{"version":1,"type":"story","url":"https://digestai.news/story/engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow","json":"https://digestai.news/story/engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow.json","markdown":"https://digestai.news/story/engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow.md","slug":"engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow","headline":"Engineer reports 11x PR increase after switching to AI-native workflow","summary":"Neil Kakkar, a software engineer with nine years of experience, details how his output increased from 8-20 pull requests per month at PostHog to over 200 per month at Tano, an AI-native startup. This represents an 11x increase in shipping volume. Kakkar attributes this shift to using Claude Code Desktop, which allows him to build entire features with minimal human input, often running agents for 1-2 hours to complete end-to-end tasks.\n\nAt Tano, traditional constraints like mandatory code reviews and heavy communication overhead have been removed. Engineers work independently, with one person owning the full stack from design to backend. Code reviews are now handled by automated agents via GitHub Actions, with human reviews becoming optional after an initial onboarding period. Kakkar notes that while this speed brings risks, such as the agent making logical errors in currency calculations, the team accepts the trade-off of fixing issues post-deployment rather than slowing down for manual verification.\n\nThe article highlights that this productivity gain is not just about faster typing but a cultural shift. Kakkar argues that pre-AI bottlenecks like peer review and coordination no longer apply when AI handles the bulk of the work. He suggests that for straightforward features, a single engineer using AI is more effective than a small team coordinating manually. However, he warns that this approach requires a high level of trust and can lead to context switching issues if not managed carefully.","keyPoints":["Neil Kakkar ships 200+ PRs monthly at Tano, an 11x increase over his previous role at PostHog.","Tano uses Claude Code Desktop for autonomous feature building, with agents running for 1-2 hours per task.","Human code reviews are optional at Tano, replaced by automated agent reviews in continuous integration."],"whyItMatters":"This case study illustrates a significant shift in software engineering productivity, suggesting that AI-native workflows can decouple output from headcount. It highlights the trade-off between speed and quality control, where automated reviews replace human oversight, potentially changing how teams structure their development processes.","category":{"slug":"society","name":"Society & Work","url":"https://digestai.news/category/society"},"entities":{"companies":["Tano","PostHog","Bloomberg","Google"],"models":["Claude Code Desktop"],"people":["Neil Kakkar"]},"firstPublishedAt":"2026-11-04T09:45:17Z","updatedAt":"2026-11-04T09:45:17Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"newsletter.pragmaticengineer.com","title":"A software engineer details how he went from merging eight to 20 pull requests per month to 200+ after joining AI-native creator startup Tano eight months ago","url":"https://newsletter.pragmaticengineer.com/p/how-software-engineering-is-changing","publishedAt":"2026-11-04T09:45:17Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[{"site":"Hacker News","url":"https://news.ycombinator.com/item?id=50356462","points":5}],"thread":null,"cite":{"text":"Digest AI, \"Engineer reports 11x PR increase after switching to AI-native workflow\", 4 November 2026, https://digestai.news/story/engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow","publisher":"Digest AI","title":"Engineer reports 11x PR increase after switching to AI-native workflow","datePublished":"2026-11-04T09:45:17Z","url":"https://digestai.news/story/engineer-reports-11x-pr-increase-after-switching-to-ai-native-workflow"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}