Enterprise AI Agents, Java Client v6 Release, and Gemini 3 Integration

Hello Weaviate Community! 🤗

Enterprise AI agents are drastically changing how companies work with their knowledge bases. That’s why this week, we’re diving into how StackAI uses Weaviate to power intelligent agents across industries, announcing the general availability of our redesigned Java Client v6. Plus, learn how to build AI agents with long-term memory using LlamaIndex, Gemini 3, and Weaviate.

How StackAI Uses Weaviate to Power Enterprise-Grade AI Agents

What gives enterprise AI agents instant access to company knowledge?

For StackAI’s no-code platform, the answer is Weaviate.

StackAI uses Weaviate as the vector backbone for every knowledge base. When customers upload internal documents (PDFs, proposals, research, contracts) the embeddings and vector indices are stored and managed through Weaviate, giving their AI agents a reliable, scalable retrieval layer for RAG workflows.

One recent example comes from a global civil engineering firm that uses StackAI to accelerate proposal writing. Their Proposal Reference Agent searches hundreds of historical proposals, retrieves the most relevant sections through Weaviate, and sends a concise, context-aware report directly to the drafter. Instead of manually digging through years of documents, teams get grounded guidance in seconds.

Across financial services, defense, insurance, and healthcare, StackAI and Weaviate empower enterprises to deploy AI agents that reason, retrieve, and take action.

🛠️ Try the Proposal Reference Agent Template

📄 Read the Full StackAI Case Study

Latest AI & tech insights

Explore our recent Weaviate content:

Read

• ✍️ AWS 2025 Rising Star Technology Partner: Weaviate recognized by AWS Partners in Benelux as leaders in helping customers drive innovation. Read the blog

• 🥳 Announcing the new Weaviate Java Client v6: The Weaviate Java client v6 is now generally available! This release brings a completely redesigned API that embraces modern Java patterns, simplifies common operations, and makes working with vector databases more intuitive than ever. Read the blog

• 🍳 Memory with LlamaIndex, Weaviate, and Gemini: This notebook shows you how you can give your AI agent long-term memory with LlamaIndex, Weaviate, and Gemini. Learn how

Watch

• 📽️ Gemini 3 is already available in Weaviate: Victoria breaks down how Google's EmbeddingGemma achieves state-of-the-art performance at just 308M parameters—outperforming models nearly double its size and proving that smart architecture beats raw scale.

  • Watch the video

  • Read more about Weaviate + Gemini

Company updates

We are very happy to share that we are welcoming Colton, joining us from Arizona 🇺🇸 as a Product Support Engineer.

Hungry for more?

Have a question or want to connect? Say hi in the Community Slack or join our Weaviate Forum to engage in community conversations.

Follow our Blog, LinkedIn, Twitter, and YouTube for more content updates.

See you in two weeks,

Femke