Dynamic Workflow
An AI agent execution pattern in which an agent dynamically determines at runtime which sub-agent or tool to invoke next based on the current state. In contrast to static pipelines with predefined steps, dynamic workflows allow task paths to be adjusted in real time as context changes.
Timeline (last 90 days)
Anthropic positions dynamic workflows as the first step toward directing test-time compute at difficult problems and making scientific discovery broadly achievable by the public.
Dynamic workflows are defined as an entirely new way of multi-agent orchestration, built specifically for the most ambitious workloads.
Dynamic workflows allow Claude to decide and orchestrate its own multi-agent topology, rather than developers pre-statically configuring a coordinator and a roster of sub-agents.
Users can still pass in pre-configured expert sub-agents in the agent configuration of dynamic workflows.
The model does not know at runtime how much available budget (token budget) it has, but developers can set a session budget.
In dynamic workflows, sub-agents share a file system and can exchange information through it, but developers cannot directly instruct one workflow sub-agent via the API to send a message to another.
Developers can always inspect sub-agent behavior through the graphical features within the Claude Console, including viewing the payload the lead agent passes to sub-agents.
Whether dynamic workflows let a stock watchlist flow self-improve (such as identifying that the scanning model is insufficient and changing the next plan) is not a built-in feature, but hill climbing and dreaming can be combined to improve the loop.
At the AI Engineer New York 2026 conference, Anthropic released and shared a new feature, dynamic workflows (flows).
Dynamic workflows allow subsequent steps to be adjusted at runtime based on intermediate results, unlike static DAGs.
6 more timeline events
All Facts (16)
Anthropic positions dynamic workflows as the first step toward directing test-time compute at difficult problems and making scientific discovery broadly achievable by the public.
50%UnverifiedDynamic workflows are defined as an entirely new way of multi-agent orchestration, built specifically for the most ambitious workloads.
50%UnverifiedDynamic workflows allow Claude to decide and orchestrate its own multi-agent topology, rather than developers pre-statically configuring a coordinator and a roster of sub-agents.
50%UnverifiedUsers can still pass in pre-configured expert sub-agents in the agent configuration of dynamic workflows.
50%UnverifiedThe model does not know at runtime how much available budget (token budget) it has, but developers can set a session budget.
50%UnverifiedIn dynamic workflows, sub-agents share a file system and can exchange information through it, but developers cannot directly instruct one workflow sub-agent via the API to send a message to another.
50%UnverifiedDevelopers can always inspect sub-agent behavior through the graphical features within the Claude Console, including viewing the payload the lead agent passes to sub-agents.
50%UnverifiedWhether dynamic workflows let a stock watchlist flow self-improve (such as identifying that the scanning model is insufficient and changing the next plan) is not a built-in feature, but hill climbing and dreaming can be combined to improve the loop.
50%UnverifiedThe core idea of Anthropic's dynamic workflow is to let multiple specialized agents each do their own job, coordinated through a workflow engine, rather than scaling up a single model.
50%UnverifiedDynamic workflows allow subsequent steps to be adjusted at runtime based on intermediate results, unlike static DAGs.
50%UnverifiedThe orchestration layer of a dynamic workflow is responsible for three things: task decomposition, agent routing and result aggregation.
50%UnverifiedAnthropic says dynamic workflows have been trialed internally in scenarios such as code migration and document generation.
50%UnverifiedDynamic workflows are better suited to scenarios requiring multi-step reasoning and the coordination of multiple tools, such as refactoring a large codebase or cross-modal content generation.
50%UnverifiedAnthropic recommends that developers dynamically enable the number of agents according to task complexity, avoid over-orchestration, and treat the token budget as a first-class workflow constraint.
50%UnverifiedAnthropic's dynamic workflow is currently closer to a "scheduler" stage, and gaps remain in observability, security, permissions and cross-vendor interoperability before it becomes a complete agent operating system.
50%UnverifiedAt the AI Engineer New York 2026 conference, Anthropic released and shared a new feature, dynamic workflows (flows).
50%