🧠 Stop Building Goldfish Agents: Build Real Memory with Oracle AI Database

Presented by: Oracle, LangChain & MLOps Community

---

🎯 About This Workshop

Tired of AI agents that lose all context the moment a session ends? This hands-on engineering session — co-hosted by Oracle, LangChain, and the MLOps Community — is designed for builders who are ready to move beyond forgetful demos and into production-ready AI systems.

Attendees will construct a Python-based AI agent with persistent memory, powered by Oracle AI Database — a platform combining structured data, vector search, and scalable database capabilities. The core focus is a practical memory pipeline:

Extract → Store → Retrieve → Inject → Forget

Using both structured memory and vector-based semantic recall, you'll engineer agents capable of retaining meaningful context across multiple interactions. You'll also learn how to encode facts, events, and user preferences; design smart retrieval logic that surfaces the right context at the right time; and apply lightweight forgetting strategies to keep memory sharp rather than noisy.

No hype — just technical depth, hands-on code, and production-minded engineering. 💻

---

🗓️ Agenda

Time	Session
⏰ 5:00 PM – 5:40 PM	🚪 Doors Open & Registration — check-in, refreshments, networking, and technical setup
🎤 5:40 PM – 5:50 PM	👋 Welcome & Opening Remarks — workshop goals, structure, and technical overview
🛠️ 5:50 PM – 6:55 PM	💡 Hands-On Workshop Part 1 — build the foundations of a memory-aware AI agent using Python and Oracle AI Database, including structured memory, storage design, and persistent memory architecture
🎓 6:55 PM – 7:30 PM	🔑 Technical Masterclass Keynote — Colin Francis from LangChain leads a deep dive into Memory Engineering for production AI agents
🛠️ 7:30 PM – 8:40 PM	⚙️ Hands-On Workshop Part 2 — implement semantic recall, retrieval logic, memory injection, and forgetting strategies
🎉 8:40 PM – 9:00 PM	🤝 Wrap-Up, Q&A & Networking — technical Q&A and next steps

---

🎁 What You'll Walk Away With

• ✅ A fully working memory-aware AI agent
• 📓 A reusable notebook and starter repository
• 🔧 Practical patterns for persistent agent memory
• 🏗️ A stronger foundation for building production-ready AI systems

---

👥 Who Should Attend

• 🤖 ML and AI engineers
• 🖥️ Backend engineers building AI-powered applications
• 🧩 Technical leads designing agent systems
• 🔨 Builders who want agents that remember, not just respond

---

📋 Prerequisites

• Comfortable working with Python and Jupyter Notebooks
• An OpenAI API key (or use the provided alternative)
• Familiarity with LangChain or LlamaIndex is helpful but not required

---

🎟️ Register Now

Seats are limited — secure your spot today!

👉 Register here