Powered by eniston
  1. Overview
  2. Integrations & Setup Guides
  3. AI Provider Configuration

AI Provider Configuration

Overview

AutomateNexus CRM includes AI-powered features such as email drafting, lead scoring, conversation summarization, sentiment analysis, and intelligent workflow automation. To use these features, you need to connect at least one AI provider by supplying an API key. AutomateNexus CRM supports multiple AI providers including Anthropic (Claude), OpenAI (GPT), Google (Gemini), Mistral, and Groq. You can configure multiple providers simultaneously and select which model to use for different AI features. This guide walks through the setup process for each provider and explains model selection best practices.

Prerequisites

Before configuring AI providers, ensure you have:

  • An active AutomateNexus CRM account with Administrator role permissions.
  • An account with at least one supported AI provider.
  • A valid API key from your chosen provider with sufficient credits or an active billing plan.
  • An understanding of the AI features you plan to use (this affects which models you should select).

Navigating to AI Settings

  1. Log in to your AutomateNexus CRM dashboard.
  2. Click Settings in the left-hand sidebar.
  3. Select Integrations from the settings menu.
  4. Click the AI Providers tab at the top of the Integrations page.

The AI Providers page shows all supported providers with their connection status. You can connect multiple providers and set a default for each AI feature category.

Anthropic (Claude) Setup

About Anthropic

Anthropic offers the Claude family of models, known for their strong reasoning capabilities, safety features, and ability to handle long documents. Claude models are excellent for email drafting, document analysis, and complex conversational tasks.

Getting Your Anthropic API Key

  1. Go to console.anthropic.com and sign in or create an account.
  2. Navigate to API Keys in the left sidebar.
  3. Click Create Key.
  4. Give the key a descriptive name (e.g., "AutomateNexus CRM").
  5. Copy the API key. It will start with sk-ant-.
  6. Ensure you have added a payment method and set a usage limit under Plans & Billing.

Connecting Anthropic to AutomateNexus CRM

  1. Navigate to Settings → Integrations → AI Providers.
  2. Click Configure next to Anthropic.
  3. Paste your API key into the API Key field.
  4. Click Test Connection. AutomateNexus CRM will make a small test request to verify the key is valid.
  5. Select your preferred default model:
    • Claude Opus 4: Most capable model. Best for complex analysis, long document processing, and nuanced email drafting. Higher cost per token.
    • Claude Sonnet 4: Balanced performance and cost. Recommended as the default for most CRM AI features.
    • Claude Haiku 3.5: Fastest and most cost-effective. Ideal for high-volume tasks like lead scoring, short text classification, and quick summaries.
  6. Click Save Configuration.

OpenAI (GPT) Setup

About OpenAI

OpenAI provides the GPT family of models, widely adopted and well-suited for general-purpose text generation, summarization, and classification tasks within AutomateNexus CRM.

Getting Your OpenAI API Key

  1. Go to platform.openai.com and sign in.
  2. Navigate to API Keys in the sidebar (under your profile settings).
  3. Click Create new secret key.
  4. Name the key (e.g., "AutomateNexus CRM") and set permissions to All or restrict to specific capabilities.
  5. Copy the key. It will start with sk-.
  6. Ensure you have billing configured under Settings → Billing.

Connecting OpenAI to AutomateNexus CRM

  1. Navigate to Settings → Integrations → AI Providers.
  2. Click Configure next to OpenAI.
  3. Paste your API key.
  4. Optionally, enter an Organization ID if your OpenAI account belongs to an organization.
  5. Click Test Connection.
  6. Select your preferred default model:
    • GPT-4o: Multimodal model with strong performance across tasks. Good default choice.
    • GPT-4o mini: Smaller, faster, and more affordable. Suitable for routine tasks.
    • o3-mini: Reasoning model, best for complex analytical tasks.
  7. Click Save Configuration.

Google (Gemini) Setup

About Google Gemini

Google offers the Gemini family of models through Google AI Studio or Vertex AI. Gemini models support multimodal inputs and are well-integrated with the Google ecosystem.

Getting Your Google AI API Key

  1. Go to aistudio.google.com and sign in with your Google account.
  2. Click Get API Key in the top navigation.
  3. Click Create API Key and select a Google Cloud project (or create a new one).
  4. Copy the generated API key.

Connecting Google Gemini to AutomateNexus CRM

  1. Navigate to Settings → Integrations → AI Providers.
  2. Click Configure next to Google (Gemini).
  3. Paste your API key.
  4. Click Test Connection.
  5. Select your preferred model:
    • Gemini 2.5 Pro: Most capable Gemini model with strong reasoning.
    • Gemini 2.0 Flash: Fast and efficient for everyday tasks.
    • Gemini 2.0 Flash Lite: Most cost-effective option for simple tasks.
  6. Click Save Configuration.

Mistral Setup

About Mistral

Mistral AI offers high-performance open-weight models that are efficient and cost-effective. They are a strong choice for organizations that value the flexibility of open models or need European data processing.

Getting Your Mistral API Key

  1. Go to console.mistral.ai and sign in or create an account.
  2. Navigate to API Keys.
  3. Click Create new key.
  4. Name the key and copy it.
  5. Ensure billing is configured in your Mistral account.

Connecting Mistral to AutomateNexus CRM

  1. Navigate to Settings → Integrations → AI Providers.
  2. Click Configure next to Mistral.
  3. Paste your API key.
  4. Click Test Connection.
  5. Select your preferred model:
    • Mistral Large: Top-tier model for complex tasks.
    • Mistral Medium: Balanced performance and cost.
    • Mistral Small: Fast and economical for simple tasks.
  6. Click Save Configuration.

Groq Setup

About Groq

Groq provides ultra-fast inference through custom hardware (LPU). It hosts popular open-source models and delivers responses with extremely low latency, making it ideal for real-time CRM features like live chat assistance and instant lead scoring.

Getting Your Groq API Key

  1. Go to console.groq.com and sign in or create an account.
  2. Navigate to API Keys.
  3. Click Create API Key.
  4. Name the key and copy it.

Connecting Groq to AutomateNexus CRM

  1. Navigate to Settings → Integrations → AI Providers.
  2. Click Configure next to Groq.
  3. Paste your API key.
  4. Click Test Connection.
  5. Select your preferred model from the available hosted models (e.g., Llama 3.3 70B, Mixtral 8x7B, Gemma 2 9B).
  6. Click Save Configuration.

Model Selection and Feature Assignment

Setting a Default Provider

After connecting one or more providers, set a default AI provider:

  1. Navigate to Settings → Integrations → AI Providers → Default Settings.
  2. Select the Default Provider from the dropdown. This provider will be used for all AI features unless overridden.
  3. Select the Default Model for the chosen provider.
  4. Click Save.

Per-Feature Model Assignment

You can assign specific models to different AI features for optimal performance and cost management:

  1. Navigate to Settings → Integrations → AI Providers → Feature Assignment.
  2. For each AI feature, select the provider and model to use:
    • Email Drafting: Recommended models include Claude Sonnet 4 or GPT-4o for high-quality, contextual email composition.
    • Lead Scoring: Use a fast, cost-effective model like Claude Haiku 3.5, GPT-4o mini, or a Groq-hosted model for rapid scoring of incoming leads.
    • Conversation Summarization: Claude Sonnet 4 or Gemini 2.0 Flash work well for summarizing long conversation threads.
    • Sentiment Analysis: A smaller model like Mistral Small or Claude Haiku 3.5 is sufficient for classifying message sentiment.
    • Content Generation: For blog posts, social media content, and marketing copy, use Claude Opus 4 or GPT-4o for the highest quality output.
    • Data Extraction: Claude Sonnet 4 or GPT-4o are recommended for accurately extracting structured data from unstructured text (e.g., parsing business cards, contracts, or emails).
  3. Click Save Feature Assignments.

Cost Optimization Tips

  • Use smaller, faster models for high-volume, repetitive tasks (lead scoring, sentiment analysis, classification).
  • Reserve larger, more capable models for tasks requiring nuance and creativity (email drafting, content generation).
  • Monitor your AI usage under Settings → Usage → AI Usage to track token consumption and costs by feature.
  • Set monthly spending limits per provider under Settings → Integrations → AI Providers → Spending Limits.
  • Consider using Groq for latency-sensitive features like live chat assistance, where response speed matters most.

Advanced Configuration

Custom API Endpoints

If you are using a self-hosted model or an API-compatible proxy, you can configure custom endpoints:

  1. Navigate to Settings → Integrations → AI Providers → Custom Provider.
  2. Click Add Custom Provider.
  3. Enter the following details:
    • Provider Name: A descriptive name for the custom provider.
    • Base URL: The API endpoint (must be OpenAI-compatible, i.e., support the /v1/chat/completions format).
    • API Key: Your authentication key for the custom endpoint.
    • Available Models: Enter the model identifiers available at this endpoint.
  4. Click Test Connection and then Save.

Temperature and Token Settings

Fine-tune AI behavior for each feature:

  1. Navigate to Settings → Integrations → AI Providers → Advanced Settings.
  2. Adjust the following parameters per feature:
    • Temperature: Controls randomness. Lower values (0.1-0.3) produce more consistent, predictable outputs. Higher values (0.7-1.0) produce more creative, varied outputs. Default is 0.5.
    • Max Tokens: Limits the length of AI-generated responses. Set this based on the expected output length for each feature.
    • System Prompt: Customize the system prompt used for each feature to align AI output with your brand voice and business context.
  3. Click Save Advanced Settings.

Testing AI Features

  1. Test email drafting: Open a contact record, click Compose Email, and use the AI Draft button. Verify the generated draft is relevant and well-written.
  2. Test lead scoring: Create a new contact with sample data and check the AI-generated lead score under the contact profile.
  3. Test summarization: Open a contact with a long conversation history and click Summarize Conversation. Verify the summary captures key points.
  4. Test sentiment analysis: Send a test message to a contact conversation and check the sentiment indicator (positive, neutral, negative) displayed next to the message.

Troubleshooting

API Key Rejected

  • Verify the API key is correct and complete (no trailing spaces or missing characters).
  • Check that your AI provider account is active and has billing configured.
  • Ensure the API key has not been revoked or expired.
  • For OpenAI, verify your organization has not exceeded its usage quota.

Slow AI Responses

  • Consider switching to a faster model (e.g., Claude Haiku 3.5 instead of Claude Opus 4, or a Groq-hosted model).
  • Reduce the Max Tokens setting to limit response length.
  • Check the AI provider status page for any ongoing service issues.
  • Ensure your internet connection is stable.

AI Output Quality Issues

  • Review and customize the system prompt for the relevant feature to provide better context.
  • Adjust the temperature setting. Lower temperature produces more focused output, higher temperature adds variety.
  • Try a different model. Larger models generally produce higher quality output but at higher cost and latency.
  • Provide more context in contact records (detailed notes, conversation history) to help the AI generate better output.

Usage Costs Higher Than Expected

  • Review your usage breakdown under Settings → Usage → AI Usage.
  • Check which features are consuming the most tokens.
  • Switch high-volume features to smaller, cheaper models.
  • Set monthly spending limits to cap costs.
  • Disable AI features that are not actively providing value.

Related Articles

Last updated March 21, 2026
Was this article helpful?