Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Jesse logo

Jesse

An AI assistant built from a folder of text files. No product, no account, no lock-in.

You own the files. The agent does the legwork. Nothing gets sent without your sign-off.

Set it up in 10 minutes See how it works

Your day is probably spread across a handful of apps – email, calendar, Slack, a task list, for example, though everyone’s mix is different. Whatever tools your agent can reach, Jesse gathers what’s new, sorts it by what actually needs you, and hands you one briefing.

An example morning briefing

morning briefing
📅 Calendar -- Today
- 10:00 AM -- 1:1 with Sarah (prep: review her project update from Friday)
- 2:00 PM  -- Team standup
 
📧 Email -- 6 new
🔴 Needs response today: Client asking about timeline for deliverable
🟡 This week: Vendor sent contract for review
🟢 FYI: 4 automated notifications
 
💬 Slack
- @mention in #projects -- someone asking about deploy schedule
- DM from manager with a question about budget
 
🔔 Reminders
- Follow up with Alex on proposal (set 3 days ago)

You scan it, correct anything it got wrong, and start your day already caught up. Behind that briefing, Jesse has also updated your task list, prepared agendas for today’s meetings, and acted on any notes you dropped in from your phone.

How it works

Instruction file your rules and routines Your tools email, calendar, chat, whatever you use AI agent any one you choose Your vault markdown files, Jesse's memory reads writes remembers You one briefing, drafts to review, nothing sent without approval

Three parts, each one you can open and read:

Memory

The vault

A folder of markdown files: your tasks, projects, people, notes. The agent starts every session fresh; the vault is what persists. You can read every bit of it in any editor.

Process

The instruction file

One file (JESSE.md) that tells the agent who you are, what your rules are, and what to do each morning. Every time it gets something wrong, you tighten a rule.

Engine

The agent

Any AI agent that can read files and call tools -- Claude Cowork and Claude Code work out of the box. Switch providers tomorrow and the vault comes with you.

Why people trust it

Drafts, never sends

Jesse writes replies and messages into a drafts folder and waits. Nothing leaves your outbox without your explicit approval.

Plain files you own

No database, no export button, no subscription. Markdown in folders, versionable with git, readable in twenty years.

You make the calls

Jesse surfaces, flags, and drafts. It shows its judgment calls so you can correct them. It doesn't decide strategy or commit you to anything.

Not a Product

There’s nothing to install, no account to create, nothing to pay for. Jesse is a method: a vault structure, an instruction file, and a set of patterns for working with an AI agent, refined through months of daily use. Copy the template, point your agent at it, and make it yours.

It was built to solve a real problem – managing the daily overhead of a demanding workload without adding yet another app to the stack. Read the full story in the blog post on Tag1’s website.

Where to Go Next

  • How Jesse Works – the mental model, a morning traced end to end, and the safety design.
  • Quick Start – copy the template and run your first session in about 10 minutes.
  • Recipes – add capabilities piecemeal: email, Slack, meeting agendas, research, reminders, and more.