Systems | Development | Analytics | API | Testing

The AI-analytics category has one operating assumption: AI’s job is to do more of what humans currently do. Adoption is measured by delegation surface. Success is when AI takes the whole task. Ask the executives running AI daily what they refuse to delegate, and you get a different story. Actually, you get the same story, from operators who do not know each other, running different companies, across different functions.

This fall, Tosca’s suite of AI capabilities will be available for on-premises deployments — giving teams the tools to meet the pressure of the AI era head-on. Customers will gain access to leading AI features, including Agentic Test Automation, AI-powered test creation, MCP connectivity, and AI Workspace, no matter their deployment type or existing infrastructure. AI’s unprecedented development means testing practices that were standard a year ago could already be outdated.

A Head of Product at a major sportswear retailer has a brilliant idea: let’s build an app that sales staff on the shop floor can have on their tablets, and ask their questions there and then, where they serve customers. They set about building. In order for the app to answer questions, it needs to have the information from the 2026 Spring/Summer Catalogue, a mammoth manual, let’s say 300k tokens.

Steering lets a client redirect an agent while the agent is still working, so a follow-up message reshapes the answer in flight instead of cancelling the Run and starting over, or waiting for it to finish. In the AI Transport SDK, a Run encapsulates the agent's output for a single turn (including multiple iterations around an agentic loop). The last release, v0.5.0, made a single agent turn survive a crash by splitting a Run into re-attemptable Steps.

As many other data teams do, we have a dedicated Slack channel (#data) where the whole company can ask data-related questions that get picked up by a designated, weekly-rotated data analyst (data mage). It can become tiresome quickly as the questions are fairly repetitive and it takes away precious time from other high-impact tasks. The team built clean, well-documented marts and reports in Metabase that are used regularly, but these were still missing something that makes reporting truly self-service.