Render Tutorials
← All tutorials
intermediate ⏱ 28 min 4 steps

Localhost Part 1: Deploy an AI code-review agent on Render

Part 1 of the localhost conference workshop. Deploy one code-review agent two ways on Render: a naive in-process web service, then a queue plus background worker. Choose the TypeScript or Python track, review the same public PRs against each pattern, and watch the runtime pattern change, not the agent.

Start tutorial
#localhost#ai-agents#typescript#python#blueprints#background-jobs#key-value#postgres

Prerequisites

  • A Render account with access to the workshop workspace
  • A GitHub account
  • The Render CLI installed and logged into the workshop workspace
  • Node.js 22.12 or newer for the TypeScript track, or Python 3.12 and uv for the Python track
  • Redis or Valkey running locally for verifying the worker ack contract
  • Comfortable with Git, the terminal, and the Render Dashboard

Steps

  1. 01 What you'll build Meet the code-review agent and the deploy-first plan. Fork the workshop repo, namespace your Blueprint resources, and clone your fork. The agent code never changes; you deploy it two ways and watch the runtime pattern do more of the work. 7 min
  2. 02 Deploy the naive agent Deploy the Pattern 1 Blueprint and review a public PR on the hosted service. The review runs inside the request, which is exactly the limitation you'll feel. 5 min
  3. 03 Deploy the queue agents Deploy Pattern 2: a thin web producer, a background worker consumer, and a Key Value queue. Re-run the same public PR and watch the web service return instantly while the worker does the work. 8 min
  4. 04 Scale and survive failures Trace the worker ack semantics, verify retry behavior, then scale the worker and restart the web tier to connect that queue code to production behavior. 8 min