Agent settings holds how the agent replies, what it remembers and your own OpenAI keys. Open it from the gear at the foot of the sidebar, under Settings > Agent settings, or from the settings menu inside any agent chat. The page is open on every plan.
The GitHub connection the agent uses to open pull requests is not here: set it up on the GitHub card in Integrations > Publish content.
Setting | What it does |
|---|---|
Reply language | The language the agent answers in. Match my messages (the default) answers in the language you write in. The setup chat follows it too. |
Tone | How much the agent explains: Balanced (a clear answer with a few short lines), Concise (the answer and little else) or Detailed (the reasoning and the steps) |
Web search | Lets the agent look up current facts about your brand, your competitors and AI search |
Things the agent saves for a brand stay in the brand's market language, whatever the reply language.
Memory lists what the agent remembers about you and your brands, newest first. Click Forget this to remove one. See Agent memory.
By default the agent spends your AI budget. With your own OpenAI key, the agent runs on your OpenAI account instead: its usage is billed by OpenAI and your AI budget is not touched. Agent API keys need Starter or higher on your own account.
Go to Agent settings > Agent API keys
Click Add key
Enter a Name (a label to recognise it) and the API key (OpenAI keys start with "sk-")
Click Add key: the app checks the key with OpenAI before saving it
Click Activate on the new key
A new key starts inactive. Only one key is active at a time. You can store up to 5 keys.
Each key has a model picker with the models your key can run the agent with. One is marked Recommended.
Click Deactivate on the active key, or delete it. The agent goes back to your AI budget.
If your key fails during a conversation (expired, out of quota), that turn runs on your AI budget and the chat says so.
Your key is stored encrypted. After saving, the app only shows a masked hint of it.
Without your own key, the agent spends AI budget: a dollar balance separate from credits, included in every plan ($1 a month on Free, up to $25 on Agency Plus; see What is the agent?). AI edits in the article editor spend it too.
/usage in the chat shows the conversation's context and your AI budget used
Subscription > Usage shows the AI budget with every credit pool, and the agent's spend under AI usage
Convert credits into AI budget on Plans > AI budget, or from Top up your AI budget when the chat tells you it ran out:
Credits | AI budget |
|---|---|
20 | $5 |
50 | $15 |
120 | $40 |
AI budget you add is spent within the current billing cycle and resets with your plan. If you do not have enough credits to convert, buy a credit top-up first. See Plans and subscription.
No. While a key is active, the agent's usage goes to your OpenAI account. The one exception is a turn where your key fails: that turn runs on your AI budget.
No. Keys, AI budget and memories are per person. Each teammate runs the agent on their own budget or key.
A model Rank Prompt picks for quality and speed. Its answers spend your AI budget; actions that cost credits, like running a report, ask first.
Email [email protected] and I'll help.
