Clemens Vasters

Bringing Clarity to Event Streams: Enabling Analytics and AI Through Rich Metadata

What if you could define a schema for data you don't have yet? Learn how to formalize event streams for powerful, AI-assisted tooling and analytics.

Bringing Clarity to Event Streams: Enabling Analytics and AI Through Rich Metadata
#1about 3 minutes

The problem of ambiguous data without clear context

Examples with LLMs demonstrate how data without metadata, like temperature units, leads to inconsistent and unreliable interpretations.

#2about 5 minutes

Using schemas to provide necessary data constraints

Providing a schema with explicit constraints and descriptions, such as units, enables LLMs to interpret data correctly and generate consistent results.

#3about 1 minute

Adopting a schema-first design for data structures

Data schemas should be created first and be independent of code assets, allowing code generation for polyglot applications and improving LLM performance.

#4about 3 minutes

Standardizing event structure using CNCF CloudEvents

Using a standard like CloudEvents provides a consistent envelope for events, preventing the chaotic and varied structures that LLMs might otherwise generate.

#5about 5 minutes

Automating client code generation with detailed metadata

By providing a comprehensive metadata document that includes endpoint and protocol details, LLMs can automatically generate complete and correct client code for publishers.

#6about 2 minutes

Moving beyond tribal knowledge in event pipelines

Current event pipelines often rely on informal communication, but a metadata-driven approach creates a formal contract that improves maintainability and compatibility.

#7about 6 minutes

A practical metadata-driven pipeline with Microsoft Fabric

A real-world example processing USGS water data demonstrates how a complete metadata definition using X Registry enables automated tooling and contract enforcement.

#8about 2 minutes

Introducing JSON Structure as a better schema language

JSON Structure is proposed as a stricter alternative to JSON Schema, designed as a data definition language with a better type system and namespace support.

#9about 4 minutes

Key standards for modern event-driven architecture

A summary of three key open standards—CloudEvents, X Registry, and JSON Structure—that provide the tools for building robust, metadata-driven systems.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

From learning to earning

Jobs that call for the skills explored in this talk.