Virtual Situation Room

 A key focus during this phase of development has been tackling retrieval and processing challenges when working with large datasets in LLM pipelines . As the Virtual Situation Room ingests more information from diverse sources, we needed a way to process and analyze large volumes of data without exceeding model context limits. Ensuring that relevant information could still be retrieved, structured, and synthesized by the agent pipeline became a central technical challenge. To address this, we explored different approaches for handling large datasets in LLM workflows, including retrieval-based architectures and tools such as Azure AI Search . After evaluating several options, we collaborated to design and implement the full report generation pipeline , moving from architecture design through to a functional implementation. The solution we developed relies on a chunking-based approach , where large datasets are broken into smaller segments that can be processed sequentially and lat...

Development on the Virtual Situation Room has continued to focus on strengthening the AI pipeline that powers crisis analysis.  A major focus has been on building out the  data ingestion and analysis pipeline  that feeds the Virtual Situation Room. This work centers on creating reliable workflows for collecting, processing, and analyzing incoming data so that downstream agents can operate on structured, high-quality inputs. Strengthening this layer is critical to ensuring the system can scale as more data sources and analytical functions are integrated. Regarding the core agentic pipeline, we drafted  structured prompts for the report generation pipeline , which will guide how agents synthesize collected information into structured analytical outputs. These prompts are designed to enforce consistency in how findings, context, and signals are organized within generated reports. These generated reports will follow the IFRC Analytical Framework as shown in the images ...