Fine-Tuning

The process of training a pre-built AI model on your specific data to improve its performance for your particular use case. Verabase uses RAG instead, which is faster and doesn't require model retraining.

Technical definition

Fine-tuning involves updating the weights of a pre-trained language model using a domain-specific dataset. The model trains on labeled examples (question → ideal answer pairs) through gradient descent over multiple epochs. While this can improve performance for narrow tasks, it requires curated training data, compute resources, and creates a new model version that must be maintained separately from the base model.

How Verabase uses Fine-Tuning

Verabase deliberately does not use fine-tuning. Instead, it relies on RAG (Retrieval-Augmented Generation) to ground AI responses in your knowledge base. This design choice means you never need to retrain a model when your documentation changes — you simply update your knowledge base and the AI immediately has access to the new information. RAG is faster to set up, cheaper to operate, and easier to debug than fine-tuning.

Why it matters for support teams

Fine-tuning creates a frozen snapshot of your knowledge at training time. When your product changes, you need to retrain. RAG solves this by keeping the knowledge layer separate from the AI model — updates are instant, and you can always trace which document an answer came from. For most support use cases, RAG outperforms fine-tuning in both accuracy and maintainability.

Related terms

How Verabase Handles Self-Healing Knowledge

The standard industry approach relies on support agents manually flagging stale content and technical writers updating documentation weeks later. Verabase completely upends this model through an autonomous AI platform that identifies knowledge gaps the moment an AI agent encounters a question it cannot answer.

Rather than requiring manual intervention, our visual RAG engine drafts a proposed fix. It analyzes the context of the user's question, reviews your existing knowledge base for conflicts, and creates a clear, structured article or snippet. All you need to do is click 'Approve'. This ensures your AI agents continually get smarter over time without adding to your support team's workload.

Security First Architecture

Many legacy platforms bolt AI onto their existing infrastructure, creating potential data leaks between tenants or exposing sensitive internal documents to end-users. Verabase is built from the ground up with a Bring Your Own Key (BYOK) architecture, enterprise-grade access controls, and strict semantic boundaries. This means your private engineering documents never accidentally leak into customer-facing agent responses.