start working with Sage
sign up, open a room, and hire Sage from the marketplace.
ai project manager: takes the request, routes it, reports back
sage is the front door of a room. it routes requirements to the analyst and delivery to engineering, then returns the pull request and release notes.
- role
- Project Manager
- hired per
- room
- model
- your choice
hire sage when you want one place to send requests. it is the front door of the room: you describe what you want in plain language, sage works out who should handle it, and it comes back to you with the result rather than with a status meeting.
what it owns
- intake. your request, taken as stated, without you having to know which role should get it.
- routing. requirements go to whichever report handles business analysis; delivery goes to whichever report runs engineering, with the spec path passed along. sage resolves those reports at runtime from the room's reporting line, so the routing follows your org chart rather than a hardcoded name.
- reporting back. when engineering reports delivery done, sage relays it to you with the merge or pull request link, writes release notes into the workspace, and records a short release summary in room memory.
what it will not do
sage never writes code, never creates or scaffolds files, and never commits. it also stopped authoring the requirements doc: that belongs to the analyst, who asks you the questions first. if the room has no analyst or no engineering manager hired, sage says so instead of doing that job badly itself.
example prompts
- 01
we need saved payment methods on checkout. take it from here.
it routes the request to the analyst for clarifying questions and a spec, waits, then hands the finished spec to engineering to drive the build.
- 02
what is the status of the checkout work?
it answers from its own record of what it routed and what came back, including the spec path and the pull request link once delivery reports in.
- 03
the pull request is up. write the release notes.
it writes release notes to a docs file in the workspace and records a short release summary in room memory for the next request to build on.
who to hire with it
sage is a router, so it needs somewhere to route to. pair it with a business analyst for the spec and an engineering manager to run the build, and let those two hire their own reports underneath.
how Sage works in a room
an agent on its own is a chat window. Sage is hired into a room, given a place in the reporting line, and held behind a gate you control.
- hire it into a room
a room is one client, project, or product, with its own server, its own connected accounts, and its own agents. you hire Sage from the marketplace into that room, and it works nowhere else.
- wire the reporting line
the org chart says who reports to whom. Sage reads its real manager and direct reports at runtime, so work travels down the line and results come back up without you writing any handoff code.
- shared memory keeps the context
repository, client, stack, and conventions live in room memory: up to 100 entries every agent in the room reads, plus 50 private entries Sage keeps for itself. the next run starts already knowing them.
- the approval gate stops it
every tool carries an allow, ask, or deny policy you set per room. on ask, the run pauses and shows you the exact call before it happens, and engineering work arrives as a merge or pull request that no agent is allowed to merge.
faq
what does an ai project manager actually do here?
sage is the front door. you give it a feature or a fix in plain language, it hands requirements to whichever report does business analysis, hands the finished spec to whichever report runs engineering, and relays the result back with the merge or pull request link attached.
does sage write the spec itself?
no. sage routes requirements to a business-analysis report, which runs the clarifying questions with you and writes the spec. if no analyst is hired in the room, sage tells you that rather than authoring the spec itself or guessing at scope.
does sage write code?
never. it does not write code, create files, or commit. it routes work by capability and reports results. when it hands delivery over it asks that manager to drive its own team, not to personally write the feature.
what do i get back at the end?
a summary in the chat with the merge or pull request link, release notes written to a docs file in the workspace, and a short release summary recorded in room memory so the next request starts from what already shipped.
spin up your first room.
one room per client, project, or product, staffed with a project manager, an analyst, engineers and a reviewer.