Skip to main content
DMLY’s chatbot already answers on its own shared AI; you don’t need a provider account to use the AI Reply step. Connecting your own OpenAI key instead gives your bot unlimited, un-metered replies on your own account, plus full control over the model, web search, and your own account behind your knowledge base. OpenAI is one of four providers you can connect; it’s the only one that supports every AI capability DMLY offers. Prefer to watch first? This walkthrough covers connecting your key end to end.
Connecting your own key is a plan feature. If your plan doesn’t allow it, the tiles still appear but you can’t open them. Your chatbot keeps working on DMLY’s shared AI instead, metered by your plan’s AI Replies allowance. See Plan gating below and Plans.

​
Connect your key

1

Create an API key at OpenAI

In your OpenAI account, go to Settings → API keys and create a key. It starts with sk-. Copy it; OpenAI shows the full key only once.
2

Open the OpenAI tile

In DMLY, go to Integrations and select the AI tab, then select OpenAI. The panel’s Setup guide points you to platform.openai.com if you still need a key.
3

Paste the key and connect

Paste the key into API key and connect. The tile then reads Connected, and the knowledge base controls appear on the panel.
4

Use it in a flow

Open a flow and add the AI Reply step; it already answers on the shared AI. Pick OpenAI as its Provider to use your own key and model instead. See AI replies.
The API key is a password to your OpenAI account. Anyone with it can spend against your OpenAI billing. Create a key for DMLY alone so you can revoke it without breaking anything else.

​
What it powers

AI replies

The AI step writes the reply instead of you scripting it, using your prompt and the conversation so far.

File search

The AI searches documents you’ve uploaded (your price list, policies, FAQs) and answers from them.

Web search

The AI can look something up on the web while writing a reply.

Tools

The AI can tag a contact, book an appointment and use the other actions you allow it.

​
Your knowledge base

Build the knowledge base at Settings → AI Knowledge: collections of sources (files, web pages, FAQs, pasted text) the AI can search while it writes a reply. Once your OpenAI key is connected and your plan allows your own keys, that is the account the collections live on. The OpenAI panel also has its own Vector stores tab, which manages the same collections scoped to this one key, with files and web addresses only: upload a PDF, TXT or MD up to 20 MB, or paste a web address and DMLY fetches the page and indexes it for you. Adding documents doesn’t make the AI use them. On the flow’s AI step you set AI Knowledge to All workspace knowledge (or pick collections) on the Built-in Tools tab. Left on No knowledge, the AI answers from its own general knowledge and your prompt only. Full detail in Knowledge base.
You don’t need your own key for a knowledge base. Settings → AI Knowledge works on DMLY’s shared AI too. What your own key changes is whose account the collections sit on, and that a collection built on one account isn’t listed or searched once the workspace replies on another.
Only OpenAI and Google Gemini can search your material. Claude and DeepSeek can’t read documents at all, so a step replying on either of those searches nothing. If a knowledge base matters to you, those two are not an option.

​
Try it before it goes live

The AI step’s Playground tab in the flow builder lets you send a test message and see the reply the AI would produce, along with which tools it decided to call. Nothing there reaches a real contact: no message is sent, nothing lands in the Inbox, and contact actions are simulated rather than actually applied. It’s the safe place to check a prompt before you publish the flow.
The Playground tab appears whenever your plan allows connecting your own AI provider key; it’s hidden only for steps forced onto DMLY’s shared AI. You’ll see the tab even before you’ve connected a provider: an orange No AI provider is connected banner appears on the step, and running a test message shows Connect this provider in Integrations first until you add a key.

​
Choosing a provider

All four AI providers connect the same way: an API key on their tile in the AI tab. They differ in what the AI can then do:
If you’re not sure, start with OpenAI. It’s the only provider where every capability is available.

​
Plan gating

AI itself is available on every plan; the shared AI always answers. What a plan can restrict is connecting your own provider key, which is what everything below is about.
The four AI tiles (OpenAI, Claude, Google Gemini and DeepSeek) stay visible on the Integrations page so you can see what’s there, but they don’t open. Each tile shows a Plan locked badge instead of its status badge, and the action reads System AI instead of Connect. Selecting the tile shows: “This plan uses the built-in system AI. Upgrade to connect your own AI provider keys.”Your chatbot isn’t affected; it runs on DMLY’s shared AI instead, metered by your plan’s AI Replies allowance. See AI replies for what that looks like in the flow builder, and Plans for whether your plan allows your own keys.
The gate is enforced on the server, not just on the tile. If a workspace moves to a plan that doesn’t allow your own keys, an OpenAI key that’s already connected stays stored but is no longer usable: connecting or re-saving a key, the vector stores and the Playground are all blocked. The AI Reply step doesn’t stop, though: it falls back to DMLY’s shared AI automatically, so your contacts keep getting replies. Move back to a plan that allows your own keys and the same key works again; you don’t need to reconnect.Settings → AI Knowledge keeps working throughout, but it follows the account that answers: it moves to DMLY’s shared AI, so collections you built on your own key aren’t listed or searched until the plan allows your key again. See Knowledge base.