Revvity has launched Signals AI, a native agentic framework built into its Signals One platform that lets scientists query complex R&D data with natural language and receive traceable, context-rich answers. The tool, announced June 29, 2026, is designed for pharmaceutical, biotech, chemical and academic research teams that need to accelerate decision-making across experiments, instruments and enterprise systems.
The launch addresses a growing challenge in the industry: turning massive volumes of disconnected data into actionable insights, a problem that has spurred interest in AI for Science & Research. Signals AI adds an intelligence layer within Signals One, allowing scientists to engage with connected R&D knowledge and dynamically recast it for different scientific and operational purposes.
Natural language search across complex R&D data
Researchers can interact with governed, ontology-driven data using everyday language. The framework transforms connected knowledge into the specific form needed for experimental design, data interpretation, portfolio decisions and operational execution. Key capabilities include:
- Natural language search and interaction across multi-source R&D data
- Dynamic transformation of information for different scientific questions and workflows
- Contextual, traceable responses grounded in structured scientific data and ontologies
Signals AI operates as an agentic framework within the platform, an approach that aligns with the rise of AI Agents & Automation in scientific workflows. This helps scientists move more efficiently from data to understanding, and from understanding to action, without leaving their existing Signals One environment.
Traceable, scientifically rigorous responses
Responses are grounded in domain ontologies and validated scientific algorithms, giving researchers the ability to explore molecules, sequences and experimental results in context. Each insight comes with a clear trail back to its source data, supporting compliance and auditability across discovery, development and analytical workflows.
From system of record to system of understanding
With the new intelligence layer, Signals One shifts from storing data to actively helping researchers interpret it. Teams can navigate multi-source data, generate insights to guide experiments, and operationalize knowledge across departments. Select capabilities are available now, with additional features expected in the coming weeks.
Why this matters for science and research professionals
For scientists, the immediate benefit is speed: natural language queries can cut the time spent extracting and reformatting data from different systems. More importantly, the framework's grounding in structured, traceable data means researchers can trust the answers they get-an essential requirement in regulated environments. As AI tools become more common in the lab, the ability to combine conversational interfaces with scientific rigor will likely separate useful assistants from distracting gimmicks.
Your membership also unlocks:
