Operations | Monitoring | ITSM | DevOps | Cloud

Elastic’s innovative investments to support an open ecosystem and a simpler developer experience In this blog, we want to share the investments that Elastic® is making to simplify your experience as you build AI applications. We know that developers have to stay nimble in today’s fast-evolving AI environment. Yet, common challenges make building generative AI applications needlessly rigid and complicated. To name just a few.

AI-related announcements dominate once more. New models for Bedrock. Vector search everywhere, and DynamoDB does a bait-and-switch. Welcome to day 3 of re:Invent 2023.

When OpenAI released ChatGPT on November 30, 2022, no one could have anticipated that the following 6 months would usher in a dizzying transformation for human society with the arrival of a new generation of artificial intelligence. Since the emergence of deep learning in the early 2010s, artificial intelligence has entered its third wave of development. The introduction of the Transformer algorithm in 2017 propelled deep learning into the era of large models.

We are pleased to share a sneak peek of Query Assistant, our latest innovation that bridges the world of declarative querying with Generative AI. Leveraging our large language models (LLMs), Coralogix’s Query Assistant translates your natural language request for insights into data queries. This delivers deep visibility into all your data for everyone in your organization.

We had the opening keynote by Adam Selipsky. If you missed the live stream, you can watch it on YouTube here. Unsurprisingly, so much of the keynote was about AI.

For modern enterprises aiming to innovate faster, gain efficiency, and mitigate the risk of failure, operational resilience has become a key competitive differentiator. But growing complexity, noisy systems, and siloed infrastructure have created fragility in today’s IT operations, making the task of building resilient operations increasingly challenging.

Does this sound familiar? The incident has just been resolved and management is putting on a lot of pressure. They want to understand what happened and why. Now. They want to make sure customers and internal stakeholders get updated about what happened and how it was resolved. ASAP. But putting together all the needed information about the why, how, when, and who, can take weeks. Still, people are calling and writing. Nonstop.

Ever since we launched Query Assistant last June, we’ve learned a lot about working with—and improving—Large Language Models (LLMs) in production with Honeycomb. Today, we’re sharing those techniques so that you can use them to achieve better outputs from your own LLM applications. The techniques in this blog are a new Honeycomb use case. You can use them today. For free. With Honeycomb.