Skip to content

Add Build Your First Team of AI Agents playbook#28

Open
willwashburn wants to merge 1 commit into
mainfrom
blog/first-agent-team
Open

Add Build Your First Team of AI Agents playbook#28
willwashburn wants to merge 1 commit into
mainfrom
blog/first-agent-team

Conversation

@willwashburn

@willwashburn willwashburn commented Jul 18, 2026

Copy link
Copy Markdown
Member

Summary

Adds the /blog/build-your-first-agent-team playbook: how to staff a five-agent team on Agent Relay (roles, engines, soul/memory/goals/heartbeat, reviewer loop, first-week order) using the CLIs you already pay for.

Test plan

  • Open /blog/build-your-first-agent-team on the preview deploy
  • Confirm frontmatter renders (title, author Will Washburn, date, tags, TOC)
  • Spot-check that install/spawn commands and skill URL match current product docs
  • Skim tone against other playbook posts for fit

Summary by cubic

Adds the “Build Your First Team of AI Agents” playbook post at /blog/build-your-first-agent-team to guide readers on staffing a five-agent team on Agent Relay. Covers roles and routing, a self-improving reviewer loop, CLI setup using agent-relay, and a first-week plan.

Written for commit 7b8a232. Summary will update on new commits.

Review in cubic

Playbook for hiring a five-agent team on Agent Relay: roles, engines,
review loop, and first-week staffing order.
@gemini-code-assist

Copy link
Copy Markdown
Contributor

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@coderabbitai

coderabbitai Bot commented Jul 18, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

Adds a blog post covering five-agent team design, Agent Relay setup, independent review loops, phased onboarding, and launch commands.

Changes

Multi-Agent Team Guide

Layer / File(s) Summary
Article framing and Agent Relay overview
web/content/blog/build-your-first-agent-team.mdx
Introduces the article and explains single-assistant bottlenecks, persistent agent identities, shared messaging, and Agent Relay capabilities.
Agent roles and room setup
web/content/blog/build-your-first-agent-team.mdx
Defines five specialist roles, maps example engines, specifies agent configuration, and provides Relay startup and spawning commands.
Review and rollout playbook
web/content/blog/build-your-first-agent-team.mdx
Documents independent review, memory updates from rejected work, first-week rollout steps, the playbook checklist, and launch resources.

Estimated code review effort: 3 (Moderate) | ~20 minutes

Possibly related PRs

Poem

Five little agents hop into the room,
Planning and building make ideas bloom.
Reviewers catch errors before they grow,
Relay helps every message flow.
With memory wiser, the team takes flight—
A rabbit-approved launch by moonlight!

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly summarizes the new AI agents playbook added in this PR.
Description check ✅ Passed The description accurately describes the new blog post and its setup, routing, and rollout guidance.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch blog/first-agent-team

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7b8a232150

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".


```bash
# 1. Start the broker
agent-relay local up --verbose

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Start the broker in the background in the setup block

For readers copying this bash block, the sequence stops here: the current CLI docs say local is an alias for node (web/content/docs/reference-cli.mdx:136), and node up stays attached by default unless --background is passed (web/content/docs/cli-broker-lifecycle.mdx:16,24). Because the following status, spawn, and tail commands are in the same block, they never execute unless the user manually opens another terminal, so the playbook's minimum setup is not runnable as written.

Useful? React with 👍 / 👎.

@github-actions

Copy link
Copy Markdown
Contributor

Preview deployed!

Environment URL
Web https://1670f845-agentrelay-web.agent-workforce.workers.dev

This is a Cloudflare Workers preview version of this PR's build.

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@web/content/blog/build-your-first-agent-team.mdx`:
- Around line 233-236: Update the broker startup instructions around
`agent-relay local up --verbose` so users can run `agent-relay local status
--wait-for 10` without being blocked by a foreground process; either explicitly
direct them to use a separate terminal or background the startup command, while
preserving the existing startup and status sequence.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: 3ab07601-6f7f-4e7a-8da8-a0fbf10ae201

📥 Commits

Reviewing files that changed from the base of the PR and between e216b9a and 7b8a232.

📒 Files selected for processing (1)
  • web/content/blog/build-your-first-agent-team.mdx

Comment on lines +233 to +236
```bash
# 1. Start the broker
agent-relay local up --verbose
agent-relay local status --wait-for 10

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Verify if agent-relay local up blocks the terminal.

If agent-relay local up --verbose runs in the foreground and blocks the terminal (which is common for daemon or broker processes), the subsequent agent-relay local status --wait-for 10 command will not execute if a user copies and pastes this entire block.

Consider explicitly advising the user to run the broker in a separate terminal tab, or appending & to background the process.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@web/content/blog/build-your-first-agent-team.mdx` around lines 233 - 236,
Update the broker startup instructions around `agent-relay local up --verbose`
so users can run `agent-relay local status --wait-for 10` without being blocked
by a foreground process; either explicitly direct them to use a separate
terminal or background the startup command, while preserving the existing
startup and status sequence.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant