Research

The ideas behind Tase

Thesis-style essays on the design principles that shape a personal assistant: capture, memory, action, and voice-first interaction.

Methodology

Voice as the Right Default: Why a Personal Assistant Should Speak and Listen

Text is a legacy interface for a personal assistant. Voice is the right default for most interactions, not because it is more impressive, but because it matches how thoughts actually form and when help is actually needed.

5 min read

Insight

Act, Do Not Just Answer: The Case for an Assistant That Takes Action

A chatbot tells you how to do something. An agent does it for you. The difference sounds small in a demo and is enormous in practice. Here is why action, not text, is the real threshold for a useful assistant.

5 min read

Methodology

Designing Personal Memory: What an AI Should Remember, Forget, and Let You Correct

A personal AI memory is not a database of everything you ever said. It is a curatorial system that decides what is worth holding onto, what should expire, and how you stay in control of what it thinks it knows about you.

5 min read

Insight

The Capture Gap: Why Most Task Systems Fail at Step Zero

Every task manager obsesses over organization. Almost none solve the moment that actually decides whether a task exists at all: the instant you think of it. Closing that gap is the highest-leverage habit in personal productivity.

5 min read