ProductAgents

Coding agents

Coding agents that work in the branch. Build, test, open a review.

Use a coding agent for an individual task in the same branch as your teammates, with the same build graph, Atlas, tests and review rules. When the work needs independent design, risk or review, AI orchestration coordinates specialist agents and keeps their evidence together.

Get startedRead the docs
feat/retry-budget
CodeGraphAtlasTasksJobs
MRJO2
Tools

Explorer

services
checkout
BUILD.rbs
client.go
client_test.go
retry.go
payments
web
.reasonos
README.md
WORKSPACE.rbs
retry.go
client.go
1package checkout
2
3import (
4 "math/rand"
5 "time"
6)
7
8// Policy is how the checkout client retries calls
9// to the payments gateway.
10type Policy struct {
11 Base time.Duration
12 Ceiling time.Duration // never wait longer than this
13 Max int
14 Rand *rand.Rand
15}
16
17// Backoff is the wait before retry number attempt.
18func (p Policy) Backoff(attempt int) time.Duration {
19 d := p.Base << attempt
20 if d > p.Ceiling || d <= 0 {
21 d = p.Ceiling
22 }
23 return d
24}
25
26// Retry reports whether a call that failed with
27// status should be tried again.
28func (p Policy) Retry(status, attempt int) bool {
29 return attempt < p.Max && status >= 500
30}
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: commandsClaude Opus 5
RBS
Ready
UTF-8
GO
✦ Completions
◆ Hide AI
◀ Hide Explorer
⫿ Split

How you use it

Coding agents, step by step.

  1. 01Coding agents

    Give one agent a task, in the branch

    From the editor’s agent panel or the branch terminal, on the server where the code already builds. The run’s mode decides what it may do on its own: accept edits, ask for commands, plan only, or everything. A headless run denies what it is not allowed rather than hanging on a prompt.

  2. 02Coding agents

    It works from the branch’s real context

    The agent uses the workspace tools for file edits, search, commands, build and test targets, dependency queries, Atlas, stacks and tasks. It runs the same checks you would, with the same coverage floor, on the branch server where the code already runs.

  3. 03Coding agents

    Every step is revertable

    Checkpoints are Merkle-tree snapshots of the workspace: unchanged subtrees are shared, so a diff across a monorepo is cheap and a revert is exact. Accept and reject feedback becomes taste signals for naming, structure and verbosity on the next run.

  4. 04Coding agents

    Use orchestration when the task needs a team

    A coding agent is the hands-on teammate for one task. AI orchestration adds role-specific agents for design, risk, impact, code, test and review; independent agents can cross-check one another, and people keep the decisions that matter. Every run still follows the branch’s required checks and review rules.

The full reference lives in the docs.

Works with

EditorAtlasAgentic QA

Open a branch and try it.

Boots in seconds. Your team joins with a link.

Get startedTalk to us