Core concepts

AI Employees

An AI Employee is a persistent persona attached to a company. They have a name, a role, a model, a sandboxed working directory, and three editable pieces of prose that define who they are and how they work.

Anatomy

Every AI Employee row carries the fields you can configure from the UI plus a few the runner needs at spawn time:

name + slug
Display name (you can rename) and slug (frozen at create-time so URLs and directory paths stay stable).
role
A short role string — Brand writer, Bookkeeper, On-call SRE.
soulBody
Markdown stored on the row. The employee's constitution — see Soul.
skills[]
One-to-many Skill rows. See Skills.
routines[]
One-to-many Routine rows, managed from the top-level AI → Routines section. See Routines.
model
One or more AIModel brains, one active at a time. See AI Models.
reportsTo
Optional pointer to another employee for an org chart. Used for handoffs.
browserEnabled
Flips on the built-in browser MCP server that drives a headless Chromium. Off by default.

Lifecycle

  1. Create. Pick a template (a starter Soul + Skill set) or start blank. The slug freezes; you can rename freely afterward.
  2. Write the Soul. The app drops you into the Soul editor with a seeded constitution. Rewrite it to fit your team.
  3. Attach a model. Pick a provider, add an API key or custom endpoint, and the runner takes over from there.
  4. Add skills + routines. Skills describe what they know; Routines describe when they work.
  5. Fire. Deleting an employee removes their DB rows, including the encrypted credential row for every model they held. There's no shared key to revoke.

Working directory

Each employee gets their own folder on disk under the company:

data/companies/<co-slug>/employees/<emp-slug>/
└── ...   # files the employee's coding tools read and write

The runner starts an in-process agent loop with this directory as cwd for the built-in coding tools (bash, read_file, write_file, edit_file, glob, grep), and captures the agent transcript into a Run log. Two employees can run different models in parallel; their provider credentials are stored encrypted in the database, never on disk.

Org chart

Set reportsTo on an employee to give them a manager. Genosyn renders this as an org chart and surfaces it to the runner — useful when you want a Handoff from one employee to another to follow the reporting line.

Surfaces inside the app

  • Chat. Free-form conversations with the employee. Messages persist; action pills surface tool calls inline.
  • Workspace. File editor scoped to the employee's directory — read what they wrote, edit it, drop in fixtures.
  • Soul. The employee's constitution, under Settings. Markdown, ⌘S to save.
  • Skills / Routines. Not employee tabs anymore — they live in the top-level AI → Skills and AI → Routines sections. Each sidebar link opens that list filtered to this employee.
  • Connections. The list of Grants this employee holds.
  • Journal. Append-only diary the employee writes about their own work via the built-in MCP server.