FAQ
What the focused coding-agent control plane includes — and what it deliberately leaves out
What does Fullbeam's focused v1 cover?
One closed loop: a private, versioned Harness Registry; runtime evidence tied to the exact configuration, session, commits, and pull request; and agent-aware PR Stories with review continuity. External alpha access still waits on the release gates and a real-service smoke test.
Is Fullbeam a generic engineering analytics or knowledge platform?
No. Runtime and delivery signals are included only when they help a team evaluate a Harness Pack or understand an agent-built pull request. Generic management dashboards, broad organizational profiles, and a general observability log explorer are outside focused v1.
Does Fullbeam score engineers or claim that a configuration caused an outcome?
No. Fullbeam reports observed associations with the denominator, sample size, and telemetry coverage visible. It does not turn those comparisons into causal productivity claims or engineer scores.
What is deliberately outside focused v1?
Generic DORA and SPACE dashboards, productivity scores, public builder archetypes, global benchmarks, prompt routing, leaderboards, a public prompt marketplace, and automatic bug review are not part of focused v1.
Which coding-agent integrations are in focused v1?
GitHub is the source of truth for repositories, commits, pull requests, and review outcomes. Claude Code and Codex are the two focused v1 agent adapters; broader provider coverage comes later. Missing runtime telemetry remains an explicit evidence gap rather than being inferred.
What would founder-led design-partner access cost?
There is no public launch today. After the release gates pass, selected design partners would pay $0 during founder-led alpha research. The $30-per-reviewer-seat figure is a later research hypothesis, not a live paid plan.