A hybrid automation framework that allows teams to combine deterministic testing with agentic AI on real devices

NEW YORK — February 17,2026 — Witbe (Euronext Growth – FR0013143872 – ALWIT) today announced the launch of Agentic SDK, a new test automation framework designed to help video service providers build, operate, and scale agentic automation across video workflows—from testing and validation to monitoring—while keeping automation grounded in deterministic logic and real-device behavior. The framework dramatically reduces onboarding time, minimizes ongoing test maintenance, and enables automation to handle unplanned UI changes and human-like content assertions autonomously.

Rather than replacing existing automation with fully autonomous AI, Agentic SDK introduces a hybrid model that allows teams to apply agentic AI selectively, where it adds value, while preserving the reliability, transparency, and repeatability required in production environments.

Scaling automation across devices, apps, and markets

When automation meets real-world complexity, teams are forced to rethink how testing and monitoring are designed and scaled. As video services expand across hundreds of applications, devices, operating systems, and markets, automation must handle constant variability while still delivering precise, repeatable results.

AI adds the flexibility needed to navigate changing interfaces and unpredictable conditions, while deterministic logic anchors automation in trusted validation and measurable KPIs. Combining both within a single governed framework enables automation to scale across complex workflows while reducing manual intervention, and the long-term cost of maintaining test scripts and regression tests across releases.

Witbe Agentic SDK was built to address these challenges by providing a structured way to introduce agentic AI into automation workflows without sacrificing determinism or observability.

One platform, multiple paths to automation

Agentic SDK was designed as a single automation platform that teams can adopt according to their needs. Organizations can run simple, one-off goal-based tests, introduce more complex measurements through preset scenarios with hybrid continuous execution, and ultimately customize workflows deeply using a python based, AI-native SDK all within the same framework.

This approach enables teams with varying levels of skills, maturity and expertise to work from a common foundation without forcing a one-size-fits-all automation model.

From goal-based automation to immediate results

For teams getting started with automation or running ad-hoc validation, the Agentic SDK supports goal-based execution driven by agentic AI. Users can describe a test objective in plain language, allowing the system to generate, execute, and analyze tests automatically on real devices.

This mode is designed for fast exploratory testing, release validation, and non-continuous QA workflows, delivering immediate results without scripting, complex setup, or ongoing framework maintenance—allowing teams to move from onboarding to first results in a matter of days rather than weeks or months. Teams can edit or refine generated steps as needed, while agentic execution handles navigation and adaptation during test runs.

Hybrid execution with pre-built, trusted scenarios

For continuous testing and operational workflows, Agentic SDK provides pre-built scenarios based on Witbe’s domain expertise in video QA and monitoring. These scenarios deliver trusted KPIs for common use cases such as QA validation, live TV monitoring, and video-on-demand asset verification.

Execution combines deterministic logic with agentic assistance only when needed, enabling reliable 24/7 automation without the maintenance burden typically associated with traditional scripting. This hybrid model ensures consistent results while allowing automation to adapt seamlessly to UI changes, unexpected states, and unplanned events across devices without breaking scenarios or requiring manual rework.

Full Customization with the Agentic SDK

For advanced use cases, Agentic SDK offers full access to an open, extensible automation environment. Teams can create, edit, and extend workflows using a mix of AI-driven and algorithmic steps, define custom KPIs, and build reusable automation components.

The SDK provides an AI-native, Python-based environment designed for secure execution and scale, where agentic reasoning, deterministic validation and governance are engineered together rather than bolted on. It enables organizations to move beyond testing and apply agentic automation across broader video workflows. This flexibility allows teams to innovate without losing governance, reuse, or control.

Grounded in Real Devices and Proven Expertise

Agentic SDK integrates natively with Witbe’s real-device testing and monitoring infrastructure, enabling agentic automation to operate on the same Smart TVs, set-top boxes, mobile devices, and browsers used by real viewers.

This hybrid approach reflects Witbe’s long-standing expertise in testing and monitoring video services on real devices. With more than two decades of experience supporting broadcasters, streaming platforms, and operators worldwide, Witbe has built its technology around deterministic measurement, repeatable validation, and real-world playback behavior; principles that now form the foundation of the Agentic SDK.

"AI is moving fast, and in many cases, it’s being layered onto products without changing how they truly work,” said Mathieu Planche, CEO of Witbe. “At Witbe, intelligence has always been part of the product: from our early algorithms to today’s agentic systems. With the Agentic SDK, we are redefining how testing and monitoring are designed, combining agentic AI and deterministic logic in a single governed framework. This marks a structural shift for our industry, and for how video services will be tested and operated going forward.”

Availability

Witbe Agentic SDK is available immediately as part of Witbe’s automation and monitoring platform. It is delivered as part of Witbe Suite’s latest release, version 41, fully compatible with all existing Witbox deployments, allowing customers to start using it right away with no additional hardware or infrastructure to deploy, requiring only AI tokens provisioning. The SDK has already been introduced to select customers and partners, who are actively deploying it in production workflows, with additional tooling and expanded use cases rolling out in the coming weeks.

Request a demo today!