liveBook · Manning

Graceful failure

As explained in AI Governance

Graceful failure is a system-design approach that limits harm and preserves safe behavior when a process halts or encounters an error.

Graceful failure limits harm when an agent encounters a problem or a workflow is halted. The safe default is to block the workflow and escalate to a human, while ensuring a stopped run does not leave work half-processed. section 6.7.1

When an agent behaves unexpectedly, containment can preserve limited operation while restricting its ability to cause harm:

  • Require more human approvals, reduce available tools, or narrow permitted actions while operators investigate. section 4.8.7
  • Use workflow checkpoints and policy rules to block unsafe actions and escalate halted runs to a person. section 6.7.1
  • Keep a kill switch that can halt operations, revoke credentials, and isolate the agent; support both automated triggers and manual override. section 4.8.7

A claim halted mid-process

A stopped claims workflow should not leave a claim stuck in limbo or half-processed. Block the run and escalate it for human attention. section 6.7.1

Table 6.7 Controls for ethical agentic deployments
Control
Why it matters ethically
Classify impact of actions and tools
Impact estimates ensure subsequent controls (e.g. human oversight, autonomy) activate before harm is done.
Autonomy tiers
Ensures that autonomy is proportional to the ethical impacts that may harm individuals.
Accountability
A named human or organization is accountable for harms the agent causes[142].
Plan preview for consequential tasks
Provides a clear explanation of the plan of action and allows the reviewer to make changes to the plan to prevent harms.
Human oversight
Provides meaningful and accessible oversight, built around what a reviewer can actually process.
Workflow design
Checkpoints and constraints outside the agent’s control keep the workflow from drifting off its goals. Graceful failure design ensures a halted run causes no new harm.
Redress path
Protects people from being trapped inside an automated process and aligns with GDPR and EU AI Act oversight requirements.
Monitoring and logging
Collects the evidence needed to redress harms and prevent recurrence.
Multi-step testing
Provides detailed understanding of how harms may propagate in the agentic system.
Memory auditing
Prevents bias from accumulating across sessions and bending future runs off their intended goal.

The controls table identifies workflow checkpoints and graceful failure as safeguards against an agent drifting from its goals. section 6.7.1

How AI Governance covers it

How deep it goes
Defines restriction, blocking, and escalation responses but does not detail recovery implementation.
Examples
Uses a half-processed claim, narrowed tool access, added approvals, and policy-enforced escalation.
What you can do after
Operate agent workflows by restricting actions, blocking unsafe runs, and escalating halted work to humans.
How it connects
Connects to graceful degradation, human oversight, policy engines, kill switches, and monitoring.

Also explained in

Compare how 3 books explain graceful failure →

Related concepts

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