Open Knowledge Format v0.2 enhances agentic trust and provenance
The Open Knowledge Format (OKF) has been updated to version 0.2, introducing new frontmatter fields to address concerns about agent-generated content trustworthiness. These additions enable consumers to assess provenance, trust, freshness, lifecycle, and attestation of knowledge assets. This release is particularly relevant for systems where agents continuously generate and consume knowledge, allowing for explicit signals to build accountability. The updates are optional and do not change the core format, maintaining compatibility with v0.1.
- →Provenance tracking via 'sources' field
- →Trust signals through 'generated' and 'verified' fields
- →New frontmatter fields for trust and provenance
- →Minimalist approach maintained with optional additions
- →Focus on decision-making signals in frontmatter
Features (2) ›
- Provenance tracking via 'sources' field
The new 'sources' field in OKF v0.2 allows concepts to record their origins, such as external documents or specific scopes. It also includes objective credibility signals like author, usage_count, and last_modified, letting consumers infer credibility rather than relying on static scores.
- Trust signals through 'generated' and 'verified' fields
OKF v0.2 distinguishes between how content was produced ('generated') and who confirmed it ('verified'). The 'verified' field supports a list of independent confirmations, enabling consumers to derive trust tiers (unverified, machine-confirmed, human-reviewed) as advisory signals.
Enhancements (1) ›
- New frontmatter fields for trust and provenance
OKF v0.2 adds optional frontmatter fields to address agentic trust, allowing consumers to evaluate provenance, trust, freshness, lifecycle, and attestation. These signals are designed to provide accountability in environments where agents generate knowledge continuously.
Notes (2) ›
- Minimalist approach maintained with optional additions
Version 0.2 builds upon OKF v0.1 by adding optional vocabulary rather than strict rules. The format remains minimally opinionated, preserving custom keys and ensuring bundles that adopt none of the new additions are still valid. The core 'type' field remains the only required element.
- Focus on decision-making signals in frontmatter
The new frontmatter fields are designed to provide concise signals for consumers to make quick decisions about a concept's relevance and trustworthiness before accessing its full content. This optimizes interactions, especially in search and discovery scenarios.
https://cloud.google.com/blog/products/data-analytics/okf-v0-2-adds-trust-signals/
Related releases
- BigQuery Enhances Conversational Analytics with New ML Functions Google Cloud release notes ·
- BigQuery Generative AI Functions Now Support New Gemini Models Google Cloud release notes ·
- BigQuery Conversational Analytics Adds AI.PREDICT for Predictive Modeling Google Cloud release notes ·
- Google Cloud Introduces Data Agent Kit for Agentic Data Analysis in IDEs Google Cloud Blog ·
- Optimizing RAG Apps: KDDI's Automated Evaluation & Performance Strategy Google Cloud Blog ·
- Google Threat Intelligence tracks evolving adversarial AI tactics and supply chain risks Google Cloud Blog ·