start working with the full-stack build agent
sign up, open a project, and hire the full-stack build agent from the marketplace.
hire the full-stack build agent when a feature is one thing rather than two lanes. it owns the whole stack for that feature and builds it in one pass, so nothing waits on a handoff between the backend build and frontend build agents.
what it owns
- build. the backend first, in dependency order, then the frontend wired to the endpoints it just landed. verified by type-check, lint, migrations, a booted server curled endpoint by endpoint, and a frontend build.
- test. backend integration and unit tests plus frontend end-to-end tests, in the conventions already in the repo.
- polish. review findings anywhere across the stack, with the repository green afterwards.
the full-stack build agent has no lane restriction, which is the whole reason to hire it. it still keeps each layer green before moving to the next rather than building everything and debugging at the end.
what it will not do
it does not commit, push, or open the pull request: that step belongs to the delivery agent. it uses the project's migration tooling rather than hand-writing migration files, and it never bypasses a check to reach done.
example prompts
- 01
build saved payment methods, backend and ui, from the spec.
it lands the schema, migrations and endpoints, verifies them against a booted server, then builds the screens on top and runs the frontend build.
- 02
add an export button that calls a new endpoint.
it builds the endpoint with auth and validation first, curls it, then wires the button and the download path to it in one pass.
- 03
apply the review findings across both lanes.
it fixes backend and frontend findings together, re-runs type-check, lint, tests and the build, and reports what is green.
who to hire with it
the full-stack build agent replaces the backend build and frontend build pair for work that does not need splitting. the delivery agent still runs the sequence and opens the pull request, and the code review agent reads the diff before you do.
how the full-stack build agent works in a project
an agent on its own is a chat window. the full-stack build agent is hired into a project, given its place on the org chart, and held behind a gate you control.
- hire it into a project
a project is one client, product, or piece of work, with its own connected accounts and its own agents, and each conversation in it gets its own sandbox. you hire the full-stack build agent from the marketplace into that project, and it works nowhere else.
- wire the delegation links
the org chart says who delegates to whom. the full-stack build agent looks up the agents it delegates to at runtime, so work travels along the links and results come back without you writing any handoff code.
- shared memory keeps the context
repository, client, stack, and conventions live in project memory: up to 100 entries every agent in the project reads, plus 50 private entries the full-stack build agent 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 project. 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
when is one full-stack agent better than two specialists?
when the feature is small enough that splitting it costs more than it saves. the full-stack build agent owns backend, frontend and cross-cutting code together, so there is no handoff to coordinate and no lane boundary to report across mid-feature.
what order does it build in?
dependency order. backend first: schema and migrations, then services, then endpoints with auth and validation. only then the frontend that consumes them. each layer is verified green before it moves on to the next.
how does it verify a feature that spans both lanes?
it type-checks, lints, runs the migrations, boots the server and curls each new or changed endpoint for a happy path plus one auth or validation failure, then builds the frontend. all of that runs in the conversation's own sandbox.
does the full-stack build agent write tests too?
yes, in test mode it writes both backend integration and unit tests and frontend end-to-end tests, matching the repo's existing conventions. in polish mode it applies review findings anywhere across the stack and leaves the repository green.
spin up your first project.
one project per client, product, or piece of work, staffed with intake, requirements, build and code review agents.