--- title: Can ODC Consume Google’s Open Knowledge Format Natively? description: A developer built a native consumer for Google's Open Knowledge Format (OKF) inside OutSystems Developer Cloud (ODC), consisting of a parsing library, a... canonical: https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Can ODC Consume Google’s Open Knowledge Format Natively? | daily.dev og:description: A developer built a native consumer for Google's Open Knowledge Format (OKF) inside OutSystems Developer Cloud (ODC), consisting of a parsing library, a... og:url: https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff og:image: https://api.daily.dev/og/posts/YAKphLjfF.png og:image:alt: Can ODC Consume Google’s Open Knowledge Format Natively? og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Can ODC Consume Google’s Open Knowledge Format Natively? **[ITNEXT](https://daily.dev/sources/itnext)** · 12 min read · 1 upvotes · 0 comments ## Summary A developer built a native consumer for Google's Open Knowledge Format (OKF) inside OutSystems Developer Cloud (ODC), consisting of a parsing library, a knowledge store, and a tool-calling agent. The build was tested against all four of Google's canonical reference bundles (53 concepts, 110 links), with outputs verified by hand against Google's own viz.html reference tool. The piece details the architecture's three layers, a debugging story about switching a trust-tier filter parameter from an integer ID to a text label to fix LLM tool-calling reliability, and honest limitations: no export/producer side, no execution of attested computations, and MachineConfirmed trust tier remains untested since no bundle exercises it. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why does an LLM agent ignore instructions to filter by a specific trust tier when the tool parameter is a numeric identifier? Because the model has to translate the semantic value in the question into an arbitrary number before passing it, and that translation step fails reliably even after five separate prompt-engineering attempts. Changing the parameter from an integer id to a text label matching the tier's own name (such as "HumanReviewed") let the model copy the word directly from the question, fixing the issue on the first attempt. _Anyone debugging flaky tool-calling behavior in agent pipelines can compare notes on daily.dev._ ### What new fields did Google's Open Knowledge Format version 0.2 add over the previous version? Open Knowledge Format version 0.2, released July 25, 2026, added verification status, trust tier, and staleness fields. These are what let an AI agent reason about the reliability of retrieved knowledge honestly rather than simply retrieving text, distinguishing OKF from a plain folder of markdown files. _Developers tracking emerging data-sharing formats like OKF can follow spec changes on daily.dev._ ## Similar posts on daily.dev - [How the Open Knowledge Format can improve data sharing](https://daily.dev/posts/how-the-open-knowledge-format-can-improve-data-sharing-qqswihmau) · Google Cloud · 15 upvotes · 0 comments - [Architecture as Code: How Google’s OKF Makes Coding Agents Follow Your Architecture](https://daily.dev/posts/architecture-as-code-how-google-s-okf-makes-coding-agents-follow-your-architecture-cc2o3991u) · Medium · 2 upvotes · 0 comments - [Using OKF to provide long term context to your agent](https://daily.dev/posts/using-okf-to-provide-long-term-context-to-your-agent-9rqtpfok6) · iO tech\_hub · 10 upvotes · 0 comments - [Knowledge as Code: The Memory File Just Got a Spec](https://daily.dev/posts/knowledge-as-code-the-memory-file-just-got-a-spec-rlawyv7rd) · Pulumi · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#nocode](https://daily.dev/tags/nocode) [View this post on daily.dev](https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Can ODC Consume Google’s Open Knowledge Format Natively?","url":"https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff"},"datePublished":"2026-08-13T19:51:06.967Z","dateModified":"2026-09-14T06:41:40.992Z","description":"A developer built a native consumer for Google's Open Knowledge Format (OKF) inside OutSystems Developer Cloud (ODC), consisting of a parsing library, a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0b86b6607d8254752099af36d693df68?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0b86b6607d8254752099af36d693df68?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"ITNEXT","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"ITNEXT","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/itnext2","url":"https://daily.dev/sources/itnext"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,nocode","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ITNEXT","item":"https://daily.dev/sources/itnext"},{"@type":"ListItem","position":3,"name":"Can ODC Consume Google’s Open Knowledge Format Natively?"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/can-odc-consume-google-s-open-knowledge-format-natively--yakphljff#faq","mainEntity":[{"@type":"Question","name":"Why does an LLM agent ignore instructions to filter by a specific trust tier when the tool parameter is a numeric identifier?","acceptedAnswer":{"@type":"Answer","text":"Because the model has to translate the semantic value in the question into an arbitrary number before passing it, and that translation step fails reliably even after five separate prompt-engineering attempts. Changing the parameter from an integer id to a text label matching the tier's own name (such as \"HumanReviewed\") let the model copy the word directly from the question, fixing the issue on the first attempt. Anyone debugging flaky tool-calling behavior in agent pipelines can compare notes on daily.dev."}},{"@type":"Question","name":"What new fields did Google's Open Knowledge Format version 0.2 add over the previous version?","acceptedAnswer":{"@type":"Answer","text":"Open Knowledge Format version 0.2, released July 25, 2026, added verification status, trust tier, and staleness fields. These are what let an AI agent reason about the reliability of retrieved knowledge honestly rather than simply retrieving text, distinguishing OKF from a plain folder of markdown files. Developers tracking emerging data-sharing formats like OKF can follow spec changes on daily.dev."}}]} ```