OpenCoze
Back to template library

Parallel Multi-Agent CI/CD Automation with /fleet

DevelopmentCozeUpdated 2026-04-02

Dispatch multiple Copilot CLI agents in parallel to automate linting, testing, and deployment for a repository, splitting tasks across files, declaring dependencies, and handling common pitfalls.

System Prompt
Generate a /fleet command script for repository {repo_path} on branch {branch} that runs agents {agents} to accomplish {task}. Ensure agents run in parallel, split work across files, declare dependencies, and capture errors.

Variable Dictionary (fill in your AI tool)

This section only explains placeholders. It is not an input form on this website. Copy the prompt, then replace variables in Coze / Dify / ChatGPT.

{repo_path}

Path to the repository, e.g., /myrepo

Filling hint: replace this with your real business context.

{branch}

Branch name to operate on, e.g., main

Filling hint: replace this with your real business context.

{agents}

Comma-separated list of agent names, e.g., lint,test,deploy

Filling hint: replace this with your real business context.

{task}

High-level description of the overall task, e.g., "Run CI/CD pipeline"

Filling hint: replace this with your real business context.

Quick Variable Filler (Optional)

Fill variables below to generate a ready-to-run prompt in your browser.

{repo_path}

Path to the repository, e.g., /myrepo

{branch}

Branch name to operate on, e.g., main

{agents}

Comma-separated list of agent names, e.g., lint,test,deploy

{task}

High-level description of the overall task, e.g., "Run CI/CD pipeline"

Generated Prompt Preview

Missing: 4
Generate a /fleet command script for repository {repo_path} on branch {branch} that runs agents {agents} to accomplish {task}. Ensure agents run in parallel, split work across files, declare dependencies, and capture errors.

How to Use This Template

Best for

Teams that need faster development output with more stable prompt quality.

Problem it solves

Reduces blank-page time, missing constraints, and inconsistent output structure from ad-hoc prompting.

Steps

  1. Copy the template prompt.
  2. Paste it into your AI tool (Coze / Dify / ChatGPT).
  3. Replace placeholder variables using the dictionary above.
  4. Run and refine constraints based on output quality.

Not ideal when

You need live web retrieval, database writes, or multi-step tool orchestration. Use full workflow automation for that.

Success Case

Input:
repo_path: "/myrepo", branch: "main", agents: "lint,test,deploy", task: "Run CI/CD pipeline"
Output:
fleet run --parallel --depends lint:test --depends test:deploy lint test deploy

Boundary Case

Input:
repo_path: "/myrepo", branch: "main", agents: "", task: "Run CI/CD pipeline"
Fix:
Provide at least one agent name.

What to Try Next

Keep exploring with similar templates and matching tools.

Continue Where You Left Off

No recent items yet.

Workflow Steps

  1. 1. Verify that the repository path and branch exist.

  2. 2. Define task files and dependencies for each agent in the {agents} list.

  3. 3. Generate the /fleet command script using --parallel and --depends to set up parallel execution and dependencies.

  4. 4. Execute the /fleet command locally or in CI, monitoring logs in real time.

  5. 5. Aggregate outputs from each agent and produce a unified execution report.

Constraints

  • Repository missing .fleet configuration file
  • More than 10 agents causing resource contention
  • Network timeout during /fleet execution

Explore More in This Category

Development

Recommended Stack

Tools that work well with this template.

Coze

Official site

Low-code agent workflow platform for fast automation delivery.

Open

OpenAI

Official site

General LLM platform for generation, analysis, and development use cases.

Open