Code Reviewer @Review
Reads a diff like a staff engineer and says the hard thing
PresetHireFeatures
Everything your team needs, and one teammate that uses all of it
Two halves, and they are not separate products: the places your team works, and the AI teammate that works inside all of them. Nothing below is a roadmap item or a beta - it is live for every workspace today.
- 14-day Start-up trial
- 1,000 AI credits included
- No credit card
Agents
Everything your team’s AI can be
Teammates with a brief, saved commands your whole team can run, panels that add a new surface, and the models behind all of it. 285 in total, and nothing to configure.
Search presets...Presets99 Commands120 Tools29 Models37
All Engineering Security Product Design Data Research Marketing Writing
99 presets
System Architect @Architect
Designs the system you need now and names the trade-off out loud
PresetHireDebugger @Trace
Hunts the root cause instead of guessing at the symptom
PresetHirePerformance Engineer @Perf
Measures before it optimises, then makes the slow thing fast
PresetHireTest Engineer @Harness
Writes the tests that would have caught it, not the ones that pad coverage
PresetHireDevOps Engineer @Pipeline
Keeps the build green, the deploy boring, and the rollback one command
PresetHireThe places your team works
Team chat
Channels and voice rooms. The AI reads all of them.
Tasks
Board and list, topics, labels. Assign one to @AI.
Docs
Collaborative pages the AI writes and edits in place.
GitHub-native
Commits feed the AI’s context. Pull requests come back.
Multiplayer
Claude Code, Cursor or Codex join over MCP. Same board.
Polls
Ask the team in chat. One line, and everyone clicks an answer.
Huddles
Voice, video and screen-share. The AI writes it up.
And the teammate that works in all of them
Coding Agents
A cloud agent works your repo and opens the pull request.
Shared memory
Everything it does becomes the next turn’s context.
Voice-to-voice
Press ⌘O and talk. The workspace is already in context.
Self-learning
Agents read the instructions your team wrote - and propose new ones as pull requests you review.
Deep Research
Searches the live web for what the workspace doesn’t hold.
Commands
Save any prompt as a command. Run it, or schedule it.
Ambience
Fact-checks comments and flags decisions that clash.