Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
117 questions with Content Safety in Foundry Control Plane tags
1 answer
Intermittent Azure OpenAI Content Filter Blocking a Benign Appointment Booking Chat Due to High Violence Detection
Hi everyone, We run customer-facing chatbots on Azure openAI, orchestrated with Semantic kernel. Some of them get a prompt-side content filter block in the violence category (severity "high"), even though the conversation is an ordinary…
Content Safety in Foundry Control Plane
asked
2026-09-11T07:08:01.55+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(128, 44%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ENN%3C/text%3E%3C/svg%3E)
Nishyanth Nandagopal
0
Reputation points
answered
2026-09-11T07:08:27.1933333+00:00
AI answer
0 answers
Intermittent "violence: high" content filter block on a benign appointment-booking chat – Azure OpenAI Title: Intermittent "violence: high" content filter block on a benign appointment-booking chat – Azure OpenAI
Hi all, We run customer-facing chatbots on Azure OpenAI, orchestrated with Semantic Kernel (Python). Some of them intermittently get a prompt-side content filter block in the violence category (severity "high"), even though the conversation is…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-09-10T18:44:12.9966667+00:00
Nishyanth Nandagopal
0
Reputation points
asked
2026-09-10T18:44:12.9966667+00:00
Nishyanth Nandagopal
0
Reputation points
2 answers
Microsoft Foundary - guardrails
We have set up a AI solution on Azure, our workloads work with partners such as HM Coroner in England and Wales. Some of the content we deal with includes death, volience and drug user. Currently we can't set the guardrails any lower so some of our…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-08-21T09:20:05.3233333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(217.60000000000002, 32%, 31%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ETH%3C/text%3E%3C/svg%3E)
Tony Healy
0
Reputation points
edited an answer
2026-09-03T09:47:57.28+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(304, 22%, 39%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ETG%3C/text%3E%3C/svg%3E)
Thanmayi Godithi
11,825
Reputation points Microsoft External Staff
Moderator
1 answer
One of the answers was accepted by the question author.
Intermittent 400 "Blocklist with name X not found" for a blocklist that exists
AnalyzeText intermittently returns HTTP 400 InvalidRequestBody — "Blocklist with name REDACTED not found, index = 0" — for a blocklist that exists and was not modified. The identical request succeeds seconds before and after the failure, from…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-08-31T11:34:08.0633333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(80, 94%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESF%3C/text%3E%3C/svg%3E)
Stefan Fleck
20
Reputation points
commented
2026-09-01T07:19:37.8466667+00:00
Stefan Fleck
20
Reputation points
1 answer
Azure Content Safety within Azure Foundry - Not always blocking the same prompt, why?
Hi, Were using a separate subscription for AI, where we have a Llama-4 model (Azure Foundry), with some Azure Content Safety (Guardrails) adjustments, to "Content harms", including a blocklist (with "Exact match"'s). According to our…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-07-23T11:41:18.9+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(144, 94%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EIT%3C/text%3E%3C/svg%3E)
Isidro TTW
5
Reputation points
commented
2026-07-24T07:20:32.3433333+00:00
Isidro TTW
5
Reputation points
2 answers
One of the answers was accepted by the question author.
Intermittent Prompt Injection False Positives with Azure OpenAI GPT-5.1 / GPT-5.4
Hi everyone, We're using Azure OpenAI GPT-5.1 and GPT-5.4 in a production application and have observed an intermittent issue with prompt injection/jailbreak detection. Occasionally, users submit completely normal inputs (such as dates, short replies, or…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-07-20T15:03:53.52+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(60.8, 7.000000000000001%, 15%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDB%3C/text%3E%3C/svg%3E)
Dharun Balaji
80
Reputation points
answered
2026-07-23T08:07:56.14+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(188.79999999999998, 37%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EPK%3C/text%3E%3C/svg%3E)
Pavan Kumar Purilla
410
Reputation points Microsoft External Staff
Moderator
0 answers
Azure Direct Models resource throttled due to CoTAbuse detection – Unable to create Azure Support Ticket
Hello Microsoft Team, We recently received an email stating that one of our Azure Direct Models resources has been throttled due to a potential violation of the Microsoft Online Services Acceptable Use Policy. The email references: Risk Category:…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-07-21T08:11:53.1133333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(137.6, 1%, 23%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESK%3C/text%3E%3C/svg%3E)
Santosh Korlepara
0
Reputation points
asked
2026-07-21T08:11:53.1133333+00:00
Santosh Korlepara
0
Reputation points
1 answer
Azure AI Doc Intelligence data extraction in salesforce
Hello Microsoft Team, We are using Azure AI Document Intelligence in a Salesforce-based digital onboarding flow for document classification and data extraction. Our current flow is: Document upload → Azure Document Intelligence custom classification…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-07-03T07:08:19.3566667+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(172.8, 85%, 26%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EIC%3C/text%3E%3C/svg%3E)
IT Cognity
0
Reputation points
answered
2026-07-03T08:34:57.21+00:00
Thanmayi Godithi
11,825
Reputation points Microsoft External Staff
Moderator
2 answers
How to set "annotate" for harmful categories within the new Foundry service.
Hi, Is it possible to set "Annotate" action for the risk types under the content harms when creating a new Guardrail in the new Foundry service. Right now, I can only see "Block" as the Action as seen the picture below. Thanks…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-06-24T15:24:21.32+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(73.60000000000001, 18%, 17%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ES1%3C/text%3E%3C/svg%3E)
SrinivasKasu-1211
0
Reputation points
commented
2026-07-01T15:08:01.01+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(28.799999999999997, 15%, 12%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAV%3C/text%3E%3C/svg%3E)
Anshika Varshney
15,625
Reputation points Microsoft External Staff
Moderator
1 answer
Azure OpenAI API: HTTP 400 content_filter error triggered by industrial safety product procurement query
Hello, I am building a product quotation system for industrial safety and monitoring equipment. During testing, I encountered an unexpected HTTP 400 content_filter error from the Azure OpenAI API when processing a routine product search query. I would…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-06-11T09:13:07.72+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(310.4, 93%, 40%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EDE%3C/text%3E%3C/svg%3E)
dw-eastwind
0
Reputation points
commented
2026-06-18T08:39:05.4333333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(6.4, 51%, 10%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKV%3C/text%3E%3C/svg%3E)
Karnam Venkata Rajeswari
5,255
Reputation points Microsoft External Staff
Moderator
1 answer
Azure OpenAI API: HTTP 400 content_filter error triggered by industrial safety product procurement query
Hello, I am building a product quotation system for industrial safety and monitoring equipment. During testing, I encountered an unexpected HTTP 400 content_filter error from the Azure OpenAI API when processing a routine product search query. I would…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-06-11T12:59:27.7633333+00:00
dw-eastwind
0
Reputation points
commented
2026-06-18T08:30:04.6566667+00:00
Karnam Venkata Rajeswari
5,255
Reputation points Microsoft External Staff
Moderator
2 answers
Microsoft Foundry: Where can I see all content-filter-blocked prompts and the reason for each (category or blocklist term)?
I have a Microsoft Foundry deployment with a content filter and a custom blocklist. I want a list of all prompts that were blocked, along with the reason each was blocked — specifically which harm category or which custom blocklist term triggered…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-06-03T08:37:08.59+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(124.80000000000001, 16%, 22%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EVT%3C/text%3E%3C/svg%3E)
Vu Thanh Trung
20
Reputation points
answered
2026-06-08T11:05:16.8166667+00:00
Anshika Varshney
15,625
Reputation points Microsoft External Staff
Moderator
3 answers
Azure OpenAI content_filter 400 errors blocking safe vaccine misinformation correction in healthcare FAQ workflow
We are experiencing reproducible Azure OpenAI content_filter 400 errors in a healthcare/public-health FAQ voicebot workflow. Context: The system is a patient-facing vaccination information assistant. It uses Azure OpenAI to answer FAQ-style vaccine…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-05-20T03:52:43.2333333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(259.20000000000005, 72%, 35%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ETR%3C/text%3E%3C/svg%3E)
Teah Rota
0
Reputation points
commented
2026-06-04T06:14:19.64+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(204.8, 15%, 29%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EMR%3C/text%3E%3C/svg%3E)
Manas R Mohanty
17,270
Reputation points
Moderator
1 answer
Azure AI Foundry: Where can I view all content-filter-blocked prompts and the reason each was blocked?
I'm using an Azure OpenAI / AI Foundry model deployment (region: Japan) with a content filter configuration attached, including a custom blocklist. I need to see a complete record of every prompt that was blocked by the content filter, along with the…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-06-03T08:31:38.57+00:00
Vu Thanh Trung
20
Reputation points
commented
2026-06-04T02:47:39.1+00:00
Vu Thanh Trung
20
Reputation points
1 answer
One of the answers was accepted by the question author.
Getting 404 error when trying Azure AI foundry AI Red Teaming
I am trying to work on AI red teaming in AI foundry, and retrieved a sample from documentation even for that even though complete setup is there like AZURE_SUBSCRIPTION_ID, AZURE_RESOURCE_GROUP, AZURE_PROJECT_NAME. here is my code: and error import…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2025-07-30T05:47:28.2666667+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(38.4, 67%, 13%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAR%3C/text%3E%3C/svg%3E)
Abhishek Ramdhan Handibag
25
Reputation points
commented
2026-06-01T22:06:40.5233333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(313.6, 61%, 40%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EAV%3C/text%3E%3C/svg%3E)
Alex Verboon
0
Reputation points MVP
2 answers
Agent randomly fails with: This interaction was blocked by a safety and security control in this asset's Foundry guardrail.
Hello, I have two Foundry agents with the same instructions, tools and guardrails (Microsoft.Default). One processes car data, and the other processes motorcycle data. The car agent works consistently, but the motorcycle agent randomly fails…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-05-06T17:35:00.19+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(67.2, 9%, 16%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ENM%3C/text%3E%3C/svg%3E)
Nuno Monteiro
0
Reputation points
commented
2026-05-18T07:18:05.6133333+00:00
Anshika Varshney
15,625
Reputation points Microsoft External Staff
Moderator
3 answers
One of the answers was accepted by the question author.
How to get rid of or edit default guardrail RAI policies in Microsoft Foundry?
When I provision Microsoft Foundry and a Foundry project, I see two RAI Policies that are created by default. If I look in the foundry portal at content filters (under Guardrails and Controls) these policies do not show up. But if I use the REST API to…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-04-29T21:08:45.87+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(108.80000000000001, 91%, 20%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EBL%3C/text%3E%3C/svg%3E)
Bob Lindenberg
80
Reputation points
accepted
2026-05-12T17:23:24.46+00:00
Bob Lindenberg
80
Reputation points
1 answer
Microsoft Foundry returns content-filter frequently for requests
For many simple requests Microsoft Foundry responds with a finish state of content-filter, but no context to what the trigger was. This is for innocuous user and agent requests such as: What is stopping you? Proceed General system or directory…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-04-13T17:36:23.09+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(230.39999999999998, 32%, 32%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EM%3C/text%3E%3C/svg%3E)
misoule
20
Reputation points
commented
2026-05-06T21:20:43.2566667+00:00
Manas R Mohanty
17,270
Reputation points
Moderator
2 answers
When will Qwen 3.5 235B be available on Azure AI Foundry?
Hi, I wanted to check on the planned availability of the Qwen 3.5 235B model on Azure AI Foundry. Could you please let us know: Is there an estimated timeline for Qwen 3.5 235B availability on Azure AI Foundry? Will it support serverless API…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-04-28T14:41:49.0633333+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(313.6, 95%, 40%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EHV%3C/text%3E%3C/svg%3E)
Hari Vinod
0
Reputation points
commented
2026-05-04T12:41:42.21+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(176, 16%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESC%3C/text%3E%3C/svg%3E)
SRILAKSHMI C
19,730
Reputation points Microsoft External Staff
Moderator
2 answers
Azure OpenAI API: content_filter triggered with null/empty category metadata
Hello, Our team is investigating an issue where the Azure OpenAI API is intermittently blocking requests via the moderation layer, despite the inputs passing manual validation. The Issue: Requests are being returned with the finish_reason:…
Content Safety in Foundry Control Plane
Content Safety in Foundry Control Plane
An Azure service that enables users to identify content that is potentially offensive, risky, or otherwise undesirable. Previously known as Azure Content Moderator.
117 questions
asked
2026-04-24T16:34:46.27+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(281.6, 75%, 37%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EYS%3C/text%3E%3C/svg%3E)
Yaroslav Saputskyi
0
Reputation points
commented
2026-05-02T18:39:36.2366667+00:00
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(208, 49%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ESJ%3C/text%3E%3C/svg%3E)
SAI JAGADEESH KUDIPUDI
3,645
Reputation points Microsoft External Staff
Moderator