This release brings AI agents into the core of the Dylogy platform. A new configuration agent helps you build Analyzer workspaces from a simple description of your use case, and each action can now search the web for up-to-date information. The conversational agent also arrives in Analyzer and Discover, ready to explore your documents and claims from any page.
1. Configuration agent: build your workspaces by describing your use case
Setting up a workspace now starts with a conversation. A configuration agent is available in the Platform, at tenant level. You describe your use case, and the agent helps you create a new workspace or modify an existing one, including document types, attributes, generation and control actions, and group metadata.
You keep full control throughout the process. Before each modification, the agent presents the proposed changes and waits for your approval. To go faster, you can also share a document or spreadsheet listing configuration elements, and the agent takes it into account.
For now, the agent configures Analyzer workspaces. A future iteration will extend it to graph configuration.
2. Web search in Actions: enrich outputs with up-to-date information
Until now, an action could only generate its content from the documents and knowledge already stored in your workspace. Each action can now activate its own web search and retrieve current information at the moment it runs.
You enable web search action by action, based on what each one actually needs, rather than for all of them at once. Your actions stay grounded in your own documents and can draw on recent external information when the task calls for it.
3. Conversational agent: explore Analyzer and Discover from any page
The conversational agent is now available in Analyzer and Discover. It comes with new tools to explore workspace information and a new interface that makes it accessible from any page.
In Analyzer, the agent can find documents and document groups, look up extracted values, and review action results and recommendations. In Discover, it explores claims and their graphs, along with topics, entities and action results.
The overall experience has also been improved. Conversations are organized in tabs, and the agent automatically picks up the context of the page you are working on. You can mention workspace elements with @, follow the agent's reasoning process, and return to past conversations in your history or export them.
These features are available today. If you would like help configuring your first workspace with the agent or enabling web search on your actions, contact us.
| Domaine d'Application | Bénéfices Clés grâce aux Graphes de Connaissances |
| Prévention | Identifier les causes racines communes à plusieurs sinistres pour proposer des actions préventives. Détecter les causes secondaires pour limiter la propagation des dommages. |
| Tarification | Proposer des segmentations plus fines des assurés en fonction des chaînes de causes réelles. Mieux évaluer l'impact d'une exclusion de garantie (par exemple, "Exclusion de l’usure de machines"). |
| Provisionnement | Comprendre les dynamiques d'évolution des pertes et identifier les causes qui, étonnamment, ne mènent à aucun coût, pour affiner les réserves financières. |
