Code Remix Summit 2026
| title | author | length |
|---|---|---|
| AI Coding Agents Don't Need Bigger Models. They Need Better Tools. | Jonathan Schneider | 31m |
Frontier, inference-only migrations succeed only about 30–40% of the time because huge models still read plain text files; replacing text with a Lossless… | ||
| Netflix’s Journey to Confident Automated Changes | Aubrey Chipman, Roberto Perez Alcolea | 54m |
Netflix runs automated dependency updates across ~5.6k repositories and ~3.6k Java applications (40k active libraries, ~1,500 Java engineers) and moves from… | ||
| Building The Upgrade Muscle with OpenRewrite at Tinder | Devin Thomson, Ryan Trontz | 43m |
Tinder describes a four‑stage upgrade pipeline that moves from spreadsheets to fully automated PR generation, using OpenRewrite recipes to rewrite tests and… | ||
| Your pipeline is the bottleneck | Cory Lucas | 26m |
AI increases code output but moves the bottleneck to review, testing, and integration: Faros finds a 210% increase in coding tasks while time from commit to… | ||
| Automating Language Migration at Scale: Tools, Tradeoffs, and the Role of AI | Eve Matthaey | 26m |
Meta builds a 250-step Kotlinator that combines a headless IntelliJ converter with AST transforms in Editus, JetBrains PSI parsing, Buck-aware symbol… | ||
| Verification, Cost, and Speed: What's Next for AI Coding at Scale | Harald Aamot, Anshu Chadha, Brian Houck, Dov B. Katz, Rachel Laycock, Jonathan Schneider | 57m |
Panel distills practical claims: verification often costs more than generation so teams use AI to produce test harnesses and deterministic checks (recipe runs… | ||
| From Developer Pain to Impact: Establishing Large Scale Refactoring at SAP | Harald Aamot | 51m |
Enterprise builds a centrally hosted, scalable refactoring platform using OpenRewrite and a mix of bots, GitHub Actions and AI to onboard repos automatically… | ||
| Scaling code health with always on rewrites and AI at Spotify | Jonatan Dahl, Sanjana Seetharam | 40m |
Spotify describes a system that applies Java conventions across 2,900 services and 190,000 repos using OpenRewrite and Error Prone, rolls changes via a… | ||
| The Human Side of AI: Unlocking Opportunity in the New Bottlenecks of Software Development | Rachel Laycock, Kiran Rouzie | 53m |
Early claims of 50% faster prediction fails after tests show coding assistants speed individual devs but simply move the bottleneck to upstream work like… | ||
| The State of AppSec in the Era of AI [Panel] | Hank Vuong, Jonathan Schneider, Mark Kraynak, Eric Baran, Matt Finkelstein | 43m |
Claim: AI pushes AppSec from finding bugs to actually fixing them by running scripted agents that test and apply changes at scale. Evidence: a single business… | ||
| Supporting Custom Frameworks and Upgrades at Squarespace with Moderne | Stacey Watro, Ellen DeWitt | 42m |
Squarespace replaces brittle Tyson CD with Moderne, building an ingestion job that builds LSTs to auto-onboard Java repos, a grouping config to map repos to… | ||
| Moderne + OpenRewrite at Morgan Stanley: 5 Lessons From a Year at Scale | Dov B. Katz, Khalid Elsawaf | 34m |
Morgan Stanley deploys Moderne and OpenRewrite across 5,000 users onboarded, with 2,000+ recipes run and 1,000+ commits shipped, and finds adoption requires… | ||
| Closing the Agentic DevOps Loop with Microsoft and Moderne | Patrick Vuong | 42m |
GitHub Copilot runs as a cloud agent calling Moderne’s MCP and Azure MCP to make deterministic code changes across repos; a live Java 11 to Java 25 migration… | ||
| How Uber Migrated 1.25M Lines from JUnit 4 to 5 with OpenRewrite | Anshuman Mishra, Kaushik Vejju | 38m |
Uber migrates over 75,000 test classes and 1.25 million lines from JUnit 4 to JUnit 5 using OpenRewrite with Bazel integration, producing more than 5,000 PRs… | ||
| How BNY Uses Moderne to Make AI Agents Cheaper and More Accurate | Marcin Osiecki | 40m |
BNY runs Moderne and OpenRewrite to extract deterministic metadata before any LLM call, using regex-based recipes to output CSV + Markdown that agents consume… | ||
| Speed Is Easy, Trust Is Hard: AI's Real Impact on Developer Productivity | Brian Houck | 44m |
AI boosts hands‑on coding efficiency — 40% more PRs per hour — yet org throughput rises only 7.8% overall PR velocity because coding is ~14% of time and just… | ||
| Beyond Grep: Semantic Code Search for Safer Change at Scale | Bryan Friedman | 37m |
Searches moving from grep to IDEs to Tree-sitter and trigram indexes leave gaps at portfolio scale, so Moderne builds a Lossless Semantic Tree that preserves… | ||
| Architecture Modernization Anti-Patterns: The Cost of Good Intentions | Javiera Laso | 59m |
Two real client rebuilds show carefully planned modernizations fail from misaligned intentions: a 30-year retail stack with 10,000 employees spends three years… | ||
| 10 Lessons for Enterprise Code Modernization with OpenRewrite & Moderne | Ben Muschko | 44m |
Ten concrete lessons for moving large-scale refactors from stalled projects into everyday engineering: proven playbook using OpenRewrite and Moderne to open… | ||
| Upgrade Your Java with AI: From Legacy Code to High-Performance Workloads | Vinicius Senger, Jonathan Vogel | 53m |
Shows an end-to-end workflow that uses AI agents and the ATX CLI to ingest a runtime JFR recording, map hotspots to source, and generate OpenRewrite-style… | ||
| How Google Uses LLMs to Migrate Code Across Its Monorepo | Celal Ziftci | 44m |
Google builds a deterministic LLM pipeline that finds references via the Kite code index (tracing up to five hops), categorizes every hit, runs an internal… | ||
| Agentic Coding at AirBnb | Szczepan Faber | 31m |
Airbnb reports 97% weekly PR authors using agentic AI with many engineers saying it saved more than eight hours a week; PR throughput rises after two flat… | ||
| nothing matches | ||