t031: Add company orchestration agent with runner configs#2054
t031: Add company orchestration agent with runner configs#2054marcusquinn merged 2 commits intomainfrom
Conversation
Add business domain agent for company-level AI orchestration: - .agents/business.md: Main agent documenting company agent patterns, coordinator integration, cross-function workflows, and guardrails - .agents/business/company-runners.md: Example runner AGENTS.md templates for hiring-coordinator, finance-reviewer, ops-monitor, marketing-scheduler, and support-triage - Update subagent-index.toon with Business agent and business/ subagent - Add Business entry to AGENTS.md domain index - Fix subagent count in TOON index (was 51, actual 54) Integrates with existing runner-helper.sh, coordinator-helper.sh, and objective-runner-helper.sh for cross-function task dispatch with safety guardrails. Closes #512
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly expands the AI agent framework by introducing a new "Business" domain focused on company-wide orchestration. It enables the creation and management of AI agents tailored to specific departmental functions like HR, Finance, and Marketing, utilizing a robust runner and coordinator pattern for task dispatch and persistent identity. This enhancement allows for more granular and automated management of business processes, complete with guardrails and cross-functional workflow capabilities. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. WalkthroughIntroduces a Company Orchestration Agent pattern with documentation and templates for coordinating multiple AI agents across company functions. Adds Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sat Feb 21 03:24:04 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces the Business domain for company-level AI orchestration, adding a main coordinator agent (business.md) and specific runner configurations (business/company-runners.md). It also correctly fixes a pre-existing count mismatch in the subagent-index.toon file. The architecture leverages existing helpers (runner-helper.sh, coordinator-helper.sh) effectively. My feedback focuses on ensuring the agent hierarchy is correctly indexed in the YAML frontmatter and that the provided setup script adheres to the repository's shell scripting standards regarding shared constants.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
.agents/business/company-runners.md (1)
86-101: Finance Reviewer threshold is described as "configurable" with no documented configuration point.Line 89 says amounts over a threshold (configurable) require sign-off, but neither the template nor the setup script shows where or how to set it. Users copying this template will have no guidance and may leave the check unconfigured.
📋 Suggested clarification
-## Constraints -- Never approve payments — flag for human approval -- Amounts over threshold (configurable) require explicit sign-off +## Constraints +- Never approve payments — flag for human approval +- Amounts over `FINANCE_APPROVAL_THRESHOLD` (default: 500 GBP; set in runner env or AGENTS.md) require explicit sign-off🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.agents/business/company-runners.md around lines 86 - 101, The "Amounts over threshold (configurable)" entry in the "## Constraints" section lacks a documented configuration point; update the template to specify where and how to set this threshold (e.g., introduce a named config key or env var such as FINANCE_APPROVAL_THRESHOLD and the config file/CLI/setup script that reads it), include the default value and units, and add a short note in the "## Tools" or setup instructions showing how to change it and how the validation in the runner (e.g., the threshold check logic) will reference that key.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.agents/business.md:
- Around line 128-131: The example uses the same convoy name (--name
"monthly-close") in multiple sections causing potential registration conflicts;
update the Coordinator Integration example (the coordinator-helper.sh convoy
invocation) to use a distinct placeholder convoy name (e.g., --name
"example-convoy" or --name "CONVOY_NAME") instead of "monthly-close", keep the
--tasks argument unchanged for that example, and ensure the Monthly Financial
Close section retains the real --name "monthly-close" so the two examples remain
clearly distinct.
- Around line 12-18: The frontmatter "subagents" list incorrectly includes
non-existent entries "general" and "explore"; remove those two values from the
subagents array in the business agent frontmatter so only valid agents remain
(e.g., accounts, sales, marketing, legal) and ensure the "subagents" key matches
the actual TOON:agents index; update the "subagents" array in
.agents/business.md to exclude "general" and "explore".
In @.agents/business/company-runners.md:
- Around line 175-196: The marketing-scheduler template (headed "Marketing
Scheduler" / identifier marketing-scheduler) is missing the required "##
Communication" section; add a new "## Communication" section that instructs the
runner to send status reports back to the coordinator following the same pattern
as other templates (include frequency, recipient "coordinator", and expected
format/summary fields such as queued drafts, scheduled sends, and flagged
items), and ensure it explicitly states to report on draft queue status and any
flagged underperforming campaigns.
---
Nitpick comments:
In @.agents/business/company-runners.md:
- Around line 86-101: The "Amounts over threshold (configurable)" entry in the
"## Constraints" section lacks a documented configuration point; update the
template to specify where and how to set this threshold (e.g., introduce a named
config key or env var such as FINANCE_APPROVAL_THRESHOLD and the config
file/CLI/setup script that reads it), include the default value and units, and
add a short note in the "## Tools" or setup instructions showing how to change
it and how the validation in the runner (e.g., the threshold check logic) will
reference that key.
marcusquinn
dismissed
coderabbitai[bot]’s stale review
Auto-dismissed: bot review does not block autonomous pipeline
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sat Feb 21 04:10:37 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
1 participant
Summary
business.mdmain agent for company-level AI orchestration — maps company departments (HR, Finance, Ops, Marketing, Support) to named runners coordinated viacoordinator-helper.shbusiness/company-runners.mdwith example AGENTS.md templates and setup for 5 company function runners: hiring-coordinator, finance-reviewer, ops-monitor, marketing-scheduler, support-triagesubagent-index.toonandAGENTS.mddomain indexArchitecture
Builds on existing infrastructure — no new scripts needed:
runner-helper.shfor persistent named agent instancescoordinator-helper.shfor stateless cross-function dispatchobjective-runner-helper.shfor safety guardrails (budget, scope, checkpoints)mail-helper.shfor inter-agent communicationVerification
Closes #512
Task: t031
Summary by CodeRabbit