PRODUCTS
states and unplanned events across devices without breaking scenarios or requiring manual rework. Full Customisation with the Agentic SDK For advanced use cases, we have found that Agentic SDK also offers 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 execution and scale, where agentic reasoning, deterministic validation and governance are engineered together rather than bolted on. It enables organisations 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 We also found that 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 expertise in testing and monitoring video services on real devices. “AI is moving fast, and in many cases, it’s being layered onto products without changing how they truly work,” Mathieu Planche, CEO of Witbe told Broadband Journal. “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.”
One platform, multiple paths to automation Agentic SDK was designed as a single automation platform that teams can adopt according to their needs. Organisations can run simple, one-off goal-based tests, introduce more complex measurements through preset scenarios with hybrid continuous execution, and ultimately customise 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 analyse tests automatically on real devices. This mode is designed for exploratory testing, release validation and non-continuous QA workflows, delivering 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 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
Availability The good news is 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, compatible with all existing Witbox deployments, allowing for use 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. More information and demo requests are available at www.witbe.net/contact-us .
www.witbe.net
Volume 48 No.1 MARCH 2026
117
Made with FlippingBook - Online magazine maker