Systems | Development | Analytics | API | Testing

Durable Sessions: Why your AI UX keeps breaking and how to fix it

AI products today are being let down not by the models — but by the delivery layer between the agent and the user. In this session, Fiona Corden, Technical Product Manager, at Ably, breaks down why AI UX is eroding consumer trust, how to spot the delivery-layer problems hiding in your product data, and what the companies getting it right are doing differently. You'll come away knowing how to diagnose whether your AI product has a session layer problem, what durable sessions are, and why they're becoming the standard solution for resilient AI UX at scale.

AI agent streaming in action: barge-in, human handover, and session continuity

You're mid-conversation with an AI support agent. You've explained the problem, the agent is halfway through a response, and the connection drops. When you reconnect, the response is gone. You type the same question again. The agent asks the same clarifying questions again. Three minutes of context, gone. Not because the model forgot it, but because the delivery layer stored nothing.

Build a Custom OBDC Driver as a Server

With the Simba Technologies SimbaEngine SDK, you can build your own custom OBDC, OLEDB, JDBC, or ADO.NET driver to connect your data source to any application, but did you know that you can create a driver that runs on a server with the switch of a configuration setting? You can convert a SimbaEngine SDK ODBC driver into a server by switching build configurations in Visual Studio within Windows or adding BUILDSERVER=exe to your makefile in Linux, then configuring a registry or INI file.

Your Tests Passed. So Why Is Your UI Broken?

So your team just pushed a CSS update. All your functional tests pass, the deployment goes through, and everything looks fine in-browser. Two hours later, a user reports that the checkout button has disappeared on mobile. Technically, the button still works, but now it’s hidden just below the fold, so your tests had no way to flag the issue. This is what’s known as a visual regression, or visual bug, and it’s one of the most common ways UI problems slip into production unnoticed.

Why AI Agents Need a Semantic Layer (and What That Actually Means in 2026)

Everyone is racing to put an AI agent on top of their data. Almost nobody is asking whether the agent can be trusted to act on what it sees. That is the wrong order. And the way most teams are trying to fix it — bigger context windows, more reasoning, another eval — is also wrong. The generative model stopped being the hard part of agentic analytics months ago. Wiring an LLM to a warehouse is a weekend project.