AI Core

Core AI infrastructure module that provides AI provider management, request routing, usage tracking, and foundational services for all AI-powered features in the platform.

Features

• AI Provider Management - Configure and manage multiple AI providers (OpenAI included by default; Gemini, Local AI available as addons)
• AI Model Management - View, configure, and test available AI models per provider
• Module-Model Mapping - Assign specific AI models to specific modules for fine-grained control
• Usage Analytics - Monitor AI usage, costs, and performance across all modules with export capability
• Request Logging - Full audit log of all AI requests with filtering, flagging, and review
• AI Settings - System-wide settings for AI features including rate limiting, cost controls, caching, and security
• AI Dashboard - Overview of AI activity and statistics

Requirements

Requirement	Details
Dependencies	SystemCore
PHP Version	8.2+
AI Provider	At least one AI provider configured (OpenAI included by default)

Installation

AI Core is a core module that is always enabled when purchased. It cannot be toggled on or off as other AI modules depend on it.

After installation, configure at least one AI provider with valid API credentials and set default provider preferences for different modules.

Configuration

AI Settings

Navigate to AI Core > Settings to configure:

General:

• Enable AI Features - Enable or disable AI functionality system-wide
• Default Temperature - Default creativity level for AI responses (0-2)
• Default Max Tokens - Default maximum tokens for AI responses
• Request Timeout - Maximum time to wait for AI API responses
• Daily Token Limit - Maximum tokens per day per company (0 = unlimited)

Cost Controls:

• Monthly Budget (USD) - Maximum monthly spending on AI services (0 = unlimited)

Rate Limiting:

• Enable Rate Limiting - Enable rate limiting for AI requests
• Global Rate Limit - Maximum requests per minute system-wide
• User Rate Limit - Maximum requests per minute per user

Security:

• Log AI Requests - Log all AI requests for monitoring and debugging
• Data Retention (days) - How long to keep AI request logs (0 = forever)

Cache:

• Enable Response Caching - Cache AI responses for similar requests
• Cache TTL (seconds) - How long to cache AI responses

Provider Management

Navigate to AI Core > Providers to manage AI providers. You can add, edit, test, and remove providers. Each provider can be tested for connectivity.

Model Management

Navigate to AI Core > Models to view and manage AI models. You can test individual models and configure their settings.

Module-Model Configuration

Navigate to AI Core > Module Configuration to assign specific AI providers and models to individual modules. You can sync available modules, toggle module AI status, and select which provider/model each module should use.

Usage

Dashboard

Navigate to AI Core > Dashboard to view an overview of AI activity across your platform, including:

• Total active providers and models
• Usage statistics for today, this week, and this month (requests, tokens, cost)
• Provider connection status
• Recent AI activity log
• Cost trends over the last 30 days
• Top models by usage

Managing Providers

Navigate to AI Core > Providers to manage AI providers:

• View all enabled providers and their associated models
• Add a new provider by selecting a type and entering API credentials
• Edit existing provider settings (name, API key, endpoint URL, rate limits, cost per token, priority)
• Test provider connectivity to verify API keys are valid
• View available provider addons that can be installed (e.g., Gemini Provider, Local AI Provider)

Managing Models

Navigate to AI Core > Models to view and manage AI models:

• Browse all available models across providers
• Test individual models to verify they are working
• Configure model settings

Module-Model Configuration

Navigate to AI Core > Module Configuration to control which AI provider and model each module uses:

• Sync Modules - Detect all AI-enabled modules in the system
• Toggle Status - Enable or disable AI for individual modules
• Assign Provider/Model - Select which provider and model each module should use
• Per-Module Control - Fine-grained control over AI behavior across different features

Usage Analytics

Navigate to AI Core > Usage to monitor AI usage:

• View summary statistics (total requests, tokens, cost, average response time, success rate)
• Filter by time period, provider, or module
• View usage trends over time with charts
• See module-level and provider-level cost breakdowns
• Browse recent usage logs with details
• Export usage data as JSON reports

Request Logs

Navigate to AI Core > Logs to audit AI requests:

• Browse all AI request logs with DataTable filtering
• View detailed information for individual requests
• Flag suspicious or noteworthy requests for review
• Mark requests as reviewed
• Export logs
• View log statistics

Settings

Navigate to AI Core > Settings to configure system-wide AI settings. See the Configuration section below for details. Settings can be reset to defaults if needed.

Available Provider Addons

AI Core includes OpenAI as the default provider. Additional providers are available as separate addons:

• Gemini Provider - Google Gemini AI models integration
• Local AI Provider - Run AI models locally with Ollama, LM Studio, LocalAI, or vLLM

AI-Powered Modules

The following modules use AI Core for their AI capabilities:

• HR Assistant - AI-powered HR support and knowledge management
• Sales Assistant - Lead scoring, pipeline analysis, and sales forecasting
• Finance Assistant - Financial analysis and expense insights
• Reporting AI - Natural language to SQL reporting
• AI Chat - General-purpose AI chat interface
• Auto Description - AI-generated content descriptions
• Document AI - AI-powered document processing

Included OpenAI Models

AI Core comes with OpenAI provider pre-configured. Available models:

Model Family	Models	Description
GPT-5.2 Series	gpt-5.2-instant, gpt-5.2-thinking, gpt-5.2-pro, gpt-5.2-codex	Latest GPT models with 400K context
o3 Series	o3-pro, o3, o3-mini, o4-mini	Advanced reasoning models
GPT-4.1 Series	gpt-4.1, gpt-4.1-mini, gpt-4.1-nano	1M token context models
GPT-4o Series	gpt-4o, gpt-4o-mini	Multimodal with vision/audio
Embeddings	text-embedding-3-large, text-embedding-3-small	Semantic search
Image	dall-e-3, dall-e-2	Image generation
Audio	whisper-1, tts-1, tts-1-hd	Transcription & text-to-speech

Web Routes

Method	Route	Description
GET	/aicore/dashboard	AI Dashboard
GET	/aicore/providers	List providers
POST	/aicore/providers/{provider}/test	Test provider connection
GET	/aicore/models	List models
POST	/aicore/models/{model}/test	Test a model
GET	/aicore/usage	Usage analytics
GET	/aicore/usage/export	Export usage data
GET	/aicore/settings	AI settings
PUT	/aicore/settings	Update settings
GET	/aicore/module-configuration	Module-model mapping
GET	/aicore/logs	Request logs

API Endpoints

Method	Endpoint	Description
POST	/api/ai/chat	Send chat request
POST	/api/ai/complete	Send completion request
POST	/api/ai/summarize	Summarize content
POST	/api/ai/extract	Extract data from content
GET	/api/ai/usage	Get usage statistics

Admin-only endpoints (requires admin or super_admin role):

Method	Endpoint	Description
GET	/api/ai/admin/providers	List providers
POST	/api/ai/admin/providers/{provider}/test	Test provider connection
GET	/api/ai/admin/providers/{provider}/usage	Get provider usage
GET	/api/ai/admin/usage/reports	Usage reports
GET	/api/ai/admin/usage/trends	Usage trends

Notes

• AI Core is the foundation for all AI-powered modules
• OpenAI provider is included; additional providers (Gemini, Local AI) are available as separate addons
• Usage is tracked and can be limited per user or system-wide
• All AI interactions are logged for audit purposes when request logging is enabled
• Rate limiting protects against excessive API usage

---

Changelog: View version history