HighLevel
Log in
Roadmap
Conversation AI
425
Changelog
Log in to your HighLevel account to give feedback
Powered by Canny

Conversation AI

posts
Please Give Conversational AI the ability to use MCP servers
14
·
in progress
Increase the word limit for Conversation AI
Voice AI doesn't seem to put a limit on the prompt word count. Can we have the same? Why limit it to 2000 and limit the LLM models?
1
·
planned
Conversation AI Context
Give Conversation AI the ability to review the contact record, their activity and communication history so that if they are reactivated, the bot knows about their past and communicate like a true customer service representative. This is especially helpful for industries with a longer sales cycle that takes more time.
3
·
planned
Allow phone number to be saved using "Add Contact Info"
For the WhatsApp channel, the phone number is no longer being saved, and under the "Add Contact Info" we cannot select Phone custom field to save it either. We need to save the phone number when it is provided in the chat
1
·
planned
Direct Webhook Integration in Conversations AI
In more robust AI integration projects with external API query APIs that return data, it would be very feasible to have the query with more flexible Webhooks that use the Open AI Tools resource. https://platform.openai.com/docs/assistants/tools The dynamic would be for the AI ​​to directly trigger a webhook with data return instead of triggering a trigger. We have this resource in several external platforms, but within High Level it is difficult to implement it for clients who need to check external data via API. Since you already have trigger activation and webhooks, I believe this option is easy to implement and even charge consumption for it.
5
·
in progress
Conversation AI summary should be generated in the sub-account's platform language
When a sub-account is set to a non-English language (e.g. French), the Conversation AI summary and transcript variables ({{conversations_ai.summary}} is still generated in English. This is misleading, as the platform advertises that setting the platform language will affect outbound communications. For agencies managing non-English speaking clients, receiving summaries in English creates confusion and breaks the workflow. The summary should be generated in the language configured in the sub-account's Platform Language setting.
1
·
planned
Anthropic models on Conversation AI
In Conversation AI, add the option to use different models (not just open.ai ), just like in voice agents. Anthropic particularly.
20
·
in progress
Custom actions on Conversation AI
Please add support for Custom Actions in Conversation AI, allowing AI agents to connect to and interact with external APIs. This would enable developers to fetch data, trigger workflows, send requests, and integrate third-party services directly from Conversation AI, significantly expanding automation and use cases.
8
·
in progress
AI hand off to a human message for Conversation AI at the end of maximum number of replies
I would like a final message to go from the Conversational AI bot to the contact when the maximum number of replies is reached. The AI assistant should not be having a two-way dialog with someone and then suddenly go silent. In the Conversation AI Advanced Settings for Auto-pilot mode there should be at least 2 fields for what happens when the max number of messages is reached: 1 - What do you want the bot to say before it goes to sleep? (Example answer: "Thank you for providing this information. It will help us determine how to best serve you. I will hand this conversation over to a human who will get back to you shortly.") 2 - What happens next? Possible options: Trigger a workflow. Notify the assigned user. Nothing (leave conversation marked unread). Mark the conversation as read.
36
·
in progress
Paragraph, Heading, and Bullet formatting in chat responses
The LONG dense paragraphs in the AI are hard to read. Why can't we format the same way Chat GPT does in their replies with paragraphs (spacing in between), bullets, etc?
32
·
in progress
Load More
→
Powered by Canny