liveBook · Manning

Threshold

As explained in Architecting Autonomous Agentic Systems

A cutoff on decision confidence that determines whether an automated decision can proceed or requires escalation.

A threshold is a confidence cutoff that determines whether an automated decision proceeds or escalates to a human. It turns uncertain model judgment into an explicit architectural boundary. section 1.2.2 section 4.6

Consider claims triage: a pilot classified medical claims with 94% accuracy and reduced triage time from 40 minutes to 4. However, the remaining 6% outside the approved confidence boundary had unknown consequences. A high-acuity claim misclassified as routine could wait 48–72 hours, creating downstream costs of $8,000–$50,000 per case. section 3.1

Use thresholds as part of a bounded-autonomy design:

  • Define the confidence band in which an agent may act and the boundary beyond which it must escalate. section 4.6
  • Estimate the consequences of decisions outside the boundary, rather than evaluating accuracy alone. section 3.1
  • Enforce the threshold architecturally so escalation still occurs when the agent’s reasoning is wrong. section 1.2.2
  • Assign escalation ownership and keep accountability with the named business owner when execution shifts between agents and humans. section 4.6

Claims triage

At 50,000 claims annually, a 2% harmful error rate could produce $8M–$50M in expected downstream failure costs, outweighing the pilot’s projected $1.8M labor savings. The threshold therefore governs both autonomy and the business case. section 3.1

How Architecting Autonomous Agentic Systems covers it

How deep it goes
Defines thresholds as runtime guardrails and connects them to authority, escalation, accountability, and consequence analysis.
Examples
Uses medical-claims triage, a 94% accuracy pilot, and projected harmful-error costs to expose threshold economics.
What it assumes
Assumes familiarity with automated decisions and introduces runtime guardrails as controls that operate beyond agent reasoning.
What you can do after
Design bounded autonomy by defining confidence bands, escalation paths, enforcement controls, and accountable ownership.
How it connects
Connects confidence thresholds with guardrails, escalation, authority boundaries, policy violations, and consequence thresholds.

Also explained in

Compare how 20 books explain threshold →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Architecting Autonomous Agentic Systems. The section links point to the parts of the book it draws on.