Studio

We keep the cache honest so the experiment can speak.

Cache Nodecore started as a reading group for Bangkok product analysts who were tired of weekly “wins” that vanished after a store release. The name is literal: node-level telemetry and client caches kept rewriting the story after assignment.

Quiet office interior with long wooden tables and daylight

Mission

Teach mobile product organisations in Thailand to treat experimentation as a record, not a performance. A good readout names what the test cannot claim. A poor readout dresses a cache artefact as a conversion lift.

We work with teams who already have flags, analytics vendors, and a backlog of disputed charts. We are not a replacement for those tools. We are the room where the tools are cross-examined.

Pedagogy

Every session begins with an artefact from the team: an exposure log, a metric window, a screenshot of a “significant” dashboard. Fellows annotate in silence first, then argue in a fixed order — assignment, observation, limitation.

We do not grade enthusiasm. We grade whether the limitation was written before the headline. That habit travels back into stand-ups more reliably than a new vendor.

People

Who holds the desk.

Portrait of Apinya Sutham, studio director

Apinya Sutham

Studio director · Signal Lab lead

Former instrumentation lead at a Bangkok super-app. Apinya designed Signal Lab after watching three consecutive “onboarding wins” collapse once the CDN TTL was shortened.

Portrait of Daniel Rojana, metrics tutor

Daniel Rojana

Metrics tutor · Cohort Grammar

Daniel came from a payments analytics desk. He is the person who will stop a session if the denominator quietly changed mid-test. Fellows find this either clarifying or mildly infuriating.

Colleagues talking around a conference table

Community and the student journey

A typical path starts with a written note to the desk, a short diagnostic call, then either Cohort Grammar or Signal Lab. After the cycle, alumni join a monthly ledger hour — not a networking mixer, a shared reading of one anonymised experiment from a Thai release calendar.

We keep the room small. Eleven organisations is already a full ledger. If we decline a cohort, it is usually because the team does not yet log exposure at user level, and we would be teaching theatre.

Ask whether your team is ready