--- title: From Blind Spots to Merged PRs: Continuous Agentic... description: A conference talk from the CTO of Thundra describing how they built an autonomous agentic workflow to continuously detect and fix performance issues in... canonical: https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud | daily.dev og:description: A conference talk from the CTO of Thundra describing how they built an autonomous agentic workflow to continuously detect and fix performance issues in... og:url: https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k og:image: https://api.daily.dev/og/posts/CU3X9dn0k.png og:image:alt: From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud 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. # From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 22 min read · 0 upvotes · 0 comments ## Summary A conference talk from the CTO of Thundra describing how they built an autonomous agentic workflow to continuously detect and fix performance issues in production applications. The system runs weekly via GitHub Actions using Claude Code and MCP to capture function-level runtime traces, scores optimization opportunities by business impact and risk, verifies fixes by re-running tests, and surfaces human-readable reports to Slack rather than flooding engineers with PRs. Key lessons include: grounding agent suggestions in real production context rather than static analysis, building scoring/guardrails to filter low-ROI fixes, starting with one PR at a time to build trust, and recognizing that agentic automation requires 80-90% confidence thresholds unlike interactive IDE usage. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Agentic automation in practice: putting standard engineering work on autopilot](https://daily.dev/posts/agentic-automation-in-practice-putting-standard-engineering-work-on-autopilot-km13vjz8f) · Atlassian · 0 upvotes · 0 comments - [The future of AI-powered software optimization \(and how it can help your team\)](https://daily.dev/posts/the-future-of-ai-powered-software-optimization-and-how-it-can-help-your-team--v63fkk8ns) · GitHub Blog · 0 upvotes · 0 comments - [Continuous integration and continuous delivery for agentic AI](https://daily.dev/posts/continuous-integration-and-continuous-delivery-for-agentic-ai-lhegkveiq) · Red Hat Developer · 5 upvotes · 0 comments --- Tags: [#performance](https://daily.dev/tags/performance), [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability), [#mcp](https://daily.dev/tags/mcp), [#clickhouse](https://daily.dev/tags/clickhouse) [View this post on daily.dev](https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k) ```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":"From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud","url":"https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k"},"datePublished":"2026-07-19T14:06:38.132Z","dateModified":"2026-07-19T14:35:33.146Z","description":"A conference talk from the CTO of Thundra describing how they built an autonomous agentic workflow to continuously detect and fix performance issues in...","image":"https://i.ytimg.com/vi/JJGbw4ggaFs/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/JJGbw4ggaFs/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","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":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/from-blind-spots-to-merged-prs-continuous-agentic-performance-optimization---may-walter-hud-cu3x9dn0k","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"performance,ai-agents,observability,mcp,clickhouse","timeRequired":"PT22M","video":{"@type":"VideoObject","name":"From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud","description":"A conference talk from the CTO of Thundra describing how they built an autonomous agentic workflow to continuously detect and fix performance issues in...","thumbnailUrl":"https://i.ytimg.com/vi/JJGbw4ggaFs/sddefault.jpg","uploadDate":"2026-07-19T14:06:38.132Z","duration":"PT22M","url":"https://api.daily.dev/r/CU3X9dn0k","embedUrl":"https://www.youtube.com/embed/JJGbw4ggaFs"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud"}]} ```