Connect PagerDuty to OpenAI (ChatGPT)

**Deprecated** — use **Update Incident** instead. Acknowledge an incident. See the documentation

Add a text note to an incident. Notes are visible in the incident timeline and useful for documenting investigation steps, resolution details, or handoff notes. Use **List Incidents** or **Get Incident** to find the incident ID. See the documentation

Trigger a new incident on a PagerDuty service. Use **List Services** to find a service ID and **List Escalation Policies** to find a policy ID. Use **List Priorities** to find priority IDs. Set incidentKey to a stable value derived from the alert source (e.g. a hash of title + service ID) to prevent duplicate incidents on retry — PagerDuty deduplicates open incidents with the same key on the same service. See the documentation

Override a schedule layer to assign a specific user for a time window. Use **List Schedules** to find a schedule ID and **List Users** to find the user ID. Time params use ISO 8601 with explicit UTC offset, e.g. 2026-06-02T15:00:00-07:00. Always include the UTC offset — do not assume UTC; using the wrong offset will place the override in the wrong time slot. See the documentation

Create a new PagerDuty service. A service represents a system or application that generates incidents. Use **List Escalation Policies** to find a valid escalation policy ID (required). Set autoResolveTimeout to 0 to disable auto-resolve. Set acknowledgementTimeout to 0 to disable re-triggering after acknowledgment. See the documentation

Find the user on call for a specific schedule. See the documentation

Get the active event orchestration routing rules configured for a service. Event orchestration routes incoming events to the right responders based on conditions. Use **List Services** to discover service IDs. See the documentation

Get full details for a single incident by ID, including its current status, urgency, assignments, and html_url. Use **List Incidents** to find the incident ID. See the documentation

Get incident volume and MTTR (mean time to resolve) metrics for one or more services over a time range. Use **List Services** to discover service IDs. Time params use ISO 8601 with explicit UTC offset, e.g. 2026-06-02T15:00:00-07:00. See the documentation

List escalation policies in the PagerDuty account. Supports both exact name match (name) and substring search (query), plus team filtering. Use policy IDs with **Create Incident**, **Create Service**, and **Update Escalation Policy**. See the documentation

Retrieves available options for the Escalation Policy ID field.

List change events (deployments, config changes) correlated to an incident. Change events show what changed in your systems around the time the incident was triggered. Use **List Incidents** or **Get Incident** to find the incident ID. See the documentation

List available incident automation workflows. Use workflow IDs with **Start Incident Workflow** to run automation on an active incident. Requires Business+ plan — accounts without this plan will receive empty results or a 402 error. See the documentation

List and filter incidents by status, urgency, service, or team. Default statuses are triggered and acknowledged (open incidents). Use **List Services** to discover service IDs and **List Teams** for team IDs. Time params use ISO 8601 with explicit UTC offset, e.g. 2026-06-02T15:00:00-07:00. See the documentation

List log entries (the audit trail of actions taken on an incident or across the account). When incidentId is provided, scopes results to that incident's log entries. Otherwise returns account-wide log entries. Use **List Incidents** or **Get Incident** to find incident IDs. Time params use ISO 8601 with explicit UTC offset, e.g. 2026-06-02T15:00:00-07:00. Set isOverview: true to get only the most recent action per incident. See the documentation

Retrieves available options for the On-Call Schedule ID field.

List on-call entries — who is on call right now or during a given time window. Filterable by schedule IDs or escalation policy IDs. Use **List Schedules** to discover schedule IDs and **List Escalation Policies** to discover policy IDs. Time params use ISO 8601 with explicit UTC offset, e.g. 2026-06-02T15:00:00-07:00. Set earliest: true to get one on-call entry per unique (schedule, escalation policy, escalation level) combination. See the documentation

List the priority levels configured for this PagerDuty account. Returns priority IDs and names (e.g. P1, P2, critical) useful for **Create Incident** and **Update Incident**. See the documentation

List on-call schedules in the PagerDuty account, optionally filtered by name. Returns schedule IDs and names useful for **List On-Calls** and **Create Schedule Override**. See the documentation

Retrieves available options for the Service ID field.

List services, optionally filtered by team or searched by name. Returns service IDs, names, status, and html_url. Use **List Teams** to discover team IDs for filtering. See the documentation

List posts on a PagerDuty status page. Use **List Status Pages** to discover status page IDs. Set activeOnly: true to filter to currently active posts (client-side filter). Requires Business+ plan — accounts without this plan will receive empty results or a 402 error. See the documentation

List configured PagerDuty status pages. Use status page IDs with **List Status Page Posts** to retrieve posts on a specific page. Requires Business+ plan — accounts without this plan will receive empty results or a 402 error. See the documentation

List teams in the PagerDuty account, optionally filtered by name. Returns team IDs and names useful for filtering incidents, users, and services. See the documentation

The Chat API, using the gpt-3.5-turbo or gpt-4 model. See the documentation

Chat using the web search tool. See the documentation

Chat with your models and allow them to invoke functions. Optionally, you can build and invoke workflows as functions. See the documentation

Chat with your files knowledge base (vector stores). See the documentation

Summarizes text using the Chat API. See the documentation

Classify items into specific categories using the Chat API. See the documentation

Translate text from one language to another using the Chat API. See the documentation

Transcribes audio into the input language. See the documentation

Creates an image given a prompt returning a URL to the image. See the documentation

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms. See the documentation

OpenAI recommends using the **Chat** action for the latest gpt-3.5-turbo API, since it's faster and 10x cheaper. This action creates a completion for the provided prompt and parameters using the older /completions API. See the documentation

Send a message or question about an image and receive a response. See the documentation

Cancels a run that is in progress. See the documentation

Sends a message and generates a response, storing the message history for a continuous conversation. See the documentation

Send a chat via the Responses API, mixing built-in tools and MCP server tools. See the documentation.

Generates audio from the input text. See the documentation

Creates an assistant with a model and instructions. See the documentation

Creates and executes a batch from an uploaded file of requests. See the documentation

Creates a job that fine-tunes a specified model from a given dataset. See the documentation

Classifies if text is potentially harmful. See the documentation

Creates a thread with optional messages and metadata, and optionally runs the thread using the specified assistant. See the documentation

Create a vector store. See the documentation

Create a vector store file. See the documentation

Deletes a specified file from OpenAI. See the documentation