Orchestration

Run multiple AI agents as one team.

Assign roles, review their work, and control what ships.

Get startedTake the tutorial
feat/retry-budget
CodeGraphAtlasTasksJobs
SCJO2
Tools
client.go
retry.go
1package checkout
2
3import (
4 "context"
5 "time"
6)
7
8// Charge sends a charge to the payments gateway,
9// retrying 5xx responses.
10func (c *Client) Charge(ctx context.Context, r Request) (*Charge, error) {
11 var last error
12 for attempt := 0; attempt < c.policy.Max; attempt++ {
13 resp, err := c.gateway.Do(ctx, r)
14 if err == nil && resp.Status < 500 {
15 return resp.Charge()
16 }
17 last = errorFor(resp, err)
18 if !c.policy.Retry(resp.Status, attempt) {
19 break
20 }
21 time.Sleep(c.policy.Backoff(attempt))
22 }
23 return nil, last
24}
AI
Chat 1

What do you want to do today?

Pick one, type its number, or describe what you need.

  1. 1Build or change somethingDesign before building
  2. 2Find and fix a problemDetect and fix issues
  3. 3Review my workChoose the project, period and evidence
  4. 4Teach meExplore RBS capabilities through guided demos
  5. 5Explore this codebaseUnderstand the architecture
Message ReasonOS
Ask: commands
Claude Opus 5
RBS
Ready
UTF-8
GO
✦ Completions
◆ Hide AI
▶ Show Explorer
⫿ Split

What you get

01

Assign roles

Give each role its own agents, models and credentials. Add independent reviewers where a second opinion matters.

02

Review their work

Every attempt, response and verdict is kept with the task, so people and later agents can check it.

03

Control what ships

Choose which decisions need a named person. Your branch rules and required reviews still apply.

Roles

Start with seven roles. Add your own.

  1. DesignProposes options and a plan for you to approve.
  2. Impact analysisFinds the services and tests a change reaches.
  3. Risk assessmentChecks the change independently.
  4. CodeMakes the change on its branch.
  5. Test generationAdds tests and edge cases.
  6. Code reviewReviews the change before a person approves.
  7. Test and iterateRuns checks and retries fixable failures, up to a limit you set.

Spend and outcomes

Know what your AI spend buys.

  • AI usage metered by person, project and model
  • Monthly token budgets per organization
  • Outcome scores per agent

Coming soonCost per change · DORA metrics · An exportable record from idea to deploy

Put a team of agents on your next change.

Open a branch, give the agents their roles, and approve the plan.

Get startedTalk to us