pulumi-neo

dirien's avatarfrom dirien

Pulumi Neo AI-powered infrastructure automation agent. Use when working with Pulumi Neo for conversational infrastructure management, creating Neo tasks, monitoring task progress, infrastructure analysis, maintenance operations, or automating multi-step cloud workflows through natural language.

⭐0stars🔀0forks📁View on GitHub🕐Updated Dec 14, 2025

When & Why to Use This Skill

Pulumi Neo is an advanced AI-powered infrastructure automation agent designed for platform engineers to manage cloud resources through natural language. It streamlines Infrastructure as Code (IaC) workflows by enabling conversational task creation, infrastructure analysis, and automated maintenance, allowing users to orchestrate complex multi-step cloud deployments without manual scripting.

Use Cases

  • Infrastructure Analysis: Automatically scan production stacks for security vulnerabilities, cost optimization opportunities, and performance bottlenecks using natural language queries.
  • Automated Maintenance: Execute complex operations such as upgrading Kubernetes clusters or patching cloud resources through simple conversational commands.
  • Code Generation & Review: Generate Pulumi TypeScript/Python code for new cloud projects and perform automated reviews of infrastructure changes within Pull Requests.
  • Policy Remediation: Identify and fix governance policy violations across cloud stacks to ensure compliance with organizational standards.
  • Workflow Orchestration: Automate multi-step cloud deployments, such as setting up complete CI/CD pipelines or adding monitoring to serverless functions.
namepulumi-neo
descriptionPulumi Neo AI-powered infrastructure automation agent. Use when working with Pulumi Neo for conversational infrastructure management, creating Neo tasks, monitoring task progress, infrastructure analysis, maintenance operations, or automating multi-step cloud workflows through natural language.

Pulumi Neo Skill

Pulumi Neo is an AI agent for platform engineers that enables conversational infrastructure management through natural language.

Prerequisites

  • Pulumi Cloud account with Neo access
  • PULUMI_ACCESS_TOKEN environment variable set with your Personal Access Token
  • Organization: Required for all Neo API calls

Detecting Organization

# Get current Pulumi organization from CLI
pulumi org get-default

# If no default org or using self-managed backend, ask user for organization name

If pulumi org get-default returns an error or shows a non-cloud backend, prompt the user for their Pulumi Cloud organization name.

Claude Code Integration

RECOMMENDED: Use MCP tools directly - they work natively with Claude Code:

mcp__pulumi__neo-bridge      # Create and interact with Neo tasks
mcp__pulumi__neo-get-tasks   # List existing tasks
mcp__pulumi__neo-continue-task # Continue polling a task

If using the Python script, ALWAYS add --no-poll:

# REQUIRED: --no-poll prevents blocking (script will hang without it)
python scripts/neo_task.py --org <org> --message "Your message" --no-poll

# Check events separately
python scripts/neo_task.py --org <org> --task-id <task-id> --get-events

WARNING: Never run the script without --no-poll in Claude Code - the polling loop will block indefinitely.

Using the Python Script

The script handles Neo task creation, polling, and management:

# Create a task and poll for updates (interactive/terminal use)
python scripts/neo_task.py --org <org-name> --message "Help me optimize my Pulumi stack"

# Create task without polling (CI/CD or programmatic use)
python scripts/neo_task.py --org <org-name> --message "Analyze this" --no-poll

# Create task with stack context
python scripts/neo_task.py --org <org-name> \
  --message "Analyze this stack" \
  --stack-name prod --stack-project my-infra --no-poll

# Create task with repository context
python scripts/neo_task.py --org <org-name> \
  --message "Review this infrastructure code" \
  --repo-name my-repo --repo-org my-github-org --no-poll

# List existing tasks
python scripts/neo_task.py --org <org-name> --list

# Fetch current events (single request, no polling)
python scripts/neo_task.py --org <org-name> --task-id <task-id> --get-events

# Poll an existing task for updates (interactive)
python scripts/neo_task.py --org <org-name> --task-id <task-id>

# Send approval for a pending request
python scripts/neo_task.py --org <org-name> --task-id <task-id> --approve

# Cancel a pending request
python scripts/neo_task.py --org <org-name> --task-id <task-id> --cancel

Neo Task Workflow

1. Creating Tasks

Tasks are created with a natural language message describing what you want Neo to do:

  • Infrastructure analysis: "Analyze my production stack for security issues"
  • Maintenance operations: "Help me upgrade my Kubernetes cluster"
  • Configuration changes: "Add monitoring to my Lambda functions"
  • Multi-step workflows: "Set up a complete CI/CD pipeline for this project"

2. Entity Context

Provide context to Neo by attaching entities:

Entity Type Use Case
stack Reference a Pulumi stack (name + project)
repository Reference a code repository (name + org + forge)
pull_request Reference a PR (number + merged status + repository)
policy_issue Reference a governance policy issue (id)

3. Task Status

Status Description
pending Task is queued
running Neo is processing the task
waiting_for_approval Neo needs user confirmation to proceed
completed Task finished successfully
failed Task encountered an error

4. Approval Flow

When Neo requires confirmation for an operation:

  1. Task status changes to waiting_for_approval
  2. Event contains approval_request_id
  3. User reviews the proposed changes
  4. Send approval or cancellation via the API

Common Workflows

Analyze Infrastructure

python scripts/neo_task.py --org myorg \
  --message "What security improvements can I make to my AWS infrastructure?" \
  --stack-name prod --stack-project aws-infra

Fix Policy Violations

python scripts/neo_task.py --org myorg \
  --message "Help me fix the policy violations in my production stack"

Generate Pulumi Code

python scripts/neo_task.py --org myorg \
  --message "Create a new Pulumi TypeScript project for a containerized web app on AWS ECS"

Review Pull Request

python scripts/neo_task.py --org myorg \
  --message "Review the infrastructure changes in this PR" \
  --repo-name infra --repo-org myorg --repo-forge github

Best Practices

Clear Instructions

  • Be specific about what you want Neo to do
  • Include relevant context (stack names, regions, requirements)
  • Specify constraints (budget, compliance requirements)

Entity Context

  • Always attach relevant stack or repository entities
  • This helps Neo understand the scope of your request

Approval Workflow

  • Review Neo's proposed changes carefully before approving
  • Neo generates pull requests for infrastructure changes
  • Use the preview feature to understand impact before deployment

Troubleshooting

Authentication Errors (401)

# Verify token is set
echo $PULUMI_ACCESS_TOKEN

# Test authentication
curl -H "Authorization: token $PULUMI_ACCESS_TOKEN" \
  https://api.pulumi.com/api/user

Organization Not Found (404)

  • Verify organization name with pulumi org get-default
  • Ensure your token has access to the organization

Cannot Respond While Request Pending (409)

  • Wait for Neo to finish processing before sending new messages
  • Poll for status updates before responding

References