{"id":53392,"date":"2023-12-22T09:30:05","date_gmt":"2023-12-22T14:30:05","guid":{"rendered":"https:\/\/sdtimes.com\/?p=53392"},"modified":"2023-12-28T11:24:31","modified_gmt":"2023-12-28T16:24:31","slug":"what-ai-can-and-cant-do-for-your-observability-practice","status":"publish","type":"post","link":"https:\/\/sdtimes.com\/ai\/what-ai-can-and-cant-do-for-your-observability-practice\/","title":{"rendered":"What AI can and can\u2019t do for your observability practice"},"content":{"rendered":"

Artificial intelligence (AI) and large language models (LLMs) have dominated the tech scene over the past year. As a byproduct, vendors in nearly every tech sector are adding AI capabilities and scrambling to promote how their products and services use it.\u00a0<\/span><\/p>\n

This trend has also made its way to the observability and monitoring space. However, the AI solutions coming to market often feel like putting a square peg in a round hole. While AI can significantly impact certain areas of observability, it is not a fit for others. In this article, I\u2019ll share my views on how AI can and cannot support an observability practice – at least right now.<\/span><\/p>\n

The Long Tail of Errors<\/span><\/h2>\n

The very nature of observability makes \u2018prediction\u2019 in the traditional sense unfeasible. In life, certain \u2018act of God\u2019 types of events can impact business and are impossible to predict – weather-related events, geopolitical conflicts, pandemics, and more. These events are so rare and capricious that it\u2019s implausible to train an AI model to predict when one is imminent.<\/span><\/p>\n

The long tail of potential errors in application development mirrors this. In observability, many errors may happen only once, such that you may never see them happen again in your lifetime, while other types of errors may occur daily. So, if you\u2019re looking to train a model that will completely understand and predict all the ways things could go wrong in an application development context, you\u2019re likely to be disappointed.<\/span><\/p>\n

Poor Quality Data<\/span><\/h2>\n

Another way that AI needs to improve in observability is its inability to make a distinction between details that are irrelevant, and those that are not. In other words, AI can pick up on small, inconsequential aberrations with a big impact on your results.<\/span><\/p>\n

For example, previously, I worked with a customer training an AI model with hours of basketball footage to predict successful versus unsuccessful baskets. There was one big issue: all footage of an unsuccessful basket included a timestamp on the video. So, the model determined timestamps have an impact on the success of a shot (not the result we were looking for).<\/span><\/p>\n

Observability practices often work with imperfect data \u2013 unneeded log contents, noisy data, etc. When you introduce AI without cleaning up this data, you create the possibility of false positives \u2013 as the saying goes, \u201cgarbage in and garbage out.\u201d Ultimately, this can leave organizations in a more vulnerable position of alert fatigue.<\/span><\/p>\n

Where AI <\/span>Does <\/span><\/i>Fit Observability<\/span><\/h2>\n

So, where should we be using AI in observability? One area where AI can add a lot of value is in baselining datasets and detecting anomalies. In fact, many teams have been using AI for anomaly detection for quite some time. In this use case, AI systems can, for example, understand what \u201cnormal\u201d activity is across different seasonalities and flag when it detects an outlier. In this way, AI can give teams a proactive heads-up when something may be going awry.<\/span><\/p>\n

Another area where AI can be helpful is by shortening the learning curve when adopting a new query language. Several vendors are currently working on natural language query translators driven by AI. A natural language translator is an excellent way to lower the entry barriers when using a new tool. It frees up practitioners to focus on the flow and the practice itself rather than the pipes, semicolons, and all other nuances that come with learning a new syntax.<\/span><\/p>\n

What to Focus on Instead<\/span><\/h2>\n

Whether beginning a journey with AI or making any other improvement, understanding usage trends is essential to optimizing the value of an observability practice. Improving a system without understanding its usage is akin to throwing darts in a pitch-black room. If no one uses the observability system, it\u2019s pointless to have it. Many different analytics can help you know who\u2019s using the system and, conversely, who isn\u2019t using the system that should be.<\/span><\/p>\n

Practitioners should focus on usage related to the following:<\/span><\/p>\n