Your knowledge-driven AI platform

Users engage with the platform through an intuitive conversational interface, enabling non-technical stakeholders to interact with AI agents using natural language. This ensures ease of use, broader adoption, and real-time access to insights without requiring query languages or deep technical know-how.

At the core of metis are AI agents powered by advanced cognitive skills that enable meaningful, context-aware interactions and decision-making. These include:

• Language understanding: Enables intuitive conversations between users and AI agents via natural language.

• Intent detection: Allows agents to accurately interpret what the user is trying to achieve.

• Planning and decision-making: Supports complex task execution by selecting the right tools and steps to fulfill user goals.

• Semantic reasoning: Leverages domain-specific semantics from the knowledge graph to ensure contextual accuracy and relevance in responses.

To act on user requests and deliver trustworthy outcomes, metis orchestrates a suite of specialized execution tools and services, including:

• SPARQL query generation: Converts natural language questions into precise semantic queries.

• Vocabulary mapping: Aligns terminology across systems and data sources to ensure consistent understanding.

• Retrieval-augmented generation (RAG): Enhances answers by grounding them in enterprise data and semantics.

• Entity linking & entity description: Identifies key concepts and connects them to their semantic representations.

• Context-driven response rendering: Generates final answers in a clear, human-readable format.

• Summarization: Condenses complex information into concise summaries.

• Custom tools integration: Supports your own execution logic or services, allowing full extensibility.

metis is built around a flexible architecture of knowledge-driven AI agents, each designed to perform specific, enterprise-relevant tasks. Out of the box, the platform includes:

• Search & Discovery Agents for querying and navigating structured knowledge, which can be further configured for specific use cases. 

• Semantic Modeling Agent to support the creation and maintenance of domain-specific semantic models.

• An Agent Registry to manage, configure and orchestrate both prebuilt and custom agents.

Beyond predefined roles, metis enables the creation of custom AI agents tailored to your unique business needs. New agents can be defined by combining:

• A selection of tools and capabilities (e.g. retrieval, summarization, entity linking, query generation) 

• A semantic model that provides the contextual and domain-specific grounding 

• Configuration options such as the choice of LLM, prompt templates or access scope.

This composable approach allows organizations to quickly build and deploy agents for diverse use cases—ranging from internal knowledge assistants to task-specific copilots—while ensuring each one operates with contextual precision and explainable logic.

An integrated quality control framework supports oversight by enabling organizations to monitor, validate and improve AI performance systematically. This adds an essential layer of trust, especially for high-stakes or regulated environments.

metis is designed to support meaningful human-AI collaboration through two complementary paradigms:

• Human-in-the-Loop: Users remain actively involved in critical steps of the AI process—reviewing, validating and refining results. This ensures oversight, traceability and trust, especially in sensitive or high-stakes scenarios. metis provides interfaces and quality control tools that make it easy for users to give feedback and guide agent behavior, enabling continuous improvement and compliance with enterprise standards.

• Augmented Intelligence: AI agents act as intelligent assistants that enhance human capabilities—not replace them. They help users access, interpret and act on complex knowledge more efficiently by automating routine tasks (e.g., query generation, summarization) and surfacing contextually relevant information. This paradigm ensures that domain experts stay in control while benefiting from scalable, AI-powered support.

Together, these modes allow metis to deliver AI that's not only powerful but also aligned with human judgment, organizational goals and enterprise governance.