Agents
'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capabilit…
'Agents = model + harness + context' is a much better mental model than treating the LLM as the entire product. The model provides capability, but the harness determines tools, permissions and behavio
"Agents = model + harness + context" is a much better mental model than treating the LLM as the entire product. The model provides capability, but the harness determines tools, permissions and behavior; context determines what the agent knows; evals determine whether the system improves rather than merely changes. This matters for ownership too. Owning intelligence is not just downloading model weights. It means having meaningful control over the complete system that selects models, handles data, executes actions and learns from results. gave a talk "owning your intelligence" - ty @sequoia @sonyatweetybird for having me talked about harnesses and evals and the role they play in owning your intelligence TLDR: > agents = model + harness + context > model - own the weights using something like @FireworksAI_HQ > cont…
Related
- the most important abstraction in AI agents isnt the model — its the harness it orchestrates tools, memory, prompts. this is where all the a…
- Model. Harness. Context. The 3 main components of agents. As you build more agents, context increasingly lives AGENTS.md, skills, policies, …
- deepagents subagents are just tools. when you call a subagent, thats conceptually a function call. this is the simplest mental model for bui…
Source: Harrison Chase (X) | 2026-08-18