How to migrate your WhatsApp AI chatbot from GPT Assistant v1.2.0 to v1.3.0
Table of Contents
This guide explains how to move an existing AI chatbot from GPT Assistant v1.2.0 (built on OpenAI's Assistants API) to GPT Assistant v1.3.0 (built on OpenAI's Responses API) inside WOZTELL.
It is for customers who already have a working chatbot on v1.2.0 and need to recreate it on v1.3.0 before the Assistants API is shut down.
What this migration is and is not
| The migration is not automatic | There is no button that upgrades v1.2.0 to v1.3.0. You create a new v1.3.0 extension and rebuild the configuration. |
| A new extension is created | Your v1.2.0 extension is left untouched. You install a separate v1.3.0 extension alongside it. |
| Your v1.2.0 chatbot keeps running | Keep the old chatbot live until the new one is fully validated, so your customers are never left without a reply. |
| End users are not affected | Customers keep writing from the same WhatsApp, Instagram, Facebook Messenger, or Webchat channel. Only the internal connection to OpenAI changes. |
Recommended approach, migrate with testing. Build the new v1.3.0 chatbot, validate it in a test environment with a small group of testers, and only switch it to production once you are confident. This way your customers keep talking to the proven v1.2.0 chatbot the whole time, with no interruption.
Before you start
Make sure you have:
- Access to your v1.2.0 extension configuration (you will copy settings from it).
- Your OpenAI API Key (the same key can be reused).
- At least one channel already connected in WOZTELL (WhatsApp Business Platform / Cloud API, Instagram, Facebook Messenger, or Webchat).
- A few testers whose accounts or phone numbers you can use to try the new chatbot safely.
The fastest way to migrate is to open your v1.2.0 configuration in one tab and the new v1.3.0 extension in another, then copy each setting across.
Step 1: Keep your v1.2.0 chatbot active
Do not disconnect or delete your current chatbot yet. It stays live and keeps replying to customers for the entire time you are building and testing the new one. You will only switch it off at the very end, during cutover (Step 6).
Step 2: Create the new v1.3.0 extension
You will create the new chatbot from scratch as a separate extension.
- Go to Marketplace, then + New Extension.
- Search for the ChatGPT extension card (Artificial Intelligence · OpenAI | WOZTELL) and click Learn More.
- Under Extension Version, select v1.3.0.
- Enter a unique Alias (lowercase, no spaces), for example my-gpt-assistant-v13.
- Click Install, then open the new extension under Installed Extensions.
- In the API Key Setup section, paste your OpenAI API Key and click Save. A green checkmark confirms the key is valid and unlocks the Configuration and Connect to Channel sections.
For the complete, screenshot-by-screenshot setup, follow the full guide: How to Create an AI Chatbot with OpenAI in WOZTELL. This migration guide focuses on the steps that are specific to moving from v1.2.0.
Step 3: Replicate your configuration
In v1.2.0, all of your chatbot’s behavior lived in the prompt (Instructions). Migrating it is mostly a matter of copying that prompt across and selecting the right model.
In the new v1.3.0 extension, open Configuration, then AI Chatbot, and set the Instructions (prompt), the Model, the Transcription model, and the advanced settings.
Understanding channels and environments
This is the concept that makes a safe migration possible, so it is worth understanding before you connect anything.
- A channel is the communication channel connected to WOZTELL: WhatsApp, Instagram, Facebook Messenger, or Webchat.
- An environment is a workspace inside a channel that lets you separate testing from production. If you have not created additional environments, the channel uses the Default environment.
During migration, environments let you run the new v1.3.0 chatbot in a test environment while your v1.2.0 chatbot stays on the live (Default/production) environment. Your customers keep talking to the old, proven chatbot until you are ready to switch.
Step 4: Connect the new chatbot to a test environment
Now connect the new chatbot, but to a test environment, not to production.
- If you don’t already have one, create a test environment and assign testers for your channel. Follow: How to create a test environment.
- In the v1.3.0 extension, open the Connect to Channel section.
- Find your channel, and select the test environment you created, not the Default/production environment where v1.2.0 is live.
- Click Connect.
- Enter a Prefix Name if required, use a clear label such as AI-CHATBOT-WHATSAPP-TEST.
- Click Confirm, then click Connect again.
When the button changes to Disconnect, the new chatbot is live in the test environment only.
Step 5: Test and validate
Now only your whitelisted testers are routed to the test environment and the new v1.3.0 chatbot. Production, and your real customers, stay on v1.2.0, untouched.
Have your testers put the new chatbot through its paces:
- From a whitelisted device or number, send messages to the channel.
- Confirm the chatbot replies, and that the replies match your Instructions.
- Test different question types and edge cases (including questions outside the chatbot’s scope).
- If you added a Knowledge Base / File Search, ask questions that should be answered from your documents and confirm it works.
- Review the logs for any errors (API Key, model, tools, File Search, or channel issues).
Step 6: Cut over to production
- Disconnect the v1.2.0 chatbot from the production (Default) channel/environment.
- Connect the v1.3.0 chatbot to that production environment (same connect steps as Step 4, but selecting the production environment this time).
- Send a final live test to confirm the new chatbot is replying in production.
Known issues during migration
| Issue | Cause | What to do |
|---|---|---|
| Unpredictable replies / users reaching the wrong bot | Two chatbots ended up active within the same environment. | Keep v1.2.0 and v1.3.0 on separate environments. During cutover, disconnect one before connecting the other in the same environment. |
| Testers can't reach the new chatbot | No Priority Group assigned, or testers not added to it. | Confirm the Priority Group is assigned to the test environment and that each tester is whitelisted (WhatsApp testers must message the WABA first). |
| Some prompt-based logic behaves differently | The Responses API handles context differently from the Assistants API. | Review and adjust the prompt during validation; consider moving reference content into File Search. |
| Assistant not responding in the test environment | API Key not saved, chatbot not connected, or wrong environment selected. | Confirm the API Key is saved, the chatbot is connected, and you are messaging the correct environment. |
Frequently asked questions
Why do I need to migrate from GPT Assistant v1.2.0 to v1.3.0?
OpenAI is shutting down the Assistants API, which v1.2.0 is built on, on 26 August 2026. After that date, chatbots still on v1.2.0 may stop working. v1.3.0 runs on OpenAI’s newer Responses API, so migrating keeps your chatbot running.
Is the migration automatic?
No. There is no button that upgrades v1.2.0 to v1.3.0. You create a new v1.3.0 extension and rebuild the configuration, while your v1.2.0 chatbot keeps running until the new one is ready.
Will my customers be affected during the migration?
Not if you migrate with testing. You keep v1.2.0 live, build and validate v1.3.0 in a separate test environment, and only switch to production once you are confident, so customers never lose service.
What is a test environment and why should I use one?
An environment is a workspace inside a channel that separates testing from production. Running v1.3.0 in a test environment lets a small group of testers try it while real customers stay on v1.2.0, which avoids two chatbots colliding in the same environment.
Do I need to rebuild my prompt and settings?
Yes. In v1.2.0 the chatbot’s behavior lived in the prompt. Copy that prompt into the new v1.3.0 extension, select the model and transcription model, and match your advanced settings. You can optionally move large reference content into File Search.
What is the deadline to migrate?
26 August 2026, when OpenAI shuts down the Assistants API. Migrate before then to avoid any interruption.
