Localhost Part 2: Run AI agents as Render Workflows

Prerequisites

• Completed Deploy an AI code-review agent on Render, or have the workshop repo forked with attendee Blueprint names set up
• The Render CLI installed (for the local authoring finale)
• Node.js 22.12 or newer for the TypeScript track, or Python 3.12 and uv for the Python track
• Comfortable with Git, the terminal, and your chosen track language
• Access to the Render workshop workspace

Steps

1. 01 What you'll build Meet Render Workflows through the same code-review agent. The queue and coordination you hand-rolled in Pattern 2 become a single primitive: the task. 5 min →
2. 02 Deploy the workflow agents Deploy the gateway Blueprint, create the separate workflow service that Blueprints do not manage yet, then submit a public PR and read the run trace in the Render Dashboard. 9 min →
3. 03 Run workflows locally (Optional) Install the Render CLI and start the local workflow runtime, then run the code-review workflow on your machine and read the same task fan-out you saw in the hosted trace. 5 min →
4. 04 Author a task Start from the shipped `your-review` sandbox, customize the `my-reviewer` agent, force a retry, then fan out a second task to see what the platform handles for you. 9 min →
5. 05 Ship your task to production Ship the task you authored to the deployed Workflow service, verify the production trace, and confirm the same task now runs on Render. 6 min →
6. 06 Go further with your review task Optional take-home challenges and production hardening paths for the review task you deployed. 10 min →
7. 07 Share your feedback Tell us what landed and what didn't, so the next run of the workshop is sharper. 2 min →