections

Dan Shipper frames personal software not as customizable apps but as agents that evolve a personality in response to you. This is a step beyond Malleable software — a tiny core that writes its own plugins — replaces fixed-feature applications — the software doesn’t just extend itself, it develops a relationship. The user doesn’t configure settings; they guide an agent through interaction, and the agent adapts its strengths and preferences over time.

This reframes the product design question entirely. Instead of asking “what features should we build?”, the question becomes “what kind of relationship should the agent develop with its user?” — connecting directly to In agent-native architecture, features are prompts — not code where the feature IS the agent’s learned behavior, not shipped code. It also implies that Context is the product, not the model extends to personal context — the agent’s accumulated understanding of one specific human becomes the moat.