A multi-tool MCP agent that walks hematology/transfusion medicine teams through platelet thresholds, dose calculations, context validation, and interaction checks—all with structured, ChatGPT-style reporting for high-risk procedures.
A role-aware, AI-powered workspace that lets Healthcare experts chat with their EMR via MCP servers to fetch, add, and update patient data in real time—delivering instant clinical insights while enforcing strict, user-level permissions
A specialized data engineering platform featuring three AI agents (Polars Expert, Code Converter, Data Engineer) connected to MCP servers for real-time tool access. Provides precise, evidence-based guidance for DataFrame operations, code migration, and infrastructure design with mandatory tool validation and strict domain expertise enforcement.
A secure clinical chatbot linking to an MCP server’s blood-transfusion rules for real-time, evidence-based guidance, with a modular design for adding more rule libraries.
This techstack introduces the concept of a "Hello World" project for modern data engineering, helping newcomers learn the basics through a practical example.
A cost-effective stack featuring a remote VSCode-enabled Jupyter Notebook with pre-installed libraries (Polars, DuckDB) and Blob Storage. LocalStack emulates cloud services. NoCoDB (OSS Airtable alternative) manages data, while Metabase powers dashboards.
Comprehensive comparison between Apache Airflow and Dagster for data orchestration needs, helping you choose the right framework for your data pipeline requirements.
Enterprise BI solution for reporting and analytics
Ideal for setups requiring robust UI and API integration. MinIO provides an alternative blob storage with a user-friendly interface, Delta Lake offers transactional capabilities, Polars or DuckDB handles data queries, and Superset ensures seamless dashboarding.
Process and analyze data in real-time for immediate insights
Unified analytics engine for large-scale data processing
Evaluate cutting-edge data processing engines for different scales and use cases. From in-memory processing to distributed computing, understand which engine fits your needs.
Open-source storage layer for data lakes
Next-generation data engineering stack featuring Apache Spark, Apache Iceberg, and Dagster's developer-friendly orchestration. Ideal for teams building modern data platforms with emphasis on developer experience, testing, and asset-based workflows.
Evaluate leading vector databases for AI and similarity search applications. Compare performance, scalability, and ease of use for different scenarios.
Suitable for scaling operations, this stack leverages Iceberg or Delta Lake for the database, Daft DataFrame for distributed data pipelines, and Metabase or Superset for dashboards.
