Hi everyone!
This idea’s status has changed from ‘Being Reviewed’ to ‘Idea Submitted’. This change is due to our improvement project to update our Ideas Forum statuses in order to provide better transparency into how we are listening to your feedback.
“Idea Submitted” means that our product teams are aware of this feedback and are monitoring the need for this feature alongside other inputs that determine their priorities & roadmap.
For more details about the statuses we use on the Ideas Forum & what they mean, you can read this community post here.
@hhiggins what is the idea that you have submitted?
We are trying to test the customer agent and we are having trouble teaching it - the “training as a custom GPT” is a good way to see it.
The agent won’t accept our red lines - we repeatedly tell it to serve only english content but it keeps serving non-Englsh content. We have created FAQ for the agent, doc and an FAQ LP to try to help it prioritize, but it won’t follow some quite basic guidelines.
What is best practice here - how can we prompt the agent with red lines? Does it matter that we are not using a (Hubspot Service) KnowledgeBase as a source?
Hi @auto-mate! The ‘Idea Submitted’ is simply the status this idea is in; it means it’s still a feature request that our product team hasn’t addressed yet. This had been reviewed by our product teams previously, but we changed the status back to ‘idea submitted’ since it’s not on the roadmap at this time. If this changes and it goes into development, we’ll provide updates here!
With that said, there weren’t specific suggestsions I had around this feature. I reached out to a PM who may have more insight into your questions; I’ll share any helpful info I receive here. In the meantime, you can always reach out to Support for troubleshooting help.
@hhiggins We still wait for a way to prompt the Customer Agent! We have tested so much and have tried it live, and we are paying credits for piloting, but the results are poor. We really miss basic prompting interface. Surely this is MVP for an AI agent and missing here!
Problem for me is that we face more pressure to adopt a different AI chat tool if you can’t deliver MVP features here.
Lots of great ideas in this thread. The “Guidelines” feature is now in Public Beta. You can now define clear guidelines for your agent’s tone, response style, scripted responses, and guardrails. You can sign up here
What is it?
You can now define clear guidelines for your agent’s tone, response style, scripted responses, and guardrails.
Why does it matter?
Previously, the agent’s tone, style, guardrails came from a single personality and a fixed set of HubSpot guidelines. Customers wanted more control. Guidelines solve this by letting you write natural-language instructions so the agent consistently responds the way you intend.
How does it work?
Go to the customer agent by clicking on Service in the main navigation, then Customer Agent.
Click on Agent identity > Guidelines.
Enter the instructions in the respective sections
Tone: How your agent sounds in text, including attitude or emotion.
Response style: How your agent formats and orders its answers.
Scripted Responses: Reusable lines for greetings, apologies, or follow-ups.
Guardrails: What your agent should avoid or refuse.
Custom: Any other instructions you want the agent to follow.
You can either write these instructions from scratch or use templates that we provide out of the box by clicking on the “Apply Template” button.
Once you’ve written your instructions, you can optimize them for best performance by clicking on the Optimize button. The Optimize function also gives clear reasoning for any updates it makes.
When you’re ready, click the Test draft button to open the tester and validate your instructions while they’re still in draft.
If you’re satisfied with your agent’s responses, hit Publish. Any unsupported instructions will get flagged at this stage.
Your instructions are now live, and your agent will express itself based on them.
You can come back to the instructions and edit them at any point by toggling on draft mode. When you do this, your previously published instructions continue to work until the new version is published.
