Monroe

Core concepts

Skills

Shipping in stages. Confirmed skill capture is live today. Monroe uses corrections in-thread, spots repeated patterns, and asks before saving anything durable: remember a preference, update the firm playbook, keep a checklist, or set up a recurring workflow. The dedicated Dashboard → Skills tab for inspect/edit/disable/delete + the imported-skills marketplace are on the public roadmap for the next release. Today the way to inspect or clear a skill is to use a DM ("what have you learned for #acquisitions?" / "forget that we always include the price per square foot in deal summaries").

A skill is a learned procedure Monroe remembers across sessions after your workspace confirms it. Think of it as "how Monroe does X for your team specifically."

Examples:

  • "How we write IC memos": after repeated corrections, Monroe can propose saving the section order, tone, and exhibits you prefer. Approve it, and the next memo uses that format.
  • "Which deals get the full workup": tell Monroe to remember the buy-box criteria that earn a full underwrite instead of a quick screen.
  • "How we triage inbound OMs": Monroe can turn an approved pattern into a checklist or recurring workflow for asset types, priority labels, and channel routing.

How skills get created

Three ways:

  1. Suggested from patterns: after Monroe sees a durable correction or repeated workflow, it can propose one concrete improvement. Set this up approves that exact scope; Monroe then can remember a preference, update the firm playbook, keep the checklist, or set up a recurring workflow.
  2. Explicit: say "remember this: when summarizing a deal in #acquisitions, always include the asking cap rate and price per unit if known." Monroe writes the rule down and confirms.
  3. Imported: workspace admins can clone skills from a marketplace or another workspace (Enterprise feature, Q3 2026).

Inspecting and editing skills (roadmap)

Today: use a DM to see what has been learned, or tell it to forget a rule. When the Skills tab ships, every skill will have:

  • A name (Monroe assigned, you can rename)
  • A description (what it does)
  • A scope (which channels/tools/contexts it applies to)
  • A history (when it was created, when it was last used)

You will be able to edit the description, narrow the scope, disable a skill, or delete it. Deleting is a one-way operation. Monroe forgets that procedure entirely.

Skills vs system prompt

Skills are different from a system prompt:

  • System prompt is the same for everyone using Monroe.
  • Skills are workspace-specific procedural learning. Your Monroe's skills aren't shared with anyone else's Monroe.

If two skills conflict, the more specific one wins (e.g. a rule scoped to #acquisitions beats a workspace-wide rule in #acquisitions).

Next → run log.