The CRM holds the people, companies, and deals your agents work on. It isn’t a
separate product you sync with — it’s the shared state your colonies read from and write
to as they run.
Setup
The CRM needs a one-time setup per workspace before records appear. Until that’s done,
the CRM section shows a setup prompt instead of a grid.
Inbox stays reachable whether or not the CRM is set up — the two are
gated separately, so an unconfigured CRM never hides your mail. What’s in it
Records are organized into four views:
Reading and writing
The grid is read-only. You browse, filter, and inspect records there, but you don’t
edit cells directly.
Writes happen through your agents. Ask a colony to update a record, move a deal, or load
a new set of accounts, and it writes through the CRM agent path. This is deliberate:
every change to the system of record arrives with an agent’s reasoning attached, rather
than as an untracked manual edit.
The view is projected server-side, so what you see is the business-level record —
never raw tables, internal IDs, or metadata blobs.
Where records come from
- Foundry runs — matched buyers loaded into your first open stage.
- Colonies — sourcing and enrichment work writing accounts and contacts as it
confirms them.
- Inbox — the mail bridge writes conversations back onto the
matching CRM records, so a reply shows up against the person who sent it.
