GPTs (custom agents) from Open AI integration
A
Andrae Aldrete
Open AI released the ability to create your own custom agents. So you could have a specific GPT (agent) the specializes in roofing, real estate, auto repair, etc. Would be awesome to have it integrated in the chat widget & all conversation channels. Massive value add to agencies & our clients.
Photo Viewer
View photos in a modal
Log In
A
Angela Livingston
Please make Claude an option for the AI Agents, it's conversational responses are far superior to ChatGPT and sound more human
E
Eddy CEO WhatSnap.ai - Connect YOUR phone to GHL
We've been building custom GPTs for different client verticals and they perform way better than generic prompts. Having them directly in GHL conversations would save us from juggling multiple tools.
S
Sales & Marketing
Merged in a post:
Add Claude 3.5 Sonnet for Conversation AI with custom knowledge base and instructions
S
Super Sim
Please please, add ability to connect Claude 3.5 Sonnet custom integration for Conversation AI with custom knowledge base and instructions. Its the only model that actually makes human like conversations and understand context well enough.
S
Sales & Marketing
Merged in a post:
Allow AI Agents to Connect to Any LLM via API (Bring Your Own LLM / BYOK)
C
Colvo Media
As GoHighLevel continues expanding its artificial intelligence capabilities (Conversation AI, Voice AI, and AI Agents), there is a clear need for greater flexibility in choosing the language models used behind the system.
Currently, users are limited to the LLM providers that GoHighLevel chooses to integrate directly. However, the AI ecosystem evolves extremely fast, with new models appearing constantly. Agencies and developers need the ability to choose the model that best fits their use case, cost structure, performance requirements, or language support.
It would be very valuable to enable a Bring Your Own LLM (BYO-LLM) approach, allowing AI Agents to connect to any external language model via API.
This could be configured easily within the AI Agent settings by allowing users to enter:
* API endpoint
* API key / secret key
* model name
* basic parameters such as temperature or max tokens
This should support two types of connections:
- Direct connections to LLM providers, for example:
OpenAI, Anthropic (Claude), Google Gemini, xAI (Grok), Mistral, DeepSeek, or self-hosted open-source models.
- Connections through aggregators such as OpenRouter, allowing access to multiple models through a single endpoint.
Key benefits include:
Flexibility to choose the best model depending on the use case.
Cost optimization by routing usage to more efficient providers.
Future-proof architecture that does not depend on specific integrations.
Greater ability to build advanced AI workflows by connecting external AI stacks or agents.
In practice, this would turn GoHighLevel into an AI-agnostic platform where the CRM manages workflows and automation while the user decides which language model to use.
S
Sales & Marketing
Merged in a post:
Different Providers to Power the Bots
T
Tim Lumsden
It would be great if we could pick a provider to power the bots. I personally prefer the way how Anthropic's Claude responds rather than OpenAI. Is it possible to build this functionality?
S
Samantha Wong Crunch Team
Please add Claude to Conversation AI
E
Eddy CEO WhatSnap.ai - Connect YOUR phone to GHL
Claude definitely feels more natural in conversations. We've tested both and clients notice the difference in how Claude handles context and tone.
E
Eddy CEO WhatSnap.ai - Connect YOUR phone to GHL
2-3 months sounds reasonable for evaluation, but curious how this works for specialized use cases? Some of our clients need models trained on specific industries or languages that might never make it to the main platform.
A
Abhishek Kumar
Colvo Media More LLM are coming like claude and gemini models
But it wont be bring your own keys as we already charge at token rate as per market
C
Colvo Media
Abhishek Kumar Thanks for the update. I understand that more LLMs will be added, but considering how fast new models are being released, how does HighLevel plan to avoid falling behind in terms of model availability?
Will there be any mechanism or strategy to keep the platform updated with new models quickly, or some way for agencies and developers to access newer models as they appear?
A
Abhishek Kumar
Colvo Media we are working on a framework where we can add new models by just something like plug and play
Ofcourse when a new model is released we will run bunch of evaluations
Once satisfied we will release the new models within 2 - 3 months.
E
Eddy CEO WhatSnap.ai - Connect YOUR phone to GHL
Claude really does handle nuanced conversations better. Our clients notice the difference when we test it against GPT for support conversations. The context retention is way more reliable too.
Load More
→