{"version":"1.0","type":"card","id":"3cd93748-cb8c-4548-a8a0-f7b2ba584e5c","url":"https://stacklist.com/card/3cd93748-cb8c-4548-a8a0-f7b2ba584e5c","title":"Integrating Open-Code-Review with DeepSeek Harness","source_url":"https://lnkd.in/p/exSPeY78","note":"This page discusses the integration of open-code-review with deepseek-harness, highlighting the evolving architecture and the shift away from relying solely on LLMs for code review processes. It emphasizes the importance of deterministic pipelines and the role of agents in managing code reviews effectively.","image":{"url":"https://ucarecdn.com/0822433a-140a-482b-a187-784dd5aa2815/","alt":"Integrating Open-Code-Review with DeepSeek Harness","width":800,"height":520},"stack":{"id":"1659549d-373d-4391-ba12-5a14d40c19ed","title":"Harness Management","url":"https://stacklist.com/c/technology/stack/1659549d-373d-4391-ba12-5a14d40c19ed"},"created_at":"2026-09-17T05:48:04.751Z","updated_at":null,"aco":{"summary":"Mitko Vasilev discusses integrating open-code-review with deepseek-harness to build a hybrid system where deterministic code handles file selection and scheduling while AI agents focus on semantic analysis and risk detection. The approach emphasizes owning private AI infrastructure and combining models, harnesses, sandboxes, and review engines into a software factory system rather than simple prompt-to-LLM workflows.","tags":["code-review","ai-agents","llm-architecture","deterministic-pipeline","deepseek","open-source","software-engineering"],"key_entities":[{"name":"Mitko Vasilev","type":"person","confidence":0.99},{"name":"Jonathan Kuzmanko","type":"person","confidence":0.85},{"name":"Nils W.","type":"person","confidence":0.85},{"name":"Bernard Sia","type":"person","confidence":0.85},{"name":"Mike Cecconello","type":"person","confidence":0.85},{"name":"Luis Coimbra","type":"person","confidence":0.85},{"name":"deepseek-harness","type":"technology","confidence":0.95},{"name":"open-code-review","type":"technology","confidence":0.95},{"name":"DeepSeek","type":"technology","confidence":0.9},{"name":"ArchGenerator.com","type":"technology","confidence":0.8},{"name":"deterministic-pipeline","type":"concept","confidence":0.9},{"name":"sub-agents","type":"concept","confidence":0.9},{"name":"reflection-stage","type":"concept","confidence":0.9},{"name":"LLM-as-a-Judge","type":"concept","confidence":0.85},{"name":"LinkedIn","type":"organization","confidence":0.95}],"classification":"transcript","language":"en","confidence":0.85,"provenance":{"model":"claude-haiku-4-5","tool":"@stacklist/be@0.1.0","confidence":0.85,"timestamp":"2026-09-17T05:48:22.316Z"},"token_counts":{"approximate":1399,"cl100k":1179},"content_hash":"sha256:d2ae796a1f9fb15378aed129ef2cb32539e059e138911fc9bade5ec3b073e3a1","acp_version":"0.2","body_available":true,"body_tokens":1399,"visibility":"public","agent_accessible":true,"status":"final"},"_links":{"self":"/api/public/card/3cd93748-cb8c-4548-a8a0-f7b2ba584e5c.json","html":"https://stacklist.com/card/3cd93748-cb8c-4548-a8a0-f7b2ba584e5c","md":"/api/public/card/3cd93748-cb8c-4548-a8a0-f7b2ba584e5c.md","stack_json":"/api/public/stack/1659549d-373d-4391-ba12-5a14d40c19ed.json"}}