Openai Integration
OpenAI model access for ManySignal AI agent reasoning pipelines.
What this integration does
OpenAI meets agentic SOC
ManySignal's AI agents support pluggable LLM backends. When configured with the OpenAI integration, ManySignal's Investigate and Triage agents route reasoning tasks to GPT-4o, GPT-4.1, or o-series reasoning models for tasks requiring structured analysis, evidence summarisation, or complex threat narrative generation.
GPT-4o and o-series model access for agent reasoning
OpenAI Responses API integration for structured output
Model routing: fast tasks to GPT-4o mini, deep analysis to o3
Data collected
Actions supported
- Route agent reasoning task to configured OpenAI model
- Generate evidence narrative from structured alert data
- Produce analyst-ready investigation summary
Getting started
Set up in minutes
- 1
Obtain an OpenAI API key
- 2
Configure in ManySignal
- 3
Configure data residency
Openai Integration: frequently asked questions
Does ManySignal send raw log data to OpenAI?
No. ManySignal sends structured, summarised alert context — not raw logs. The prompt contains entity identifiers, event counts, and patterns. Raw log events remain in your environment.
Can I use my own OpenAI fine-tuned model?
Yes. Enter your fine-tuned model ID in the model configuration. ManySignal supports any model accessible via the OpenAI Chat Completions or Responses API.
Related integrations
Amazon Web Services Integration
Integration
Aws Cloudtrail Integration
Integration
Aws Guardduty Integration
Integration
Aws Security Hub Integration
Integration
Aws Config Integration
Integration
Aws Vpc Flow Logs Integration
Integration
Microsoft Azure Integration
Integration
Azure Activity Logs Integration
Integration
Microsoft Entra Id Integration
Integration
Microsoft Defender Integration
Integration
Microsoft Defender For Cloud Integration
Integration
Microsoft Defender For Identity Integration
Integration
See the agentic SOC in action
Watch AI agents work a real alert queue — verdicts, evidence, and confidence scores included. In-house SOC or MDR, your call.