Hermes BibleUnofficial Docs
← All flows Flow / Engineering Automation

How we used four AI agents to turn Jira tickets into reviewed PRs for about $12 each

An event-driven engineering workflow where four specialized Hermes agents handle ticket intake, coding, review, and CI — while humans keep merge authority. Routine tickets go from intake to reviewed PR in about four hours for roughly $12 in AI spend.

Hermes AgentJiraagentsticketsreviewedaboutevent-drivenengineeringworkflow
Category
Engineering Automation
Level
Community
Author
Luke
Reading time
5 min

An event-driven engineering workflow where four specialized Hermes agents handle ticket intake, coding, review, and CI — while humans keep merge authority. Routine tickets go from intake to reviewed PR in ab...

Community flow by Luke. View source

Flow sections

Section outline mirrored from the public community flow. Use the source page for full prose and examples.

Upstream outline

  1. 1. The Architecture
  2. The Four Named Agents
  3. 1. Mark — The Intake & Gate Agent (Claude 3.5 Haiku)
  4. 2. Andrew — The Senior Coder (OpenAI 5.5 Pro, fallback Claude Opus 4.8)
  5. 3. Rev — The Code Reviewer (Claude 3.5 Haiku)
  6. 4. Mr. Pipeline — The CI/Lint/Style Gate (Claude Haiku)
  7. Communication Paths
  8. 2. The Event-Driven Flow
  9. Step 1: Ticket Created in Jira
  10. Step 2: Mark Intake (Orchestration)
  11. Step 3: Andrew Codes (Implementation)
  12. Acceptance Criteria
  13. Tests
  14. Changes

Section map

1. The Architecture

Frames 1. the architecture for this Engineering Automation workflow, including the operating context to verify in the source page.

The Four Named Agents

Frames the four named agents for this Engineering Automation workflow, including the operating context to verify in the source page.

Communication Paths

Frames communication paths for this Engineering Automation workflow, including the operating context to verify in the source page.

2. The Event-Driven Flow

Frames 2. the event-driven flow for this Engineering Automation workflow, including the operating context to verify in the source page.

Step 1: Ticket Created in Jira

Frames step 1: ticket created in jira for this Engineering Automation workflow, including the operating context to verify in the source page.

Step 2: Mark Intake (Orchestration)

Frames step 2: mark intake (orchestration) for this Engineering Automation workflow, including the operating context to verify in the source page.

Step 3: Andrew Codes (Implementation)

Frames step 3: andrew codes (implementation) for this Engineering Automation workflow, including the operating context to verify in the source page.

Acceptance Criteria

Frames acceptance criteria for this Engineering Automation workflow, including the operating context to verify in the source page.

Implementation notes

  • Use this Engineering Automation flow as a pattern library entry: start from the summary, then inspect the linked source before copying any commands, schedules, or account wiring.
  • Primary decision areas: 1. The Architecture, The Four Named Agents, Communication Paths, 2. The Event-Driven Flow, Step 1: Ticket Created in Jira. Treat those sections as checkpoints for scope, cost, orchestration, and human review.
  • Useful search signals for this flow: agents, tickets, reviewed, about, event-driven. These are derived from the public title and summary, not from private runtime data.

Decision table

Best fitEngineering Automation workflow pattern

Use when the summary outcome matches your own workflow and 1. the architecture is relevant to your setup.

Verify firstAccounts, models, schedules, and tool access

Open the source sections for 1. The Architecture and The Four Named Agents before wiring credentials or automation.

Review boundaryHuman approval point

Keep human approval for merges, spending, external messages, credentials, and unattended execution.

Verification checklist

  1. Confirm the workflow outcome matches your use case: An event-driven engineering workflow where four specialized Hermes agents handle ticket intake, coding, review, and CI — while humans keep merge authority. Routine tickets go from intake to reviewed PR in about four hours for roughly $12 in AI spend.
  2. Open the source section for 1. The Architecture before copying commands, prompts, or schedules.
  3. List every credential, account, model, and external service the flow would touch.
  4. Define the human approval step before spending money, sending messages, trading, merging, or running unattended.
  5. Run a small dry run and compare the result with the source sections for 1. The Architecture and The Four Named Agents.

Risk notes

Model spend

Set provider, token, and retry limits before scaling the workflow beyond a single test run.

Runtime access

Check filesystem, shell, browser, repository, and server permissions before granting the agent write access.

What this page covers

  • Core concept and where it fits in the Hermes Agent system.
  • Setup or operating context implied by the upstream page summary.
  • The source page link for full current details and updates.

Source mirror note

This page is generated from the public Hermes Bible index so the clone has the same route coverage and search surface. It stores the public title, category, summary, and source link locally; use the source page for full upstream text and updates.

Open source page