Does it modify my data?
No. The Agentic Query Layer is read-only. It queries through existing APIs and never writes anything back, so it's safe to run against production systems.
The Agentic Query Layer (AQL) translates natural language questions into secure, permission-aware queries against your existing systems — without exposing your data to AI models.
Core is open source. Advanced reporting tools available via modest subscription.
The AQL sits between your data sources and your AI models. You ask questions in plain language. The layer translates intent into safe, auditable queries, executes them against your systems, and returns structured results with context and suggested follow-ups.
Install the core AQL for Moodle LMS today. Use basic functions immediately at no cost.
Premium plugins and composite reporting tools available through modest subscriptions or self-hosted.
Already in use by training providers, educational institutions, and government agencies.
No. The Agentic Query Layer is read-only. It queries through existing APIs and never writes anything back, so it's safe to run against production systems.
No. It works with standard Web Services / API access. You enable the API and create a token. There is no custom plugin required on the source system.
Any MCP-compatible client or model path, including Claude, GPT, Gemini, and local models through Ollama or llama.cpp.
Yes. Paired with a local model, the entire stack can run on your own hardware so sensitive data never leaves your network.