Speaker
Abstract
AI agents are a perfect fit for serverless environments, as they can leverage the power of the cloud and the edge for fast and accurate decision making. It is often the case that AI applications do not require the costly vector database and compute solutions which are often used today, to store and process data. In this talk, I will show you:
- How to design useful AI agents
- Effective use of vector storage and AI models in the browser and at the edge
- Performance considerations for AI driven web based experiences
If you are interested in learning how to build useful and accurate AI agents with minimal engineering overhead, join me in this session.
AI agents are a perfect fit for serverless environments, as they can leverage the power of the cloud and the edge for fast and accurate decision making. It is often the case that AI applications do not require the costly vector database and compute solutions which are often used today, to store and process data. In this talk, I will show you:
- How to design useful AI agents
- Effective use of vector storage and AI models in the browser and at the edge
- Performance considerations for AI driven web based experiences
If you are interested in learning how to build useful and accurate AI agents with minimal engineering overhead, join me in this session.
Sponsored session
Session Sponsored By
Build, deploy, and deliver trusted applications everywhere with Cloudflare’s Developer Platform.
QCon San Francisco 2023 is a three day conference for senior software engineers, architects and team leads. An international program committee of working engineers selects every session. Patterns and practices, not products and pitches.
Part of the track
Sponsored Solutions Track IVFrom the same track
Wednesday 4 October
10:35 Pacific LM Sponsored Designing AI Agents with System Thinking Logan Grasby Founder @Azule.ai AI agents are a perfect fit for serverless environments, as they can leverage the power of the cloud and the edge for fast and accurate decision making. It is often the case that AI applications do not require the costly vector database and compute solutions which are often used today, to… 11:45 Pacific LM Sponsored Can’t Apps and Databases All Just Get Along? Joshua Hight Software Engineer @Stytch Availability is a tricky thing. In order for your tier 0 endpoints to be available all their hard dependencies have to be available. For Stytch that means basically network, compute, database, and messaging providers. 13:35 Pacific LM Sponsored Introduction to Real-Time Training and Scoring in AI/ML Wes Wagner Solutions Engineer @Redpanda In the rapidly evolving landscape of AI/ML, the shift from batch to real-time data processing is significant. It impacts how quickly and dynamically we can learn from data, leading to more responsive AI applications. 14:45 Pacific LM Sponsored Simple Platform Engineering and Simply High Cardinality Observability Piyush Verma Co-Founder and CTO @Last9 Platform engineering transforms repetitive Engineering requirements into standardised and dependable services, or "paved roads". These paved roads offer engineering teams a smooth way to develop and deploy business logic layers continuously. 15:55 Pacific LM Sponsored LLMs + Knowledge Graphs = Better Together Mark Quinsland Senior Field Engineer @Neo4j LLMs are often like the know-it-all at a bar - they can quickly and confidently produce realistic sounding answers to just about any question - even if the answers are complete fabrications.