January 2023 Summaries

Aporia Labs has released a revision of its documentation, focusing on maximizing the value of ML models running in production and providing an observability platform for monitoring drift, improving model performance, and ensuring business impact. The new docs offer technical guides on effective monitoring and observability for models in production, as well as educational content on best practices and core concepts. Additionally, Aporia has partnered with Portkey to bring secure and reliable Guardrails to production.

Aporia Labs has achieved Service Organization Control (SOC) 2 Type II compliance, demonstrating its commitment to the security and reliability of its services. This is particularly important for companies in the machine learning observability space, as sensitive data may be processed and analyzed during model monitoring and improvement. By achieving SOC 2 Type II compliance, Aporia ensures that customer data is secure and protected when using their ML observability Platform. The company will continue to prioritize security and integrity of its services while growing and evolving.

Aporia Labs has introduced Direct Data Connectors (DDC), a novel way to monitor Machine Learning models in production by connecting directly to your training and inference datasets. DDC allows you to monitor without duplicating any of your data, enabling monitoring of billions of predictions without data sampling, production code changes, or hidden cloud costs. By simply connecting Aporia to a database where you already store your model predictions, you immediately get fully-customizable ML dashboards tailored to your use case, customizable drift detection, live alerting, XAI, and root-cause analysis tools at your fingertips. DDC is a transformative technology that empowers ML teams to effortlessly monitor and track their ML models by seamlessly integrating Aporia with their production database.