Systems | Development | Analytics | API | Testing

Use AI and traffic replay to test AI-generated code

When I ask an AI agent to change code, I also want it to run the application and test what it changed. Asking it to write some tests is a start. But if it invents the expected responses from the same assumptions it used to write the code, those tests can miss the same mistake. Traffic replay gives the agent something concrete to test against: requests and responses captured from a working application.

AI's Impact on Automated Test Script Generation

AI-powered automated test script generation is transforming how software teams approach quality assurance. By analyzing real user behavior, code changes, and system logs, these tools reduce the time and effort needed to create and maintain tests. This shift from manual scripting to AI-generated scripts helps teams keep test coverage in sync with rapid release cycles.

Start your AI agent testing with deterministic tooling

By now everyone is aware of the limitations inherent in generative AI and the AI agents that use it to complete their tasks, and the challenges involved in getting them enterprise quality. If you are planning to incorporate AI agents into your enterprise IT architecture, how are you planning to validate their quality and accuracy?

Which AI Analyst Holds Up Best for Your Hard Questions?

Analytics vendors claim their AI answers questions accurately, but almost none of them will show you how they checked. The standard move is a percentage with no denominator: "90%+ accuracy on internal benchmarks." No dataset you can download. No scoring method you can inspect. No competitor runs under the same conditions. You're asked to trust the grade without ever seeing the exam1 We ran the exam in public terms instead.

Ep 90 | Can AI Make Sense of Pharma's Messiest Data?

Human biology is extraordinarily complex, and researchers often have only fragments of information to work with. Brian Martin compares it to looking at a skyscraper through a keyhole: you can see something clearly, but only a tiny piece of the whole. Recorded at EVOLVE26 Singapore, this episode of The AI Forecast brings Paul Muller together with Brian Martin, CTO of Applied AI at Cloudera and co-founder of Rare Hopes NFP, to explore what one of the world’s most data-intensive industries can teach us about AI and decision-making.

Automating Trust: How Business Review Management Fits Into the Modern Ops Stack

Most companies still treat reviews as a marketing chore. Someone on the team remembers, sends a batch of emails, watches a few stars roll in, and forgets about it for six weeks. That model is finished. Consumers now expect a reply within days, they discount anything written more than three months ago, and a growing share of them never read your reviews at all because an AI assistant read them first and summarized the themes. None of that can be served by a human remembering to check a dashboard.

The Smarter Safety Net: Modernizing User Acceptance Testing (UAT) with AI

Every engineering leader knows the scenario: sprint tickets are closed, unit coverage shows green across the board, API pipelines pass without a hitch, and the build is tagged "ready for release." Yet, the moment the software reaches actual business users, reality hits. A multi-tier approval workflow breaks on a regional tax calculation. An enterprise customer encounters friction during a custom bulk checkout.