Skip to main content

Deploy as ChatGPT

Built in SmythOS. Published to ChatGPT.
Use this guide to connect your SmythOS agent to GPT Builder via OpenAPI. Fast. Flexible. No rewrites.

INFO

TL;DR: Deploy your agent → copy its OpenAPI URL → import it into GPT Builder as an Action. Done.

Why Connect Your SmythOS Agent to ChatGPT?​

If you want to:

  • Let users interact with your agent inside ChatGPT
  • Avoid duplicating agent logic
  • Control updates, access, and visibility

... then you’re in the right place.

This method uses SmythOS’s OpenAPI output + GPT Builder’s Action system.

Prerequisites​

  • A deployed agent in SmythOS (Test or Production)
  • Access to OpenAI GPT Builder (Pro or higher plan)

Step 1: Get the OpenAPI URL​

  1. Go to Agent Settings → Deployments
  2. Scroll to Environment URLs and locate:
    • Test subdomain (for development use)
    • Production subdomain (for stable releases)

Example subdomains:

https://salesbot.agent.stage.smyth.ai (Test)
https://salesbot.agent.pstage.smyth.ai (Production)

You’ll use these to form your OpenAPI URL by appending /api-docs/openapi-llm.json to your subdomain:

https://salesbot.agent.pstage.smyth.ai/api-docs/openapi-llm.json

General format:

https://<subdomain>/api-docs/openapi-llm.json
Use the production subdomain for stable GPTs and test subdomain when you're actively iterating.

Step 2: Create and Configure Your Custom GPT​

1. Open GPT Builder​

Click here to open GPT Builder

2. Set Basic Configuration​

Click the Configure tab.

3. Add Name, Instructions, and Welcome Message​

Fill in:

  • Name – the public-facing name of your GPT
  • Instructions – paste your SmythOS agent behavior or prompt config
  • Welcome message – what users see on launch
INFO

Tip: Copy your SmythOS agent behavior directly into the Instructions field for consistent results.

4. Add an Action to Use the Agent​

Scroll to Actions, then click Create new action.

5. Import the OpenAPI URL​

Depending on your use case:

For Test Agent:​

https://<test-subdomain>/api-docs/openapi-llm.json

For Production Agent:​

https://<prod-subdomain>/api-docs/openapi-llm.json

Paste the correct URL based on your chosen environment, then click Import.

INFO

Import your OpenAPI actions directly from https://<subdomain>/api-docs/openapi-llm.json

6. Finalize the Setup​

Click Create in the top right corner to save the custom action.

7. Test or Customize Further​

You’re ready to use the GPT... or customize it further if needed.

INFO

If you’re using the test URL, your GPT will reflect your agent’s latest edits. In debug mode, requests wait for manual execution in Studio.

Keeping Your GPT Synced​

  • Re-deploy your agent after edits
  • Re-check your subdomain to ensure it’s unchanged
  • Re-import the OpenAPI URL in GPT Builder to sync new logic
Reimport your OpenAPI URL after every significant agent update or version bump.
INFO

Every time your agent logic changes, re-deploy and re-import the updated OpenAPI file.

Troubleshooting Common Issues​

IssueFix
401 UnauthorizedDouble-check auth token format and value
Import failsVisit URL in browser... if it redirects, use the final .json link
GPT doesn't see new endpointsRe-import OpenAPI file after changes
('openapi',): Input should be '3.1.0'Change OpenAPI version from 3.0.1 to 3.1.0 in the schema

What’s Next?​

Great! Your SmythOS agent is now live and available inside ChatGPT as a custom GPT.

  • Build different GPTs using the same backend logic
  • Route traffic by versioning your agent and updating GPT URLs
  • Monitor usage from Settings → Deployments → Analytics in SmythOS

You can now:

  • Avoid duplicate workflows
  • Get versioned, testable GPT behavior
  • Control how and when users interact with your logic
Connect a SmythOS agent to a new GPT using OpenAPI URL and auth key.

Need more? Build multiple GPTs from one agent. Use different prompts, auth setups, or endpoint sets. SmythOS keeps the backend clean.