WayToClawEarn
Beginner30 min readMay 22, 2026

How to use Runtime to build a team AI programming Agent collaboration environment: a 30-minute complete tutorial

From zero configuration to team launch, products/design/operations can also safely use Claude Code and Codex

Edisen Lu · WayToClawEarnPublished May 22, 2026Updated Sep 28, 2026

Reviewed from public sources · AI-assisted drafting under editorial oversight. How we work

Editorial original

Written by WayToClawEarn editorial; cite this page as the primary analysis.

How we review content

Tutorial Objectives

In 30-45 minutes, use Runtime to set up a team-level AI coding Agent collaboration environment. Your product, design, and operations colleagues can directly talk to agents such as Claude Code and Codex to complete tasks, instead of having to be accompanied by engineers every time.

What will you build?

  • Sandboxed Agent Environment: Each team has an independent coding Agent, with its own project context and tool chain, ready to use at boot.
  • Slack/Linar integration: Directly summon Agents to complete tasks in the team's daily collaboration channels
  • Safety Guardrails: Cost limit, command whitelist, network export control, Agent will not touch the production environment

Preparation list

  • GitHub account (Runtime uses GitHub OAuth to log in)
  • Slack workspace (optional, recommended) - facilitates scheduling Agents directly in messages
  • Your own AI API Key (Claude Code / OpenAI / Gemini are all acceptable)

Overall architecture

Runtime provides an "Agent infrastructure layer": you configure the project environment once and take a snapshot, and then when anyone triggers the Agent, it will run in an environment where everything has been configured.

ModuleInputOutputEstimated time
Registration and project creationGitHub accountSandbox environment5 minutes
Configure project contextSystem commands + skill filesReusable configuration10 minutes
Set up security guardrailsCommand whitelist/network policySecurity policy5 minutes
Integrated collaboration channelsSlack / LinearAgent touch portal5 minutes
Team hands-on verificationReal tasksFinal PR5-10 minutes

Runtime agent dashboard with team sessions

Step 1: Register and create your first sandbox

Open app.runtm.com and log in with your GitHub account. The runtime reads the list of repositories you own through GitHub OAuth.

terminal

# CLI
brew install runtmdotcom/tap/runtm
runtm login

, Create Sandbox,。Runtime Docker Compose、package.json ,。

****,。Runtime Session docker-compose.yml 。

2

","。

" DevOps , .cursorrules "Agent
.runtm/skills/deploy.md

.runtm/instructions.md

markdown

# Runtime Agent Instructions

## Code Style
- ESLint + Prettier
- `npm run test`
- PR Conventional Commits

## Permissions
- `.env.example`()
- `preview/`
- `production/`

Runtime Guardrails

git, npm, docker, curl
api. github.com registry.npmjs.org
Session $2

Configuring Runtime project context and guardrails

3 Slack Linear

Runtime Agent。 Slack @ Agent 。

Runtime Dashboard Integrations → Slack

  1. "Add to Slack", Runtime
  2. #ai-agents
  3. Agent @mention
text

# ai-agents

@runtime-eng API 504 , Sentry , PR

@runtime-eng , upstream Postgres 。
PR: https://github.com/org/repo/pull/452()

Runtime ,。

4 Agent(Background Agent)

Agent。** Agent**

PagerDutySentry → →PR +
StripeSnowflake →+ Slack
GitHub PRpreviewURL

—— Agent,,。Runtime 、。

5

,。Runtime ****

  1. Slack " Hero " → Agent → URL → PM
  2. "" → Agent →
  3. " API " → Agent →

Session Agent ,, Google Docs 。

Runtime Agent , 3 ,。

(FAQ)

Q1Runtime Claude Code ?

Claude Code Agent 。Runtime 、、、、Slack 。 5 Claude Code,, Runtime 。

Q2Agent ?

。Runtime ,Agent API Key。 Agent 。 Agent 。,Agent PR 。

SEO+GEOFAQ GEO ,

, tools hover-cardOpenAI、ChatGPT、Claude、Claude Code、Codex、Gemini、n8n.

Reference video/material

Internal link guidance

Educational reference only: cases summarize public sources and may use AI-assisted drafting under editorial review. Not financial advice; outcomes are not guaranteed.

Related tutorials