Harness for hybrid teams
What has to exist around a model so humans and agents can work on the same team, with trust?
The model sets the ceiling of intelligence. The harness — context, tools, loop and governance — decides how much of that ceiling reaches real work.
The most mature line in the lab. It comes from building the OrganIA platform (agent-builder) and Squad Híbrido: agents working alongside people, with shared memory, live dashboards and governance.
What I am investigating
- Harness engineering: why production failures are rarely the model’s fault.
- Context engineering: context as a budget, not a warehouse.
- Memory: each person’s second brain and the company brain, without copying data.
- Interface: the agent’s answer as an operable dashboard (Live Apps), and configuring the platform by talking (No Brain Mode).
- Evolution under governance: the agent that improves with use without changing on its own.
Agent-to-agent protocol across systems. On the radar, not yet built into the platform.
ag-ui-protocol/ag-uiUsingAG-UIAgent–UI protocol. Powers the visual blocks and Live Apps in the OrganIA platform.
langchain-ai/langgraphUsingLangGraphStateful agent orchestration. Part of the agent-builder execution core.
modelcontextprotocol/modelcontextprotocolUsingModel Context ProtocolStandard for connecting agents to external tools and data. Used for remote tools in the platform.