Agent vs model: clarifying the AI stack
A blog post clarifies the distinction between an agent and a model, explaining that an agent system comprises a harness, tools, and an inference service running a model. It notes that features like MCP and Skills are part of the harness layer, not the model.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Suno user reports published song changed after a year
- Suno users debate AI music quality patterns
- Databricks uses AI to accelerate incident investigation
- AWS introduces Agentic Resource Discovery (ARD) spec for agent discovery
- Users frustrated by Enter-to-send in AI chat interfaces