Correct context is vitally important in the production of building not only AI agents, but any software systems in the agentic age. It helps combat what my old maths teacher would refer to as "rubbish in, rubbish out". In this talk we'll take a walk through the different approaches for retrieval, from naive, to agentic RAG using tools and reranking, with examples leveraging Elasticsearch.
Carly Richmond
Elastic
Carly is Developer Advocate Lead at Elastic, based in London, UK. Before joining Elastic in 2022, she spent over 10 years as a software engineer at a large investment bank, specialising in front-end web development and agility. She is a UI developer who dabbles in writing backend services, a speaker, and a regular blogger.
She enjoys cooking, photography, drinking tea, and chasing after her young son in her spare time.
She enjoys cooking, photography, drinking tea, and chasing after her young son in her spare time.
