Multi-Agent
-
The Harness Is No Longer Hand-Built: Meta-Orchestration and the Rise of Self-Evolving Agents
Raven constructs and revises its own agent harness, and OpenAI's Agents API turns the harness into a managed service. Two moves automating the same layer away from developers, and why the audit problem is the part that matters.
-
Topology as the New Dial: Supervisors, Swarms, and Who Holds the State
The framework debate consolidated into a spectrum. The next argument is over orchestration topology: every multi-agent design reduces to who holds state and control, and a February 2026 research cluster is formalizing that choice as an optimization problem rather than a brand pick.
-
Single-Prompt AI Hit Its Ceiling — the Next Gap Is Durable Execution
Andrew Ng's 2024 numbers made the empirical case that workflows beat models. By 2026 the missing layer is no longer the framework but the runtime: durable execution and durable memory. A single prompt has no state to lose; an agent does.