--- title: PowerContext 1.2.0 Adds Jev Integration, Improving... description: OceanBase released PowerContext 1.2.0, adding integration with decision-judgment services (TypeSafe's Jev and Laya) that check coding-agent proposals against a... canonical: https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: PowerContext 1.2.0 Adds Jev Integration, Improving Accuracy by 14.2% | daily.dev og:description: OceanBase released PowerContext 1.2.0, adding integration with decision-judgment services (TypeSafe's Jev and Laya) that check coding-agent proposals against a... og:url: https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf og:image: https://api.daily.dev/og/posts/gU66qvQPF.png og:image:alt: PowerContext 1.2.0 Adds Jev Integration, Improving Accuracy by 14.2% 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. # PowerContext 1.2.0 Adds Jev Integration, Improving Accuracy by 14.2% **[Medium](https://daily.dev/sources/medium_js)** · 14 min read · 1 upvotes · 0 comments ## Summary OceanBase released PowerContext 1.2.0, adding integration with decision-judgment services (TypeSafe's Jev and Laya) that check coding-agent proposals against a project's saved memory and conventions, returning yes/no/abstain rather than blocking tasks. The release also adds native code understanding, letting agents trace implementation and call sites in a repository with freshness checks before editing, plus memory governance (quality checks on saved records) and expanded integrations with Codex, Claude Code, and ZCode. A LoCoMo-Plus stress test reportedly showed adding Jev raised question-answering accuracy from 60.37% to 68.947%, about a 14.2% relative gain, though independent tests remain the final verification step for code correctness. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does PowerContext 1.2.0 add for coding agents? PowerContext 1.2.0 adds a DecisionModel interface integrating with TypeSafe's Jev and Laya decision models, letting a coding agent's proposal be checked against saved project memory and conventions, returning yes, no, or abstain. It also introduces native code understanding to trace implementation and call sites before edits, plus memory quality checks and expanded Codex, Claude Code, and ZCode integration. _Teams wiring decision models into coding agent workflows can track releases like this one on daily.dev._ ### How much did adding Jev improve PowerContext's question-answering accuracy in the LoCoMo-Plus test? Adding Jev on top of PowerContext's existing retrieval flow raised answer accuracy from 60.37% to 68.947% on a LoCoMo-Plus stress test, a relative gain of about 14.2%. The gain reflects improved selection of historical material during context assembly, while actual code correctness still relies on independent test verification rather than the decision model's judgment. _Developers evaluating context-selection improvements for AI agents can follow benchmark results like this via daily.dev._ ### What is OpenAI's Decisions API announced at DevDay and how does it compare to Jev? OpenAI announced the Decisions API at its DevDay event on September 29, 2026, targeting the same kind of bounded judgment as TypeSafe's Jev, which entered early access on September 15, 2026. Both let developers define a fixed set of questions with predetermined answers, supply text or image context, and use results to classify content, route requests, or choose an agent's next step; OpenAI's version uses a model called Luna. _Teams choosing between emerging decision-model APIs can track announcements like these on daily.dev._ ## Similar posts on daily.dev - [Introducing the AI context engine for your entire codebase](https://daily.dev/posts/introducing-the-ai-context-engine-for-your-entire-codebase-1prl18dgx) · Atlassian · 1 upvotes · 1 comments - [Jev Doesn't Write Text. It Returns Probabilities.](https://daily.dev/posts/jev-doesn-t-write-text-it-returns-probabilities--3tcrb0ghc) · DEV · 7 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#context-engineering](https://daily.dev/tags/context-engineering) [View this post on daily.dev](https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf) ```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":"PowerContext 1.2.0 Adds Jev Integration, Improving Accuracy by 14.2%","url":"https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf"},"datePublished":"2026-10-03T12:37:08.960Z","dateModified":"2026-10-03T12:38:08.479Z","description":"OceanBase released PowerContext 1.2.0, adding integration with decision-judgment services (TypeSafe's Jev and Laya) that check coding-agent proposals against a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0ac0c20d298f0605a1c93b9f6c0749d3?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0ac0c20d298f0605a1c93b9f6c0749d3?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,context-engineering","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"PowerContext 1.2.0 Adds Jev Integration, Improving Accuracy by 14.2%"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/powercontext-1-2-0-adds-jev-integration-improving-accuracy-by-14-2--gu66qvqpf#faq","mainEntity":[{"@type":"Question","name":"What does PowerContext 1.2.0 add for coding agents?","acceptedAnswer":{"@type":"Answer","text":"PowerContext 1.2.0 adds a DecisionModel interface integrating with TypeSafe's Jev and Laya decision models, letting a coding agent's proposal be checked against saved project memory and conventions, returning yes, no, or abstain. It also introduces native code understanding to trace implementation and call sites before edits, plus memory quality checks and expanded Codex, Claude Code, and ZCode integration. Teams wiring decision models into coding agent workflows can track releases like this one on daily.dev."}},{"@type":"Question","name":"How much did adding Jev improve PowerContext's question-answering accuracy in the LoCoMo-Plus test?","acceptedAnswer":{"@type":"Answer","text":"Adding Jev on top of PowerContext's existing retrieval flow raised answer accuracy from 60.37% to 68.947% on a LoCoMo-Plus stress test, a relative gain of about 14.2%. The gain reflects improved selection of historical material during context assembly, while actual code correctness still relies on independent test verification rather than the decision model's judgment. Developers evaluating context-selection improvements for AI agents can follow benchmark results like this via daily.dev."}},{"@type":"Question","name":"What is OpenAI's Decisions API announced at DevDay and how does it compare to Jev?","acceptedAnswer":{"@type":"Answer","text":"OpenAI announced the Decisions API at its DevDay event on September 29, 2026, targeting the same kind of bounded judgment as TypeSafe's Jev, which entered early access on September 15, 2026. Both let developers define a fixed set of questions with predetermined answers, supply text or image context, and use results to classify content, route requests, or choose an agent's next step; OpenAI's version uses a model called Luna. Teams choosing between emerging decision-model APIs can track announcements like these on daily.dev."}}]} ```