TL;DR: Runtime tool use is the governance pressure point in agentic AI examples in Python, WorkOS says, because the system can change actions and recover from failure without redeploys. Access, logging, and revocation have to follow each delegated action so those runtime choices stay bounded and auditable.
Editorial analysis by NHI Mgmt Group, based on content published by WorkOS: “Agentic AI Examples”.
Key questions
Q: When does agentic automation create more governance risk than it reduces?
A: It becomes riskier when the organisation cannot explain why a particular execution path was chosen, cannot verify reconciliation quickly, or cannot contain exceptions in legacy systems.
Q: What are the signs that an agentic workflow is exceeding its intended control boundary?
A: Warning signs include hidden retries, widening search windows, unlogged tool calls, persistent state that outlives the task, and fallback logic that keeps expanding scope.
Q: What breaks when software can choose actions at runtime instead of following fixed code paths?
A: Fixed-path governance breaks when the next action is no longer known in advance.
Practitioner guidance
- Define tool-level authorisation boundaries Map every API, shell, database, and messaging action an agent can invoke, then bind each one to explicit scopes, ownership, and revocation paths.
- Separate goal input from privilege assignment Avoid giving the same runtime entity both the objective and unrestricted access.
- Log decision traces and state transitions Record prompt changes, tool selections, retries, and fallback branches so investigators can reconstruct why the system acted the way it did.
Bottom line: Agentic AI examples in Python show why deterministic branch logic is no longer the only viable execution model for delegated work.
Glossary terms: Agentic AI, Deterministic Codemod, Runtime Authorisation, Decision trace
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Deterministic control assumptions collapse once software can choose its own execution path: Branch-based governance assumes the next action is known at design time. That assumption fails when an agent forms a plan, selects a tool, and decides whether to retry or switch strategy at runtime. The implication is that access governance has to move from static path review to runtime authorisation and traceability.
A few things that frame the scale:
- 67% of organisations still rely heavily on static credentials despite the risks they pose to agentic AI deployments, according to the 2026 Infrastructure Identity Survey.
- Gartner predicts that by the end of 2026, 40% of enterprise apps will feature task-specific AI agents.
A question worth separating out:
Q: How should security teams govern delegated control in autonomous AI systems?
A: They should treat delegated control as a first-class identity problem, not a by-product of application integration. That means binding every action to a named owner, a defined purpose, and a constrained scope, then reviewing whether the agent still operates within those limits as its behaviour changes. Accountability must remain traceable throughout the agent lifecycle.
👉 Read our full editorial: Agentic AI examples in Python reveal the limits of deterministic code