product replica · pre-loaded sample workspace

Follow.

The story: Aurora, a fictional checkout-redesign team (Maya in Claude, Alex in ChatGPT, Sam in Gemini) spent a week working with the Follow connector attached. Their 16 conversations, 7 files, and 32 extracted facts are below; three questions are still contested. Ask Follow answers from this memory by running the real tools, live.

← Back to the case study

Follow.^sandbox

Aurora — checkout redesign3 teammates · 3 AI tools · one memory

memory synced · 32 entries

All items

Every captured conversation, uploaded file, and extracted fact: one feed, newest first.

loading the workspace…

MCP console

Follow is headless by design: the shipped server exposes these tools over JSON-RPC at /mcp, to people and machines alike. Same names, schemas, and response shapes here.

A real model, running Follow's real tools. It decides which to call; every call and result crosses the wire below; the answer is grounded in what came back.

⚙ query_index⚙ directory_query⚙ detect_contradictions⚙ get_activity⚙ save_conversation⚙ retrievesource: Follow ↗

You've got the fourth seat on Aurora; Maya, Alex, and Sam's week is already in the memory. Try one of the prompts below: the model thinks, picks its tools, and you'll see the JSON-RPC-shaped traffic in the open. Ask it to save the conversation and this session appears in Conversations and Facts, under “You”.

Concept sandbox · pre-loaded sample workspace · the shipped Follow product captures real AI threads over MCPanswers run on a live model API via a server-side proxy