SnowFlow AI - go from documents to database in a flash! | DC .

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

February 24, 2026 · DC

SnowFlow AI: Document to Snowflake

See how SnowFlow AI transforms financial documents into structured database entries for Snowflake, a practical fintech solution built with AI.

Video
Overview
Links
Tech stack
  • Landing AI API
    The developer-first API for Andrew Ng’s LandingLens: deploying production-grade computer vision models for industrial inspection.
    Landing AI (founded by Andrew Ng) provides the API infrastructure for LandingLens: a platform designed for industrial computer vision. This tool allows teams to deploy models for defect detection and object classification in minutes. The API returns structured JSON (including bounding boxes and confidence levels) to automate quality control on manufacturing lines. It focuses on the Data-Centric AI approach: ensuring high accuracy even with small datasets (often fewer than 50 images).
  • LangGraph
    A low-level orchestration framework for building long-running, stateful, and cyclic multi-agent systems using a graph-based architecture.
    LangGraph is the specialized, low-level runtime for developing complex AI agents, extending the LangChain ecosystem to handle intricate, stateful workflows. It models the agent's logic as a directed graph: nodes represent actions (LLM calls, tool use), and conditional edges dictate the flow, enabling critical features like cycles (loops) for iterative reasoning. This graph-based approach ensures durable execution, allowing agents to persist through failures and resume operations. Key capabilities include comprehensive memory management via a shared state object and built-in human-in-the-loop functionality (interrupts) for external oversight. This robust framework is trusted by production teams at companies like Klarna and Replit for deploying scalable, resilient agent architectures.
  • Snowflake API
    A RESTful interface for executing SQL statements and managing data workflows via HTTP requests without persistent drivers.
    The Snowflake SQL API provides a lightweight alternative to traditional JDBC or ODBC drivers by exposing a RESTful endpoint for data operations. Developers submit POST requests to the /api/v2/statements resource to trigger queries, manage warehouse scaling, or execute COPY INTO commands for data ingestion. The API returns results in partitioned JSON blocks: an ideal structure for serverless environments (like AWS Lambda) that require stateless, high-speed connections. It supports asynchronous execution and custom timeout settings (up to 3600 seconds) to ensure reliable processing for complex analytical workloads.

Related projects