AI Providers
OpenAI
Language models behind assistant, summarisation and drafting features.
OpenAI
AI Providers
On RequestWorks with AnantaTech Hub · Provided by OpenAI
What this connects
Assistant and automation features to OpenAI models.
Supported workflows
- Answering questions about business data in plain language
- Summarising documents and communication threads
- Drafting messages and document text
- Extracting structured data from unstructured input
Data exchanged
- The prompt and whatever business context is included in it
- Generated response
- Token usage for billing
Setup requirements
- An OpenAI API account
- API key configured server-side
- An explicit decision on what data may be included in prompts
Permissions required
- Permission to send the nominated data categories to the provider
Security and privacy
- Data is transmitted over encrypted connections (TLS).
- Credentials and tokens are stored server-side and never exposed to the browser.
- What business data is sent is decided with you before any AI feature is enabled — it is not switched on by default.
- Data handling is governed by OpenAI's API terms, which you should review as part of that decision.
Known limitations
Stated plainly, because finding these out during implementation is worse than knowing them now.
- Generated output can be wrong and should be reviewed before it is acted on.
- Usage is billed by the provider based on tokens consumed.
- Sending business data to a third-party model is a decision to make deliberately.
Need OpenAI connected?
Tell us how you use it today and we will confirm what is possible for your configuration before anything is committed.

