liveBook · Manning

Execution topology

As explained in Designing AI Agents

A structural arrangement that determines how steps or agents are organized and executed in an agent system.

An execution topology is the arrangement through which work and information move in an agent system. It describes how a design runs; a cognitive function describes what the design is meant to do. A fixed pipeline can use an LLM without being an agent: model-directed control flow distinguishes an agent. section 1.1 section 2.3.1

Six recurring flow shapes provide a framework-neutral vocabulary:

Figure 2.4 The six execution flow shapes used as the map's X-axis. The diagrams show data flow; cognitive function supplies the design intent.

Compare the six flow shapes independently of their cognitive purpose. section 2.3.1

The same topology can serve different functions, and one function can use different topologies. A loop might test reasoning hypotheses or coordinate adversarial review; those designs have different evidence ownership and failure modes. Conversely, reasoning can use a chain, route, or parallel exploration. section 2.3.2

Route a pull request by complexity

A code-review agent can send a simple rename to a quick check and a caching-layer change to deeper analysis. Routing spends more latency and cost where greater scrutiny is warranted. section 1.4.1

Choose a topology from the task outcome and dominant constraint, such as missed evidence, reasoning cost, action risk, latency, or coordination. Compare candidates against failure modes and trust boundaries as well as cost and latency. Then decide what the harness controls, what the model decides, where state lives, and how errors are contained. section 2.3 section 1.4

How Designing AI Agents covers it

How deep it goes
Defines six flow shapes and compares their cognitive uses, failure modes, and selection constraints.
Examples
Uses code-review routing to contrast a quick rename check with deeper analysis of a caching-layer change.
What it assumes
Assumes experience calling an LLM API and trying a simple tool-calling or agent workflow, but not production experience or a specific framework.
What you can do after
Evaluate and compare candidate flow structures against cost, latency, failure modes, and trust boundaries.
How it connects
Connects execution topology with cognitive functions, agent harnesses, governance, and model-directed control flow.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Designing AI Agents. The section links point to the parts of the book it draws on.