←Story detail

Trending story

Anthropic launches dynamic workflow feature

1 reports1 story updatesUpdated Oct 13 02:18

Understand this story

AI overview

At AI Engineer New York, Anthropic introduced a new feature: dynamic workflows (flows). According to a report by Latent Space, the feature is defined as a multi-agent orchestration approach for high-load tasks: a lead agent formulates a plan and writes the orchestration program, launches sub-agents, collects results, and manages the flow of information, so developers no longer need to configure the coordinator and the list of sub-agents themselves. The feature is located in the Claude Console, and developers can still pass in preconfigured specialized sub-agents in the agent configuration. The speaker said that flows are much more expensive than single-agent approaches but are better at finding all the details; developers can set a session budget, and the model does not know its own budget while running. Currently, there are no facts about further developments of this feature.

AI-generated from public reports

Latest development · Report

Anthropic Launches Dynamic Workflows, Letting Claude Orchestrate Multi-Agent Systems on Its Own

Developments

1 confirmed developments

  1. Anthropic launches dynamic workflow feature

    Source:Latent Space

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 13

  1. Latent Space

    Anthropic Launches Dynamic Workflows, Letting Claude Orchestrate Multi-Agent Systems on Its Own

    At AI Engineer New York, Anthropic introduced a new feature called dynamic workflows (flows), defined as a multi-agent orchestration approach for high-load tasks: a lead agent draws up a plan and writes the orchestration program, launches sub-agents, collects results, and manages the flow of information, so developers no longer need to configure the coordinator and sub-agent roster themselves. The feature lives in Claude Console, and developers can still pass in preconfigured specialized sub-agents in the agent configuration. The speaker said flows cost far more than single-agent approaches but are better at finding all the details, and that developers can set a session budget, though the model does not know its budget while running.

Related stories

  1. Related storiesEnglish translation is being prepared.
  2. Related storiesAnthropic releases Claude Opus 5.5
  3. Related storiesGoogle releases image model Nano Banana 2.1
  4. Related storiesGemini 4 Argon appears on the GCP quota page