Operations | Monitoring | ITSM | DevOps | Cloud

Datadog on LLMs: From Chatbots to Autonomous Agents

As companies rapidly adopt Large Language Models (LLMs), understanding their unique challenges becomes crucial. Join us for a special episode of "Datadog On LLMs: From Chatbots to Autonomous Agents," streaming directly from DASH 2024 on Wednesday, June 26th, to discuss this important topic. In this live session, host Jason Hand will be joined by Othmane Abou-Amal from Datadog’s Data Science team and Conor Branagan from the Bits AI team. Together, they will explore the fascinating world of LLMs and their applications at Datadog.

Datadog acquires Quickwit

Organizations in financial services, insurance, healthcare, and other regulated industries must meet stringent data residency, privacy, and regulatory requirements while maintaining full visibility into their systems. This becomes challenging when logs need to remain at rest in customers’ environments or specific regions, hindering teams’ ability to attain seamless observability and insight.

Kickstart your investigations and reduce alert noise with Doctor Droid's offering in the Datadog Marketplace

Being an on-call engineer is often overwhelming, requiring you to pivot between tickets, dashboards, runbooks, and different data sources as you try to separate legitimate incidents from unnecessary noise. Not only does the process of investigating irrelevant alerts take time away from remediating important issues, but it also compounds alert fatigue.

Tools for collecting and monitoring key Snowflake metrics

In Part 1 of this series, we looked at how Snowflake enables users to easily store, process, analyze, and share high volumes of structured and semi-structured data, as well as key metrics for monitoring compute costs, storage, and datasets. In this post, we’ll walk through how to collect and analyze these metrics using Snowsight, Snowflake’s built-in web interface.

Key metrics for monitoring Snowflake cost and data quality

Snowflake is a self-managed data platform that enables users to easily store, process, analyze, and share high volumes of structured and semi-structured data. One of the most popular data platforms on the market, Snowflake has gained widespread adoption because it addresses a range of data challenges with a unified, scalable, and high-performance platform. Snowflake’s flexibility enables users to handle diverse workloads, such as data lake and data warehouse integration.

How to monitor Snowflake performance and data quality with Datadog

In Part 2 of this series, we looked at Snowflake’s built-in monitoring services for compute, query, and storage. In this post, we’ll demonstrate how Datadog complements and extends Snowflake’s existing monitoring and data visualization capabilities, enabling teams to get deeper visibility and extract more valuable insights from their Snowflake data.

Monitor your multi-cloud costs with Cloud Cost Management and FOCUS

Monitoring cloud costs can be complex. When those costs span more than one cloud service provider (CSP) or SaaS provider, that complexity can make it difficult to understand your overall spending. Datadog Cloud Cost Management (CCM) enables teams to understand cloud costs, but each provider tags its cost data differently. Teams need to understand each provider’s unique cost data model before they can make sense of their costs in each cloud.

Monitor your Google Gemini apps with Datadog LLM Observability

Google’s comprehensive AI offering includes Vertex AI, a cloud-based platform for building and deploying AI applications, AI Studio, a web platform for quickly prototyping and testing AI applications, and Gemini, their multimodal model. Gemini offers advanced capabilities in image, code, and text generation and can be used to implement chatbot assistants, perform complex data analysis, generate design assets, and more.

Track AI Costs with Datadog Cloud Cost Management for OpenAI! Learn More on TMiDD! #AI #CloudCost

On This Month in Datadog, we’re spotlighting Datadog Cloud Cost Management for OpenAI, which enables you to break down costs by project and organization, as well as by individual model and their token consumption.