SIGNAL INDEX / 001
I’m LIU, a product manager and AI-collaborative builder. This index shows how I use judgement, prototypes, and evidence to move AI products forward.
View product experiments01 / FOCUS
Making agent search deliver verifiable, traceable answers.
Turning collaborative memory into a durable personal workflow.
Making product judgement, prototypes, and evidence open to discussion.
02 / PROJECT SIGNALS
Three evolving product problems, each with a judgement, prototype, and evidence trail.
Search infrastructure that agents can inspect and control
The decision was not to find a cheaper search API, but to treat search as a product capability with multi-source verification, progressive disclosure, and replaceable engines.
An external-PR investigation that scanned 93 open-source agent projects selected it as an architecture-validation case in the MCP search category.
Reversible MCP context compression
Reduce the context an agent receives first while preserving selected arguments, one upstream call, and exact recovery.
Across a frozen set of 12 tools and 24 bilingual tasks, normal-path tokens fell from 71,388 to 17,007; all 24 tasks completed with 24 upstream calls.
Make AI collaboration persist beyond a single session
Treat documentation, handover, and reusable skills as product information architecture rather than post-delivery paperwork.
The practice record covers trajectory mining across 196 sessions and turns the learning into reusable skills and a maintenance loop.
03 / TRANSMISSIONS
Recently updated methods, validation results, and boundaries from active product experiments.
04 / OPERATOR
I care not only about whether AI can produce an answer, but how people frame the problem, verify the result, and retain final judgement.
Read the full profile