liveBook · Manning

Uncertainty

As explained in Designing AI Agents

Uncertainty is the lack of complete predictability about a system's state, behavior, or outcome.

Uncertainty is an operating condition of agent systems: the language model’s behavior is probabilistic, its reasoning is opaque, and its failures can include hallucination, drift, and unbounded loops. Agent architecture must allocate resources within bounds even when the decision-maker itself is unpredictable. section 1.0 section 1.5

Three forms of uncertainty shape agent architecture:

  • Output uncertainty: the same prompt can produce different responses. A retry may return a different answer rather than repeat the original result. section 1.2.2
  • Behavioral uncertainty: the agent chooses actions at runtime. A reasoning-and-action loop can vary in both length and content. section 1.2.2
  • Environmental uncertainty: the world can change between observations. Page layouts, codebases, and data sources may change or become unavailable. section 1.2.2

Conventional controls such as timeouts, retries, and tolerant parsers contain some uncertainty, but agent architectures must account for it from the start. Earlier distributed-systems patterns offer useful precedents: circuit breakers inform loop detectors, while saga transactions inform plan-and-execute workflows. section 1.2.2 section 1.5

How Designing AI Agents covers it

How deep it goes
Distinguishes three forms of uncertainty and their architectural implications without specifying a detailed implementation.
Examples
Illustrates uncertainty with variable model responses, reasoning-and-action loops, changing web pages, and evolving codebases.
What you can do after
Evaluate agent architectures by identifying output, behavioral, and environmental uncertainty.
How it connects
Connects uncertainty to retries, circuit breakers, loop detection, saga transactions, and plan-and-execute workflows.

Also explained in

Compare how 17 books explain uncertainty →

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.