Gencore AI for Amazon S3

Gencore AI helps organizations rapidly build secure, enterprise-ready generative AI (GenAI) systems, copilots, and AI agents. It accelerates enterprise GenAI adoption by simplifying the creation of AI pipelines that combine structured and unstructured data with proprietary business data sourced from hundreds of enterprise systems and applications.

The platform supports any foundation model available on Google Cloud—such as Vertex AI, Gemini, and PaLM 2—as well as leading third-party models including Anthropic Claude, Meta Llama 2, Mistral, and others.

Key capabilities include:

1. Build secure enterprise AI copilots
   Quickly create AI copilots and knowledge systems by aggregating data from multiple sources. Built-in enterprise controls, AI usage monitoring, and end-to-end provenance tracking are automatically applied.

2. Safely synchronize data to vector databases
   Securely ingest and sync large volumes of data from diverse systems. Generate custom embeddings enriched with metadata to prepare enterprise data for LLM-powered use cases.

3. Curate and sanitize data for model training
   Easily assemble, cleanse, and sanitize high-quality datasets to support AI model training and fine-tuning.

4. Protect AI interactions
   A conversation-aware LLM Firewall safeguards prompts, responses, and data retrievals across AI applications.

Key features:

1. Seamless enterprise data connectivity
   Ingest data safely using hundreds of native connectors, enabling AI applications to leverage both structured and unstructured data across SaaS, on-premises, public cloud, and data cloud environments.

2. Inline controls across the AI pipeline
   Secure AI workflows with layered protections, including pre-model data sanitization, policy-enforced LLM firewalls, and continuous compliance monitoring aligned with standards such as NIST AI RMF and the EU AI Act.

3. End-to-end AI system provenance
   Gain complete visibility into data and AI usage, tracking every file, user, model, and inference endpoint.

How to load Amazon S3 data to build your GenAI pipeline:

1. Select Amazon S3 as the data source.

2. Choose the relevant bucket or system attributes.

3. Define the scope for Amazon S3 data.

4. Apply optional filters, such as object prefix, name (regex), tags, extension category, extensions, size, or last modified date.

5. Click Save and Continue to proceed to the Data Sanitizer stage.