---
id: post/demiliani-com/13840
type: post
title: Securely accessing an Azure OpenAI model from an Azure Logic Apps Standard AI agent using a Private Endpoint.
summary: "Summary withheld: an Opus review found that the machine-written summary did not match the post. Read the original post."
tier: community
language: en
tags:
  - azure openai
  - private endpoint
  - security
  - managed identity
  - logic apps
  - vnet integration
  - ai agents
system: integration
review:
  state: flagged
  by: opus
  at: "2026-10-08T01:54:52.447Z"
  flags: []
generated:
  at: "2026-10-08T01:26:53.141Z"
  pipeline: 0.2.0
  prompts:
    extract-post: 1
  input_hash: 51ee50433a90bb81edd6f54666d443bb7427f6d37b7c157494ba4e3d4a9a7b22
evidence:
  - kind: blog
    url: https://demiliani.com/2026/06/16/securely-accessing-an-azure-openai-model-from-an-azure-logic-apps-standard-ai-agent-using-a-private-endpoint/
    title: Securely accessing an Azure OpenAI model from an Azure Logic Apps Standard AI agent using a Private Endpoint.
    date: "2026-06-16"
    commit: null
    t: null
    quote: null
  - kind: blog
    url: https://demiliani.com/2026/06/16/securely-accessing-an-azure-openai-model-from-an-azure-logic-apps-standard-ai-agent-using-a-private-endpoint/
    title: Securely accessing an Azure OpenAI model from an Azure Logic Apps Standard AI agent using a Private Endpoint.
    date: "2026-06-16"
    commit: null
    t: null
    quote: All traffic flows privately. No data traverses the public internet.
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
post_id: "13840"
source_id: demiliani-com
source_name: Stefano Demiliani
url: https://demiliani.com/2026/06/16/securely-accessing-an-azure-openai-model-from-an-azure-logic-apps-standard-ai-agent-using-a-private-endpoint/
published_at: "2026-06-16T07:56:52.000Z"
author: Stefano Demiliani
full_text: false
words: 1897
quotes:
  - text: All traffic flows privately. No data traverses the public internet.
    why_it_matters: Summarizes the security goal achieved by the architecture described
code_objects_mentioned: []
systems:
  - integration
  - copilot
  - platform
versions_mentioned: []
preview:
  embeddable: true
  frame_url: https://demiliani.com/2026/06/16/securely-accessing-an-azure-openai-model-from-an-azure-logic-apps-standard-ai-agent-using-a-private-endpoint/embed/
  image: https://i0.wp.com/demiliani.com/wp-content/uploads/2026/06/azureopenaiprivateendpoint_00.png?fit=1200%2C792&ssl=1
  image_alt: null
  image_w: 1200
  image_h: 792
  site_name: Stefano Demiliani
  favicon: https://demiliani.com/wp-content/uploads/2022/09/sd_wordpress_logo.png?w=32
  probed_at: "2026-10-07T11:50:34.760Z"
---

# Securely accessing an Azure OpenAI model from an Azure Logic Apps Standard AI agent using a Private Endpoint.

[Read the post](https://demiliani.com/2026/06/16/securely-accessing-an-azure-openai-model-from-an-azure-logic-apps-standard-ai-agent-using-a-private-endpoint/) · Stefano Demiliani (Stefano Demiliani, MVP) · 2026-06-16 · 1897 words · tier community · **flagged** (a review found a problem)

> Summary withheld: an Opus review found that the machine-written summary did not match the post. Read the original post.

## Quotes

- "All traffic flows privately. No data traverses the public internet." (Summarizes the security goal achieved by the architecture described)

## Context

- Features: Agent Loop capability, Private Endpoint configuration, Virtual Network integration, System-assigned Managed Identity, Cognitive Services OpenAI User role, Private DNS Zone, VNet subnet delegation

Source: Stefano Demiliani, community blog. Summary, key points and quotes are derived (CONTENT-NOTICE.md); read the original for the full text.