| |
|
| |
| DETAILS |
|
Join Oracle & AICamp for an immersive, hands on workshop learning how to build reliable agents with LangChain & Oracle AI Database.
AI agents often feel smart in a single turn, then fall apart over longer sessions: they forget user context, repeat work, & lose track of decisions. In this interactive, hands-on workshop, you'll learn how to design & implement Agent Memory as a first-class system-turning a stateless agent loop into a stateful, memory-augmented agent that improves continuity, reliability, & believability over time.
We'll go end-to-end:
Define what Agent Memory is (and how it differs from just chat history)
Build practical memory abstractions (short-term working memory, semantic memory, episodic memory, & lightweight procedural memory)
Implement ingestion, storage, retrieval, summarization, & managed forgetting patterns
Integrate Tavily for real-time internet lookups, & use Oracle AI Database as the agent's Memory Core for unified retrieval & persistence
Apply context engineering, prompt engineering, & memory engineering techniques to reduce drift, improve grounding, & keep the agent consistent across turns
You'll leave with a working reference implementation, plus a set of reusable patterns for building scalable agent scaffolding & evaluation harnesses focused on reliability & believability.
Who should attend:
This hands-on workshop is designed for AI developers, AI engineers, AI practitioners, python developers
Prerequisite:
* Required - Fully charged laptop
* Required - Comfortable writing Python (basic to intermediate)
* Required - Familiarity with LangChain fundamentals: prompts, tools, chains, & basic agent patterns
* Required - Basic understanding of what an AI agent is (tool use + multi-step reasoning loop)
* Strongly recommended - Prior exposure to LangChain + Oracle Database integration (or willingness to follow a guided setup)
* Strongly recommended - Comfort running a local notebook / Python environment (uv/pip/conda)
* Strongly recommended - Basic SQL familiarity helps, but isn't required
What you should have installed on your laptop:
o Python 3.10+ (3.11 recommended)
o A working environment to run notebooks or scripts (Jupyter, VS Code, etc.)
o Access to an Oracle AI Database environment (will be provided in workshop)
o API keys / credentials (as applicable): 1) LLM provider key (your chosen model); 2) Tavily API key (for internet search tool)
Agenda:
- 5:30pm~6:00pm: Checkin, food & networking
- 6:00pm~6:15pm: Welcome & Community update
- 6:15pm~7:30pm: Tech talks, hands-on labs & Q&A
- 7:30pm~8:30pm: Open discussion & Closing.
Venue:
Frontier Tower, Spaceship, 995 Market St, San Francisco
Sponsors:
We are actively seeking sponsors to support AI developers community. Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 50,000+ AI developers in San Francisco Bay Area & 500K+ worldwide.
Local & Global AI Community on Discord
Join us on discord for local & global AI tech community:
- Events chat: chat & connect with speakers & global & local attendees;
- Learning AI: events, learning materials, study groups;
- Startups: innovation, projects collaborations, founders/co-founders;
- Jobs & Careers: job openings, post resumes, hiring managers;
|
|
|
|
|
|
|
|
