Curated by
More in Harness Management
See all 38 →More from Mike Boscia
See all stacks →Integrating Open-Code-Review with DeepSeek Harness
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.
Built for AI agentsACO · 1399 tokens
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
Mitko Vasilev (person, 0.99) · Jonathan Kuzmanko (person, 0.85) · Nils W. (person, 0.85) · Bernard Sia (person, 0.85) · Mike Cecconello (person, 0.85) · Luis Coimbra (person, 0.85) · deepseek-harness (technology, 0.95) · open-code-review (technology, 0.95) · DeepSeek (technology, 0.9) · ArchGenerator.com (technology, 0.8) · deterministic-pipeline (concept, 0.9) · sub-agents (concept, 0.9) · reflection-stage (concept, 0.9) · LLM-as-a-Judge (concept, 0.85) · LinkedIn (organization, 0.95)
Classification
transcript · language en · status final
Provenance
claude-haiku-4-5 via @stacklist/be@0.1.0, confidence 0.85, 17 Sep 2026