@Saboo_Shubham_: Google just shipped Open Knowledge Format v0.2, and it is all about agentic trust. When a person writes a wiki page, yo…

X AI KOLs Timeline Tools
google open-knowledge-format agentic-trust knowledge-catalog data-catalog metadata-management ai-agents

Summary

Google released Open Knowledge Format v0.2, adding frontmatter fields for sources, verification, freshness, and status, plus Attested Computation for verified metrics, enabling agentic trust in data catalogs.

Google just shipped Open Knowledge Format v0.2, and it is all about agentic trust. When a person writes a wiki page, you know who to ask if it is wrong. When an agent writes ten thousand pages overnight, nobody is accountable for any of them. The agent reading those pages needs signals it can check before it reads a single line. v0.2 puts four of them in the frontmatter: • sources: what the page was built from, with author and usage count. Raw signals, no trust score. • generated and verified: who wrote it, who checked it. Human checked and machine checked stay separate. • stale_after: a fixed date, so freshness is a date comparison. • status: draft, stable, or deprecated. The best part is a new type called Attested Computation. It holds the approved query for a metric. The agent fills in parameters and nothing else. It never writes the SQL. After a run, a small script compares what actually ran against what was approved. Rename a table or drop a join and it fails, and the number never gets shown. Still just markdown and YAML. Every new field is optional. Your v0.1 bundles still work. GitHub Repo: https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf…
Original Article
View Cached Full Text

Cached at: 07/29/26, 03:59 PM

Google just shipped Open Knowledge Format v0.2, and it is all about agentic trust.

When a person writes a wiki page, you know who to ask if it is wrong. When an agent writes ten thousand pages overnight, nobody is accountable for any of them. The agent reading those pages needs signals it can check before it reads a single line.

v0.2 puts four of them in the frontmatter:

• sources: what the page was built from, with author and usage count. Raw signals, no trust score. • generated and verified: who wrote it, who checked it. Human checked and machine checked stay separate. • stale_after: a fixed date, so freshness is a date comparison. • status: draft, stable, or deprecated.

The best part is a new type called Attested Computation. It holds the approved query for a metric. The agent fills in parameters and nothing else. It never writes the SQL. After a run, a small script compares what actually ran against what was approved. Rename a table or drop a join and it fails, and the number never gets shown.

Still just markdown and YAML. Every new field is optional. Your v0.1 bundles still work.

GitHub Repo: https://github.com/GoogleCloudPlatform/knowledge-catalog/tree/main/okf…

GoogleCloudPlatform/knowledge-catalog

Source: https://github.com/GoogleCloudPlatform/knowledge-catalog

Knowledge Catalog

Knowledge Catalog (formerly Dataplex), is an AI-powered data catalog and metadata management platform. It provides a dynamic knowledge graph of all your data, structured and unstructured, to provide semantics and business context to AI agents

This repository features tools, agents, and samples that demonstrate Knowledge Catalog features, and building context management, enrichment and retrieval solutions.

Getting Started

Open in Cloud Shell

Contributing

See the contributing instructions to get started contributed.

License

All solutions within this repository are provided under the Apache 2.0 license. Please see LICENSE for more detailed terms and conditions.

Disclaimer

This repository and its contents are not an official Google product.

Similar Articles

Introducing the Open Knowledge Format (9 minute read)

TLDR AI

Google Cloud introduces the Open Knowledge Format (OKF), an open specification for representing metadata and curated knowledge in markdown files to improve data sharing and context for AI agents. The format aims to make knowledge from fragmented internal systems portable and interoperable.