---
title: "AI with Pulumi"
description: "AI-powered services and applications. Tutorials, examples, blog posts, and workshops for AI with Pulumi."
url: "https://www.pulumi.com/dev/tag/ai/"
image: "https://www.pulumi.com/assets/og/dev/tag/ai.png"
---

# AI with Pulumi

AI-powered services and applications. Tutorials, examples, blog posts, and workshops for AI with Pulumi.

## Tutorials

- [ChatGPT clone with Pulumi ESC managed secrets](https://www.pulumi.com/dev/tutorials/esc-managed-chatapp.md): Use the Pulumi CLI and ESC SDK to manage secrets for a basic OpenAI-based ChatGPT clone. — Python, YAML

## Examples

- [Serverless AI inference endpoint with Amazon Bedrock](https://www.pulumi.com/dev/examples/aws-ts-ai-app-infrastructure.md): A serverless AI inference endpoint on AWS - a Lambda Function URL that invokes an Amazon Bedrock foundation model, scoped to least privilege. — AWS · TypeScript · One-click deploy

## Blog Posts

- [Adding data to Pinecone using S3, Embedchain and Pulumi on AWS for an AI Slack bot](https://www.pulumi.com/blog/ai-slack-bot-adding-data-to-pinecone-using-s3-embedchain-and-pulumi-on-aws/): Learn how to add data to Pinecone using S3, Embedchain and Pulumi on AWS for an AI Slack bot. — AWS
- [Build an AI Slack Bot on AWS Using Embedchain & Pulumi](https://www.pulumi.com/blog/ai-slack-bot-to-chat-using-embedchain-and-pulumi-on-aws/): Learn how to build an AI-powered Slack bot with Embedchain & Pulumi on AWS. — AWS
- [Uploading documents to your AI Slackbot in real-time using S3, SQS and Pulumi on AWS](https://www.pulumi.com/blog/ai-slackbot-in-real-time-using-s3-sqs-and-pulumi-on-aws-uploading-documents/): Uploading documents to your AI Slackbot in real-time using S3, SQS and Pulumi on AWS — AWS
- [Deploy a Private Hermes Agent on Render Securely with Pulumi, Modal, and Tailscale](https://www.pulumi.com/blog/deploy-a-hermes-agent-with-pulumi/): Deploy a self-hosted Hermes agent as one Pulumi program across Render, Modal, and Tailscale — a code-executing AI agent with nothing on the public internet. — Python, TypeScript
- [Deploy an AI/ML Chatbot Frontend on Vercel with Pulumi](https://www.pulumi.com/blog/deploy-ai-ml-vercel-app/): Deploy your AI chatbot frontend on Vercel using Pulumi and Python. Follow this step-by-step guide to streamline your AI DevOps workflow.
- [Deploy OpenClaw on AWS or Hetzner Securely with Pulumi and Tailscale](https://www.pulumi.com/blog/deploy-openclaw-aws-hetzner/): Deploy OpenClaw (formerly Moltbot/Clawdbot), an open-source AI assistant, to AWS and Hetzner using Pulumi with Tailscale for secure private access. — AWS · TypeScript
- [Deploy LangServe Apps with Pulumi on AWS (RAG & Chatbot)](https://www.pulumi.com/blog/easy-ai-apps-with-langserve-and-pulumi/): Learn to deploy LangServe LLM apps on AWS using Pulumi. Includes real-world examples: a Gandalf chatbot and a Pinecone-powered RAG system with LangChain. — AWS
- [From 'Works on My Machine' to Production-Ready: Building AI Agents with Amazon Bedrock AgentCore](https://www.pulumi.com/blog/from-works-on-my-machine-to-production-ready-ai-agents-with-amazon-bedrock-agentcore/): Transform local AI agent prototypes into production-ready deployments using Amazon Bedrock AgentCore, Strands SDK, and Pulumi. — AWS
- [Fully Automated AI Inference on AWS, Azure, and Google Cloud with Pulumi](https://www.pulumi.com/blog/fully-automated-ai-inference-aws-azure-gcp-pulumi/): A zero-touch Ollama GPU inference server on AWS, Azure, or Google Cloud as one Pulumi program, with OIDC credentials from Pulumi ESC and no static keys. — AWS, Azure, Google Cloud · TypeScript
- [How Ralph Wiggum Built a Serverless SaaS with Pulumi](https://www.pulumi.com/blog/how-ralph-wiggum-built-a-serverless-saas-with-pulumi/): See how an AI agent using the Ralph Wiggum loop built a full AWS serverless SaaS with Pulumi—unsupervised. Frontend, backend, tests, and CloudFront included. — AWS · TypeScript
- [Kubernetes Agent Sandbox: What It Is and How to Deploy It with Pulumi](https://www.pulumi.com/blog/kubernetes-agent-sandbox/): Agent Sandbox gives AI agents kernel-isolated, disposable environments as Kubernetes resources. Here's what it is and how to deploy it on GKE with Pulumi. — Google Cloud, Kubernetes
- [Deploy Low-Code LLM Apps on AWS with Flowise and LocalAI](https://www.pulumi.com/blog/low-code-llm-apps-with-local-ai-flowise-and-pulumi/): Quickly build & deploy low-code LLM apps on AWS EKS using Flowise, LocalAI, and Pulumi. Follow this step-by-step guide & streamline your AI workflows. — AWS
- [AI-Assisted Infrastructure as Code with Pulumi's Model Context Protocol Server](https://www.pulumi.com/blog/mcp-server-ai-assistants/): Learn how AI assistants like Cursor with Pulumi's MCP server accelerate IaC workflows and improve developer experience.
- [Deploy AI Models on Amazon SageMaker using Pulumi Python IaC](https://www.pulumi.com/blog/mlops-huggingface-llm-aws-sagemaker-python/): Guided short tutorial on starting a Pulumi infrastructure as code project to deploy Hugging Face LLMs on Amazon SageMaker machine learning platform with Python — AWS · Python
- [The Real AI Challenge is Cloud, not Code!](https://www.pulumi.com/blog/mlops-the-ai-challenge-is-cloud-not-code/): Accelerating AI/ML innovation with infrastructure as code through a hands-on journey to deploy your own chatbot — Azure · Python
- [Run Open-Source LLMs on AWS EC2 with Ollama and Pulumi](https://www.pulumi.com/blog/run-deepseek-on-aws-ec2-using-pulumi/): Self-host DeepSeek, Llama, Qwen, or Mistral on AWS EC2 with Ollama and Pulumi. Includes instance-type recommendations, cost math, and copy-paste IaC.
 — AWS
- [Use Your Mac for AI Agents: Self-Host Gemma 4 12 B with Pulumi and Tailscale](https://www.pulumi.com/blog/self-host-gemma4-llama-cpp-k8s-tailscale-pulumi/): Self-host multimodal Gemma 4 on a Mac with Pulumi, llama.cpp, and Tailscale, using Unsloth's Gemma 4 12 B Q8 GGUF with a 128K context window.
 — Kubernetes · Python
- [Self-Verifying AI Agents: Vercel's Agent-Browser in the Ralph Wiggum Loop](https://www.pulumi.com/blog/self-verifying-ai-agents-vercels-agent-browser-in-the-ralph-wiggum-loop/): Vercel's agent-browser uses 82% less context than Playwright MCP. I tested both on the same six browser tests to see how they compare.

## Workshops

- [Taking AI Apps to Production](https://www.pulumi.com/events/ai-apps-to-production/): The Pinecone and Pulumi teams will explore the infrastructure and service architecture you need to scale AI apps in production.
- [Building AI-powered Applications at Pulumi](https://www.pulumi.com/events/building-ai-powered-applications-at-pulumi/): Learn how the Pulumi engineering team builds AI-powered capabilities and the lessons learned bringing these features into production.
- [Cloud Automation: AWS and Pulumi’s Path to Intelligent Ops](https://www.pulumi.com/events/cloud-automation-intelligent-ops/): Join Pulumi and AWS for a discussion on how next-generation AI capabilities are transforming infrastructure operations. — AWS
- [Deploying LangChain Applications on AWS with Pulumi](https://www.pulumi.com/events/deploying-langchain-apps-on-aws-with-pulumi/): This workshop will show a practical AI use case for Pulumi. Using Pulumi & TypeScript, we'll demonstrate deploying a LangChain app on AWS. — AWS · TypeScript
- [Deploying LlamaIndex Applications on AWS with Pulumi](https://www.pulumi.com/events/deploying-llamaindex-applications-on-aws-with-pulumi/): Dive into a session where we'll deploy an AI application using LlamaIndex on AWS. Discover the seamless integration of IaC in launching AI solutions. — AWS
- [Deploying LLMs on GKE with NVIDIA GPUs & Google Cloud](https://www.pulumi.com/events/deploying-llms-gke-pulumi/): Deploy a Mixtral 8x7B LLM on GKE with NVIDIA GPUs using Pulumi and Python. Learn to build scalable, GPU-enabled AI workloads on Google Cloud. — Google Cloud, Kubernetes · Python
- [Extending Pulumi Neo: MCP Servers and Cloud CLIs](https://www.pulumi.com/events/extending-pulumi-neo-mcp-cloud-cli/): Connect Pulumi Neo to Datadog, PagerDuty, Linear, and more via MCP, and to aws, gcloud, az, and kubectl — live workshop with real incident workflows.
- [Getting Started with Infrastructure Agents](https://www.pulumi.com/events/getting-started-with-infrastructure-agents/): Learn to add intelligent automation to infrastructure workflows with proper controls and human oversight. — AWS
- [Getting Started with Pulumi Insights](https://www.pulumi.com/events/getting-started-with-pulumi-insights/): In this workshop, you will learn how you can improve your team's productivity with the Search, Analytics, and Intelligence capabilities of Pulumi AI
- [Enterprise Guardrails for Agent-driven Operations](https://www.pulumi.com/events/governance-enterprise-guardrails-for-agent-driven-operations/): Learn how to balance team velocity with security and compliance by implementing governance frameworks for AI agents and policy as code. — AWS
- [Onboarding your first non-human platform engineer](https://www.pulumi.com/events/onboarding-your-first-non-human-platform-engineer/): Onboard an AI coding agent onto a real infrastructure repo with Pulumi ESC, Pulumi previews, and Entire's memory and review Trails. — AWS
- [Scaling AI Apps](https://www.pulumi.com/events/scaling-ai-apps/): How do you build and scale the infrastructure and service architectures for AI apps? — AWS
- [Self-Service AI Application Platforms](https://www.pulumi.com/events/self-service-ai-application-platforms/): Build self-service platforms for delivering AI-powered applications and agents. — AWS
- [Self-Service & AI Agents for Developer Productivity](https://www.pulumi.com/events/self-service-enabling-developer-productivity/): Learn how to build self-service developer platforms using Pulumi's AI agent, templates, and automation for Kubernetes and DigitalOcean deployments. — AWS, DigitalOcean, Kubernetes
- [Streamlining AI/ML Workflows on GKE with Pulumi](https://www.pulumi.com/events/streamlining-ai-ml-gke-pulumi/): Learn to harness the capabilities of GPUs and TPUs effortlessly, empowering data scientists to focus on model development rather than infrastructure management. — Kubernetes · Python
