Notifications
Clear all
Topic starter
18/08/2026 2:36 pm
TL;DR: Compaction can silently erase in-context agent policies, turning long-horizon AI systems into governance drift machines, according to TruFoundry’s analysis of recent research on governance decay. The operational lesson is that compliance and blast-radius controls must live outside the context window, because anything inside it can be summarized away.
NHIMG editorial — based on content published by TruFoundry: Governance decay, explained: how context compaction erodes agent policy and where enforcement belongs
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, sharing sensitive data, and revealing access credentials.
Questions worth separating out
Q: What breaks when agent policy lives only in prompts or application code?
A: When policy lives only in prompts or application code, it becomes easy to bypass, hard to audit, and fragile across model changes.
Q: Why do long-horizon agents create governance risk for IAM teams?
A: Because the agent behaves like a runtime subject with access to tools and data, but its policy memory can decay over time.
Q: How do security teams know when compaction is weakening control?
A: Look for behaviour changes immediately after summarisation, especially when a rule that was previously enforced suddenly vanishes.
Practitioner guidance
- Move high-consequence rules out of context Place data-handling, tool-use, spend, and approval rules in a gateway or policy plane so they remain enforceable after compaction.
- Track compaction as a security event Log when history is summarised, correlate behaviour changes with compaction points, and investigate any policy loss as a governance failure.
- Separate steering from enforcement Keep tone, preference, and task framing in the prompt, but move compliance and blast-radius controls to durable infrastructure that the agent cannot rewrite.
What's in the full article
TruFoundry's full analysis covers the operational detail this post intentionally leaves for the source:
- A deeper explanation of the governance decay research findings and the benchmark conditions that produced policy loss.
- Examples of out-of-band enforcement patterns for gateways, policy stores, and tool-boundary controls.
- A breakdown of how prompt instructions, memory, and compaction interact across long-horizon agent sessions.
- The article’s own synthesis of how request-path controls differ from in-context steering.
👉 Read TruFoundry's analysis of governance decay and agent policy erosion →
Governance decay in AI agents: where should enforcement live?
Explore further
18/08/2026 3:21 pm
Governance decay is a new name for an old governance mistake: putting controls inside a memory system that is designed to forget them. Long-horizon agents turn context compaction into a policy lifecycle event, which means the control surface is the harness, not the model. For AI governance teams, that shifts the design goal from better prompting to durable enforcement at the request boundary.
A question worth separating out:
Q: What should teams do if an agent can forget its own policy?
A: Treat the prompt as steering, not enforcement. Put access checks, data boundaries, and tool permissions into a gateway or policy layer that evaluates every request, then verify that the same rule applies at turn three and turn three thousand. The control must survive without relying on memory.
👉 Read our full editorial: Governance decay in AI agents shows where policy enforcement belongs
