Solidatus launches 2026.3 product update
Solidatus launches 2026.3 product update to put governed data lineage within reach of AI agents
New release adds MCP support, Bring Your Own LLM, and persistent AI Assistant sessions to help enterprises govern AI with trusted data context
LONDON, UNITED KINGDOM – July 6, 2026 – Solidatus, the enterprise data lineage platform trusted by global banks including HSBC and Deutsche Bank, today announced Solidatus 2026.3, a major product update that connects governed data lineage to the emerging AI agent ecosystem while giving organisations greater control over how AI is deployed, managed and audited.
AI adoption is now widespread across the enterprise, with Microsoft finding that more than 80% of Fortune 500 companies today use AI agents built with low-code/no-code tools. Yet as adoption accelerates, many organisations are discovering that model performance is only part of the challenge. AI tools need access to trusted business context, clear data provenance, and an auditable record of how answers and actions are produced.
Solidatus 2026.3 addresses this by extending the platform’s AI capabilities across three pillars: governance of AI, governance by AI, and governance for AI. The release introduces Model Context Protocol (MCP) support, enabling external AI tools and agents to connect to Solidatus and work with governed data lineage model content. It also adds Bring Your Own LLM, allowing organisations to run the Solidatus AI Assistant against their own approved model provider and keys.
Together, these updates give regulated enterprises a controlled path to AI adoption. External tools can access lineage that has been modelled, approved and maintained by humans, while organisations retain control over the AI models they use. Every AI-assisted change remains staged for human review, and every accepted change is captured as an attributed, timestamped revision in the model’s history.
The release also makes the Solidatus AI Assistant more persistent and easier to govern. Conversations now continue across browser sessions, while Chat Rollup carries active states, filters, traces and key entities into a fresh conversation when a long session reaches its context limit. This allows users to continue complex lineage investigations without rebuilding their work from memory.
A new Prompt Library allows teams to create, store and reuse prompts for recurring governance tasks, helping organisations turn repeatable regulatory questions into consistent, governed workflows. Quick Actions surface contextual next steps from the current session, while queued follow-up requests allow users to line up additional tasks while the assistant is still generating a response.
Solidatus 2026.3 also improves how users navigate and act on enterprise data. Data Domains now include a Domain Spine, keeping Home, AI Assistant, Reference Hub, Lineage Models, saved Data Maps and related domain content one click away. Lineage models now have a clearer home inside Data Domains, while searchable entity hierarchy tables help users explore nested structures without leaving the domain context.
Analytics and reporting workflows have also been enhanced. Users can now export the records behind any metric to CSV from the Analytics report drill-down panel, giving teams direct access to the evidence behind governance metrics. Reports can also be edited and deleted directly from the Data Domain home page, while Data Maps now save without reloading and retain display rules more reliably.
“AI governance is quickly becoming one of the defining challenges for enterprises, particularly in regulated sectors where organisations need to prove not just what a system said, but what data it relied on and who approved the outcome,” said Philip Dutton, Founder of Solidatus. “Solidatus 2026.3 gives AI assistants and agents access to the governed lineage they need, while keeping model choice, human oversight and auditability firmly in the hands of the organisation.”
The update also continues Solidatus’ wider platform modernisation work, improving performance, compatibility and maintainability across large models and everyday workflows, including smoother navigation, better Data Map rendering, more reliable search, and improved handling of large or complex sessions.
For on-premises upgrades, customers should check the Ops Release Notes before planning their rollout. Customers interested in BYOLLM or MCP access should contact their Account Manager or Customer Success Manager.
