--- title: Agentic toolkit eval: dltHub REST API toolkit | daily.dev description: A controlled experiment comparing two Claude Code agents — one with dltHub's AI workbench toolkit (MCP servers, CLAUDE.md rules, skills) and one without —... canonical: https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Agentic toolkit eval: dltHub REST API toolkit | daily.dev og:description: A controlled experiment comparing two Claude Code agents — one with dltHub's AI workbench toolkit (MCP servers, CLAUDE.md rules, skills) and one without —... og:url: https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5 og:image: https://api.daily.dev/og/posts/Xj6pI7KY5.png og:image:alt: Agentic toolkit eval: dltHub REST API toolkit 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. # Agentic toolkit eval: dltHub REST API toolkit **[dltHub](https://daily.dev/sources/dlthub)** · 7 min read · 0 upvotes · 0 comments ## Summary A controlled experiment comparing two Claude Code agents — one with dltHub's AI workbench toolkit (MCP servers, CLAUDE.md rules, skills) and one without — across 12 runs building REST API data pipelines. The base agent leaked credentials in 100% of runs, never read current docs, skipped sampling, made only one edit per run, and often produced non-persistent pipelines. The workbench agent passed all behavioral checks: safe credential handling, doc fetching, sampling before full loads, iterative refinement, and proper pipeline initialization. The workbench costs ~58% more per run ($2.21 vs $1.40) but that premium funds the engineering practices a careful data engineer would follow. The key insight: both agents produce running code, but only the workbench-guided agent follows a process that would pass a senior engineer's code review. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Agents can write dlt pipelines. Now they can run & deploy them.](https://daily.dev/posts/agents-can-write-dlt-pipelines-now-they-can-run-deploy-them--vqtnhbzgx) · dltHub · 1 upvotes · 0 comments - [dltHub: dlt made agents good at building pipelines. Now they're safe enough to run for your whole team.](https://daily.dev/posts/dlthub-dlt-made-agents-good-at-building-pipelines-now-they-re-safe-enough-to-run-for-your-whole-te-wrcai08os) · dltHub · 1 upvotes · 0 comments - [Computer use is 45x More Expensive Than Structured APIs](https://daily.dev/posts/computer-use-is-45x-more-expensive-than-structured-apis-jvsojv51q) · Hacker News · 0 upvotes · 0 comments - [How we eliminated $1 million a year of wasted AI agent spend in one hour](https://daily.dev/posts/how-we-eliminated-1-million-a-year-of-wasted-ai-agent-spend-in-one-hour-sl4y8p7za) · databricks · 1 upvotes · 0 comments --- Tags: [#backend](https://daily.dev/tags/backend), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude](https://daily.dev/tags/claude), [#vibe-coding](https://daily.dev/tags/vibe-coding) [View this post on daily.dev](https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5) ```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":"Agentic toolkit eval: dltHub REST API toolkit","url":"https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5"},"datePublished":"2026-04-14T12:47:23.335Z","dateModified":"2026-04-14T12:47:54.574Z","description":"A controlled experiment comparing two Claude Code agents — one with dltHub's AI workbench toolkit (MCP servers, CLAUDE.md rules, skills) and one without —...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1dda1f709177eed7a5417a4c5e43db5c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1dda1f709177eed7a5417a4c5e43db5c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"dltHub","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":"dltHub","logo":"https://media.daily.dev/image/upload/s--lanGOBQH--/f_auto/v1734606584/logos/dlthub","url":"https://daily.dev/sources/dlthub"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/agentic-toolkit-eval-dlthub-rest-api-toolkit-xj6pi7ky5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"backend,ai-agents,claude,vibe-coding","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"dltHub","item":"https://daily.dev/sources/dlthub"},{"@type":"ListItem","position":3,"name":"Agentic toolkit eval: dltHub REST API toolkit"}]} ```