How Jot works · a blueprint you can copy

Speak it.
Agents do it.
Jot remembers it.

One voice request becomes real work on your own computer. The context stays for the next conversation.

The whole system on one page

Three places, five parts

Phone ⇄ server: seconds, while you talk
Server ⇄ computer: minutes to hours, in the background
The key idea

A tool server is the bridge

What ChatGPT sees: a tool menu

MCP (Model Context Protocol) is the standard plug. Each tool has a name, a plain description and fields. ChatGPT picks the tool from the description.

Why this shape

Safe: your computer only calls out Reliable: jobs wait if the computer is off One record of everything Swap ChatGPT or the agent
The server does not think, and it does not do the work. It stores and passes on. So it stays small.
Idea 1 · Voice first

One spoken request, from start to finish

Idea 2 · A second brain

Every chat starts with what Jot remembers

Kept in Jot

  • Project pages and notes
  • Decisions and corrections on jobs
  • Every job: brief, report, files
  • Project rules that each agent gets
  • Old versions of each note

Only in ChatGPT

  • The current conversation
  • ChatGPT's own memory. Agents never see it.
  • Anything that no tool call saved
Rule: if it matters later, save it to Jot. A new chat reads it back with a tool call.
Idea 3 · Code jobs

Each code job gets its own branch and folder

job 57 · branch bd57 · own folder job 58 · its own branch, at the same time main GitHub if the project has it 1 new branch + folder 2 agent edits + commits 3 checks 4 merge 5 push job 57 job 58 main GitHub if the project has it 1 new branch + folder 2 agent edits and commits 3 checks 4 merge into main 5 push
Local commitin the job's own branch, on your computerevery code job with changes
Jot uploadreport, screenshots, files to the serverevery job
GitHub pushthe merged main, not the job branchonly at merge, only with a GitHub remote
Build your own

The map: buy two parts, build three

Build order

1Jobs: add_job, get_job
2Runner + one agent, one folder per job
3Results back: ask “how did it go?”
4Memory: write_note, read_note
5Code: branch per job, checks, merge
The whole idea: a voice front door, a shared memory and queue in the cloud, and workers on your own computer.

Speaker notes