--- title: Reviews of DevAI Conference 2026 From a Speaker’s Eye description: A developer recaps DevAI 2026 in Warsaw, a conference with 50 presentations across 4 tracks covering AI topics. One team transformed a Java recruitment system... canonical: https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Reviews of DevAI Conference 2026 From a Speaker’s Eye | daily.dev og:description: A developer recaps DevAI 2026 in Warsaw, a conference with 50 presentations across 4 tracks covering AI topics. One team transformed a Java recruitment system... og:url: https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3 og:image: https://api.daily.dev/og/posts/wDpxm1lY3.png og:image:alt: Reviews of DevAI Conference 2026 From a Speaker’s Eye 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. # Reviews of DevAI Conference 2026 From a Speaker’s Eye **[We Are .NET](https://daily.dev/sources/wearedotnet)** · 30 min read · 0 upvotes · 0 comments ## Summary A developer recaps DevAI 2026 in Warsaw, a conference with 50 presentations across 4 tracks covering AI topics. One team transformed a Java recruitment system to .NET 10 + Blazor + PostgreSQL, reporting 19 working days to a functional platform and 10 weeks to production versus an estimated 7-9 months traditionally, and used spec-driven development. Another speaker described NER-RAG, which reports 330x cheaper document processing than LLM-based extraction in their illustrated scenario. A study of 806 GitHub projects using Cursor, presented by a speaker, reported a 41.6% increase in code complexity and a 30.3% increase in static analysis warnings over the longer term. A separate talk catalogued coding agent failure modes: one agent overestimated task time by up to 177x, a development environment had 268 stale Git branches on a single laptop, and sycophancy and tunnel vision were discussed. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much faster was a .NET rewrite using spec-driven AI development compared to traditional development? A 10+ year-old Java recruitment system was rewritten to .NET 10, Blazor and PostgreSQL in 19 working days to a functional platform and 10 weeks to production, versus an estimated 7 to 9 months with traditional development. The team followed a process of business problem to specification to plan to small tasks to code and tests, with human approval at every stage, and shipped 69 changes after adopting it. _Teams weighing AI-assisted rewrites can track real-world results like this one on daily.dev._ ### Does using Cursor to write code actually increase long-term code quality? No. A study comparing 806 GitHub projects that adopted Cursor against 1,380 similar projects found code production increased 28.6% to 281% initially, but code complexity rose 41.6%, static analysis warnings rose 30.3%, and duplicate code density rose 7.03% over the longer term, with the initial productivity gains disappearing within 1 to 2 months. _Developers deciding whether to lean on Cursor long-term can follow findings like this on daily.dev._ ### Why do AI coding agents overestimate how long a task will take? Coding agents like OpenCode, Codex, pi and Claude Code gave time estimates far higher than their actual execution time in one comparison: OpenCode (GPT-5.5) estimated 18 hours for a task that took 6.1 minutes, a 177x overestimate, while Claude Code overestimated by 12x. One explanation offered is that models generate estimates based on patterns from human development timelines rather than their own execution speed. _Anyone relying on agent time estimates for planning can track agent-behavior findings like this on daily.dev._ ## Similar posts on daily.dev - [AI and NDC London 2026: A .NET Conference From a Developer’s Perspective](https://daily.dev/posts/ai-and-ndc-london-2026-a-net-conference-from-a-developer-s-perspective-rruw1sx8x) · We Are .NET · 0 upvotes · 0 comments - [What I learned at DevTalks Cluj-Napoca 2026](https://daily.dev/posts/what-i-learned-at-devtalks-cluj-napoca-2026-lcgxdifxk) · Vlad Mihalcea · 0 upvotes · 0 comments - [DevDays 2026 Conf From a Speaker’s View](https://daily.dev/posts/devdays-2026-conf-from-a-speaker-s-view-uawono0aq) · We Are .NET · 1 upvotes · 0 comments - [What I Learned from Attending 23 Developer Events in 6 Months](https://daily.dev/posts/what-i-learned-from-attending-23-developer-events-in-6-months-pdoimnwko) · Kilo Blog · 6 upvotes · 0 comments - [Devnexus 2026: Focus on AI with Core Java, Java Frameworks, Security and Career Mentoring](https://daily.dev/posts/devnexus-2026-focus-on-ai-with-core-java-java-frameworks-security-and-career-mentoring-kdodhq1as) · InfoQ · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#architecture](https://daily.dev/tags/architecture), [#rag](https://daily.dev/tags/rag), [#conference](https://daily.dev/tags/conference), [#spec-driven-development](https://daily.dev/tags/spec-driven-development) [View this post on daily.dev](https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3) ```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":"Reviews of DevAI Conference 2026 From a Speaker’s Eye","url":"https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3"},"datePublished":"2026-10-30T13:23:10.418Z","dateModified":"2026-10-30T13:23:52.207Z","description":"A developer recaps DevAI 2026 in Warsaw, a conference with 50 presentations across 4 tracks covering AI topics. One team transformed a Java recruitment system...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/aedbfcfdb9f7aa2d4f383a7432d32fde?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/aedbfcfdb9f7aa2d4f383a7432d32fde?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"We Are .NET","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":"We Are .NET","logo":"https://media.daily.dev/image/upload/s--BsnVOa3i--/f_auto/v1718347410/logos/wearedotnet","url":"https://daily.dev/sources/wearedotnet"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,architecture,rag,conference,spec-driven-development","timeRequired":"PT30M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"We Are .NET","item":"https://daily.dev/sources/wearedotnet"},{"@type":"ListItem","position":3,"name":"Reviews of DevAI Conference 2026 From a Speaker’s Eye"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/reviews-of-devai-conference-2026-from-a-speaker-s-eye-wdpxm1ly3#faq","mainEntity":[{"@type":"Question","name":"How much faster was a .NET rewrite using spec-driven AI development compared to traditional development?","acceptedAnswer":{"@type":"Answer","text":"A 10+ year-old Java recruitment system was rewritten to .NET 10, Blazor and PostgreSQL in 19 working days to a functional platform and 10 weeks to production, versus an estimated 7 to 9 months with traditional development. The team followed a process of business problem to specification to plan to small tasks to code and tests, with human approval at every stage, and shipped 69 changes after adopting it. Teams weighing AI-assisted rewrites can track real-world results like this one on daily.dev."}},{"@type":"Question","name":"Does using Cursor to write code actually increase long-term code quality?","acceptedAnswer":{"@type":"Answer","text":"No. A study comparing 806 GitHub projects that adopted Cursor against 1,380 similar projects found code production increased 28.6% to 281% initially, but code complexity rose 41.6%, static analysis warnings rose 30.3%, and duplicate code density rose 7.03% over the longer term, with the initial productivity gains disappearing within 1 to 2 months. Developers deciding whether to lean on Cursor long-term can follow findings like this on daily.dev."}},{"@type":"Question","name":"Why do AI coding agents overestimate how long a task will take?","acceptedAnswer":{"@type":"Answer","text":"Coding agents like OpenCode, Codex, pi and Claude Code gave time estimates far higher than their actual execution time in one comparison: OpenCode (GPT-5.5) estimated 18 hours for a task that took 6.1 minutes, a 177x overestimate, while Claude Code overestimated by 12x. One explanation offered is that models generate estimates based on patterns from human development timelines rather than their own execution speed. Anyone relying on agent time estimates for planning can track agent-behavior findings like this on daily.dev."}}]} ```