Operations | Monitoring | ITSM | DevOps | Cloud

AI

Testing GenAI: How to approach nondeterministic software development

Michael Webster, principal engineer at CircleCI, talks to Rob about testing AI-enabled applications. In this episode, learn how to face the unique challenges posed by the probabilistic and non-deterministic nature of AI output, as well as the importance of subjective evaluation criteria. Webster covers how model graded evals can be used to test AI applications, and the importance of caution in using this approach.

Monitor and optimize your modern, AI-powered applications with Cisco AppDynamics

Learn how Cisco AppDynamics OpenAI API monitoring provides comprehensive insights that enable application owners and operations to optimize cost and monitor performance of OpenAI integrations. The rapid advancement of generative artificial intelligence (GenAI) has reshaped various industries and transformed the way we interact with technology. Companies across diverse sectors have fully embraced the power of GenAI to such an extent that it is now an integral part of the digital experience.

AI will empower app developers-not replace them

Despite the rise of AI, the need for app developers isn’t going away. In fact, a 2023 ServiceNow-sponsored study by Pearson suggests approximately 95,000 new application developer roles will be added globally over the next five years. According to ServiceNow’s special report on the impact of AI on tech skills, based on the research, only about 20% of app developer tasks will be either automated or augmented by 2027.

Use embedded AI to find performance problems

The root cause of a performance transaction can be complex to troubleshoot, but it does not have to be. By using AppDynamics’s built-in machine learning capabilities, we can quickly identify Health Rule violations triggered by transaction response times deviating from their baseline and then combine those with diagnostic capabilities that get us to the specific cause. We are able to drill down into the relevant snapshots to see which method and specific line of code is to blame.

Latest breakthroughs in vector search for Elasticsearch and Lucene: ElasticON AI

Elastic experts Jim Ferenzi and Ben Trent discuss key Elasticsearch and Lucene improvements — including intuitive vector search support, multi-threading, RRF, and hybrid search with filtering and doc-level security. Plus, hear what they are working on next! Additional resources.

AI-Generated Runbooks

AI-generated Runbooks lower the barrier to entry to new automation developers and speeds up the time to create new automation for experienced automation authors. This feature works seamlessly with the user’s preferred scripting language, offering a low-code solution for what used to be a high-code task. Watch how Runbook Automation users can write the task they wish to automate in plain-English and let AI build a template of automation for that particular task.