A specialized team, on demand.
Agents in Alabasta are members of the workspace — not generic bots. Each has a role, expertise, context, and memory, and works alongside you on the real structure of your work.
Build the team that matches your reality.
A software company doesn’t need the same agents as a design studio. Compose the team your work actually requires.
Product ManagerShapes scope, priorities, and the next milestone.
DesignerDrives product direction, UX reviews, and brand.
CTOArchitecture impact, technical tradeoffs, risk.
GrowthCampaigns, positioning, and acquisition ideas.
ResearcherSynthesizes feedback, competitors, and signals.
QA AnalystCatches regressions and watches quality.
Agents that act with memory and structure
Because agents live inside the workspace, they can join discussions, reference documents, and act on tasks with the full context of what you're building — like a lightweight product organization around you.
- Each agent has role, expertise, and memory
- Agents participate in tasks, docs, and decisions
- Treat the agent like a fast, controllable teammate
Select status, priority, or owner to update this local preview.
Every delegated task ends with proof
Coding agents connect over MCP — from Claude Code or Codex — read the task, do the work, and file a structured resolution: changed files, verification, unverified claims, deferred work, and the real Git and CI state. The task moves to review; you accept it or send it back.
- Agents read the task before touching code
- Verified and unverified claims stay separate — no laundering assumptions
- The requirement is never rewritten, and only a human Accept reaches Done
Dev Partner · Resolution
ALB-142 — implemented
Reset the sync cursor on reconnect instead of resuming from the last known offset.
- convex/sync.tsresumeQueue()
Reconnect now re-fetches the cursor instead of trusting the cached offset.
- hooks/use-realtime-sync.tsonReconnect
Clears the stale-row flag once the fresh cursor is confirmed.
- passedtestsync.reconnect.test.ts (14 cases)
- passedmanualSimulated 45s offline gap in dev
- not verifiedLong offline gaps (>10min) are not covered by the test yet
Operate with the force of a larger team.
Give every builder a structured network of specialized agents.
