Join our Newsletter — 33% off our NHI Course

Why do agentic loops turn into workflows with one LLM call?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20225
Topic starter  

TL;DR: Runtime control flow is the real divider, because the next step is either preplanned or selected after an outcome, Archestra explains. Governance has to match the execution shape so adaptive loops get runtime authorization and logging, not workflow-only review.

Editorial analysis by NHI Mgmt Group, based on content published by Archestra: “Most "agents" are workflows with a trigger”.

Key questions

Q: When should a team choose an agent instead of a workflow?

A: Choose an agent only when the number of steps is not known in advance, each result changes the next question, or tool selection depends on runtime state.

Q: What are the security risks of allowing an AI model to choose its next action?

A: The main risk is that the system stops behaving like bounded software and starts behaving like a runtime decision-maker.

Q: What is the difference between an AI agent and an agentic workflow?

A: An AI agent is the autonomous software entity that decides and acts.

Practitioner guidance

  • Classify systems by control-flow shape Document whether the path is fixed in advance or selected at runtime by the model, then use that classification to decide whether the build is a workflow or an agent.
  • Limit runtime authority for adaptive loops If the model can choose the next step, scope its tool access, constrain the action set, and define a hard stop condition before deployment.
  • Audit LLM use inside deterministic pipelines Treat embedded LLM calls as bounded functions when the surrounding graph is fixed, and review them for data handling, output shape, and failure recovery rather than autonomy.

Bottom line: Most systems sold as agents are still deterministic workflows with one model call embedded in the middle.

Glossary terms: Agentic Loop, Deterministic Workflow, Runtime decision authority

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →


This topic was modified 1 week ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20715
 

Most agent branding is really governance debt in disguise: when organisations call a bounded workflow an agent, they often overstate autonomy and understate the controls needed around delegation, logging, and rollback. The operational risk is not the label itself but the false assumption that a model has earned decision rights it does not actually need. Practitioners should classify systems by control flow first and by branding last.

A few things that frame the scale:

  • AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: How should security teams govern agent workflows at runtime?

A: Security teams should govern agent workflows with controls that evaluate prompts, tool calls, and outputs during execution, not only after deployment. Runtime checks matter because risk can appear at each stage of the workflow. The goal is to stop unsafe behavior before it becomes an executed action or a leaked response.

👉 Read our full editorial: Agents vs workflows: where runtime choice really starts


This post was modified 1 week ago by NHI Mgmt Group

   
ReplyQuote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.