Pathway

What is Pathway?

Pathway is a software framework built to solve a specific industry problem: the lack of infrastructure that can reason over data streams in real time. It lets software engineers build real-time data products without being weighed down by constantly changing data inputs.

Because Pathway uses a reactive design, it handles data updates smoothly, making data products easier to develop and maintain while running efficiently on its engine. It simplifies the ML/AI project lifecycle from prototype to production, offers flexible deployment options, and processes updates at high speed from live data sources such as cloud folders, databases, and APIs.

Key features include:

• Simplified cloud-native development
• Fast, synchronized data processing
• Flexible deployment options
• Customizable code templates
• Interaction with external APIs and models, including LLMs

Who created Pathway?

Pathway was built by a team with backgrounds in AI, including people who previously worked at top AI labs like Google Brain — ex-Googlers, competitive programmers, and experts in Distributed Systems, Machine Learning, and Complexity Science.

Founder Zuzanna completed her PhD on forecasting maritime trade, where she identified the need to apply Machine Learning to data streams in logistics. She teamed up with Jan, who brought experience from Google Brain, and together with Adrian and Claire developed Pathway to fill the gap in software infrastructure for real-time data processing.

Who is Pathway for?

• Software engineers
• Python developers

How to use Pathway

1. Set up data ingestion: Connect and sync data from over 300 sources for vector search, real-time features, and anomaly alerts. Pathway keeps data in sync automatically, so AI insights stay accurate whether they come from documents or tables.
2. Use app templates: Ready-made templates and a setup guide make it simple to build applications that fetch real-time data, without setting up complex databases or full tech stacks.
3. Develop in Python: Built in Rust but designed for Python developers, Pathway streamlines the path from prototype to production. Deploy locally, in a notebook, or scaled up in containers.
4. Connect live data sources: Access live data from SharePoint, Google Drive, S3, Delta Tables, Kafka, various databases, and over 300 APIs such as Salesforce and HubSpot. The high-speed engine is built for real-time updates, scalability, and cost-effective computing.
5. Deploy your way: You keep full ownership of deployment — use Docker or Kubernetes on-premises or in the cloud, avoiding multiple databases and compute engines.
6. Customize and integrate: Use industry-tailored templates and customize them with Pathway’s library, connectors, and integrations, designed for safe interaction with LLMs and external APIs.