Systems | Development | Analytics | API | Testing

Custom AI agents via MCP (Model Context Protocol) let an autonomous QA system reach beyond its built-in skills by connecting to external tools such as GitHub and browser automation services. In practice, that means a QA agent can inspect source code changes, identify new features, compare them against existing test coverage, and create missing test cases automatically. For teams managing growing test suites, this turns AI from a closed assistant into a connected workflow engine.

Your AI agent is mid-task, waiting on the result of a search tool call it made 30 seconds ago. The user is watching a spinner. Then a network blip drops the connection. The application reconnects in under a second, fast enough that most monitoring wouldn't flag it. But the tool call result that came back during the gap is gone, and so are the 200 tokens the agent generated before the silence began. The reconnect succeeded - but the session didn't.

Generative AI for QA is the use of large language models to accelerate the creation and analysis of testing artifacts — drafting test cases, summarizing requirements, and generating synthetic test data. AI agents extend that capability into multi-step autonomous workflows that plan, delegate, and execute testing tasks across an entire delivery pipeline. For SDETs, the shift is not about learning to prompt more cleverly.

The question isn't whether to use AI in QA. It's knowing exactly where to keep a human in control. The core risk: Over 75% of multi-agent failures are silent semantic errors that pass automated checks but violate business logic — detectable only by human inspection (Cemri, Pan et al., NeurIPS 2025). The division of labor: AI owns repetitive generation and execution; humans own risk analysis, requirement interpretation, exploratory investigation, and final sign-off. The operational discipline.

Earlier this year, our team launched the N|Solid Extension, a Node.js production debugging and observability tool designed for modern development environments. The goal was simple: help developers investigate production issues without constantly switching between dashboards, monitoring platforms, and their editor. Instead, runtime telemetry, diagnostics, security insights, and AI-assisted workflows could live directly where developers already spend most of their time.

Your customers are no longer comparing you to the bank down the street. They are comparing you to Amazon, Netflix, and every hyper-personalized digital experience they interact with daily. And most banks are losing that comparison. Quite literally! Somewhere between the legacy core systems, the compliance overhead, and the quarterly earnings pressure, a tectonic shift has started. Agentic AI is no longer a concept in a research paper.

NERSC, the mission high-performance computing center for the U.S. Department of Energy Office of Science, is using ClearML as part of the AI infrastructure stack for Perlmutter, the upcoming Doudna supercomputer, and the broader American Science Cloud. Here is a look at what they are exploring and why it matters for AI for science at scale.

Each change to Kong Gateway's codebase triggers a comprehensive test suite that runs more than 17,000 * 2 = 34,000 test cases among the two primary architectures (x86 and ARM) we support. This process takes about 23.5 hours on a single machine. But we don't wait that long. A large fleet of machines runs the suite in parallel, and we shard the work aggressively so each commit finishes in a fraction of that time. That setup works well, right up until flaky tests get involved.