PagerDuty
Also known as: PagerDuty Advance, PagerDuty Operations Cloud, PD Reliability Platform
Incident management and operations platform whose AI agents (SRE, Scribe, Shift and Insights) triage, document, cover shifts and analyze incidents, with approval before remediation and service scoped agent memory.
PagerDuty is a publicly traded incident management and operations platform. Events from monitoring tools trigger incidents that page on call responders through schedules and escalation policies, incident workflows run the response, and the incident timeline records each status change, action and notification with timestamps.
Its AI agents sit on top, and all four are generally available. Paige, the SRE Agent, detects, triages and diagnoses incidents from alert payloads, related and past incidents, change events and 21 connected observability, code and documentation tools. It offers its next steps as nudges a responder runs, and it carries out a fix once the service owner approves it. In Early Access, Paige can join incident workflows as a virtual responder that starts the moment an incident triggers, and teams can write their own skills.
Scribe captures incident meetings, Shift resolves on call coverage conflicts automatically, and Insights analyzes history to recommend prevention. Paige keeps memory scoped to each PagerDuty service, holding an incident playbook, incident summaries and a service profile, and it reads the runbook stored for each service. Customers can view, update or redact that memory through the Paige Memory API. A hosted MCP server, with a separate EU address, lets outside AI tools create and update incidents. The fall launch on November 3, 2026 put Paige at the center of the product.
Pricing is public for most of the range. A free plan covers 5 users, and Professional costs $25 per user per month ($21 billed annually) with PagerDuty Advance as an add on. PD Reliability Platform tiers run from $2,800 a year to $48,000, with a custom Ultimate tier, and each includes an allowance of AI Actions. PagerDuty holds SOC 2 Type II, ISO 27001 and FedRAMP Low, and customers choose a US or EU service region.
Vendor details
Canonical URL
https://www.pagerduty.com
Category
SRE / DevOps agent
Subcategory
AI incident management and agentic operations
Funding status
Independent and publicly traded on the New York Stock Exchange under the ticker PD, headquartered in San Francisco, founded in 2009 by Alex Solomon, Andrew Miklas and Baskar Puvanathasan, former Amazon engineers, and led by chief executive Jennifer Tejada. PagerDuty went public in 2019. Its November 2026 launch post puts its customers at almost 40,000 companies, and it reported 15,506 paid customers for its second fiscal 2027 quarter in August 2026, including about two thirds of the Fortune 100. Named customers include Anthropic, Banco Pichincha, CoreWeave, Delivery Hero, Kawasaki Heavy Industries, Palo Alto Networks and Block. More than 250 customers adopted its MCP server within two months of its October 2025 launch.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Events arrive from monitoring integrations and trigger incidents, schedules and escalation policies. Paige reaches 21 connectors, including Grafana, Datadog, New Relic, AWS CloudWatch, Confluence and GitHub, and works in Slack, with Microsoft Teams in Early Access. Scribe joins Zoom and Microsoft Teams meetings, and a developer API, a hosted MCP server and a Claude plugin extend the platform.
In practice
An anomaly hits at peak traffic and responders lose minutes collecting data. PagerDuty's SRE Agent triages from the alert payload, related incidents and change events and suggests the next checks.
The same failures keep recurring because no one learns from past incidents. PagerDuty's Insights agent analyzes historical data to surface patterns and recommend prevention.
On call coverage gaps and scheduling conflicts create risk before an incident starts. The Shift agent detects conflicts between time off and shifts and finds replacements automatically.
Sources & related URLs
Research sources
Agentic Index coverage score
10.5 / 14 capabilities · 75%
| Integrations & Tool Calling | Full |
|---|---|
|
Paige, the SRE Agent, reaches 21 connectors, some through each tool's API and some over MCP, including Grafana, Datadog, New Relic, AWS CloudWatch, Confluence and GitHub. Admins set each tool to always allowed or blocked, and the write tools include a revert of a GitHub pull request, on a platform whose events arrive from monitoring integrations. Sourcedocs.pagerduty.com/ai-automation/advance/connectors-tools-and-skillsread 2026-11-03 |
|
| Workflow Orchestration | Full |
|
Incident workflows and escalation policies route and run the incident lifecycle. Paige can join an incident workflow as a virtual responder, in Early Access, beside the Scribe, Shift and Insights agents, each working its own part of the incident. Sourcedocs.pagerduty.com/ai-automation/advance/sre-agentread 2026-11-03 |
|
| Knowledge Grounding & RAG | Full |
|
A Customer Service Runbook stored for each service holds the customer's documentation for Paige. During triage Paige also reads past and related incidents, change events, the opening of the alert payload and connected Confluence and GitHub sources. Sourcedocs.pagerduty.com/ai-automation/advance/sre-agentread 2026-11-03 |
|
| Human Oversight & Guardrails | Full |
|
Paige offers its next steps as nudges a responder clicks to run, and the SRE Agent performs remediation once the service owner approves it. Admins set each connector tool to always allowed or blocked, with read only tools grouped apart from those that write or delete. PagerDuty's November 2026 launch post says a team can go on to let Paige run a fix without approval. Sourcepagerduty.com/platform/ai-agentsread 2026-11-03 |
|
| Security, Identity & Governance | Full |
|
Professional includes single sign on and team based advanced permissions, and audit trail reporting starts on the PD Reliability Platform's Starter tier. PagerDuty holds SOC 2 Type II, ISO 27001 and FedRAMP Low, with reports available through assurance.pagerduty.com. Sourcepagerduty.com/securityread 2026-11-03 |
|
| Observability & Auditability | Partial |
|
The incident timeline shows timestamps of each incident status along with all actions taken and notifications sent from the incident, filterable by event and action. Paige records its findings as incident notes. The agent's own tool calls are not shown. Sourcedocs.pagerduty.com/incident-management/incidents/overviewread 2026-11-03 |
|
| Memory & State Persistence | Partial |
|
Paige keeps a memory scoped to each PagerDuty service, holding an SRE incident playbook learned from history, incident summaries and a service profile. Customers can view, update and redact it through the Paige Memory API. PagerDuty states no retention period or lifetime for it. Sourcedocs.pagerduty.com/ai-automation/advance/sre-agentread 2026-11-03 |
|
| Deployment & Data Residency | Full |
|
Customers choose a United States or European Union service region at signup. US accounts run in AWS US West (Northern California and Oregon) and US East (Ohio), and EU accounts in AWS EU Central (Frankfurt) and EU West (Ireland). Application logs, product analytics, support, billing and Global User Profile data may be processed outside the chosen region. PagerDuty does not say where the AI agents' model processing runs, and there is no on premises or self hosted option. Sourcedocs.pagerduty.com/get-started/service-regionsread 2026-11-03 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Four named agents ship, all generally available, each for its own job. The SRE Agent, Paige, handles triage, diagnosis and approved remediation, Scribe captures incident meetings, Shift resolves on call coverage conflicts, and Insights analyzes history and recommends improvements. Customer written skills are in Early Access. Sourcepagerduty.com/platform/ai-agentsread 2026-11-03 |
|
| Triggers & Channel Coverage | Full |
|
Incidents trigger from monitoring events and page responders, and the Shift agent automatically detects conflicts between time off and on call shifts. Paige takes requests in Slack, the Operations Console and the incident page, with Microsoft Teams in Early Access, and as a virtual responder, also in Early Access, it starts the moment an incident triggers. Sourcedocs.pagerduty.com/ai-automation/advance/sre-agentread 2026-11-03 |
|
| Model Flexibility & Routing | Not documented |
|
PagerDuty names no model provider in its product documentation and points to an AI disclosure on its assurance portal. Customers cannot choose a model. Sourcedocs.pagerduty.com/ai-automation/advanceread 2026-11-03 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
PagerDuty publishes a developer API reference, including the Paige Memory API to view, update and redact agent memory. Its hosted MCP server at mcp.pagerduty.com, with a separate EU address, signs in with a user API token or OAuth and lists 18 tools, which can create and update incidents, add notes and responders and start workflows. Sourcedocs.pagerduty.com/ai-automation/advance/pagerduty-mcp-serverread 2026-11-03 |
|
| Testing, Debugging & Optimization | Partial |
|
Responders rate the answers of Paige, the SRE agent, with thumbs up or down through a Rate AI Response button, which PagerDuty says helps improve the product and future recommendations. That feedback loop comes without a stated mechanism or measure, and there is no evaluation harness, scored test cases or quality gate the customer runs against the agent. PagerDuty's engineering posts on how it evaluates its own agent describe vendor QA of its own product. Sourcedocs.pagerduty.com/ai-automation/advance/sre-agentread 2026-11-03 |
|
| Browser & Computer Use | Not documented |
|
Agents work through connectors, tools, incident workflows and chat. There is no browser, desktop or computer control. Sourcedocs.pagerduty.com/ai-automation/advance/connectors-tools-and-skillsread 2026-11-03 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Free for 5 users. Professional is $25 per user per month ($21 billed annually), and the PD Reliability Platform starts at $2,800 a year (Starter, 5 seats plus 5 bonus seats for a limited time).
Per user per month on Professional. The PD Reliability Platform tiers carry an annual platform fee with seats and Signal Intelligence Events and include AI actions, while PagerDuty Advance is an add on for Professional.
Included quota
Free covers 5 users, 1 schedule and 1 escalation policy. Starter includes 5 seats plus 5 bonus seats for a limited time (capped at 30), 5,000 Signal Intelligence Events and 1,000 AI Actions. Essential includes 25 seats, 25,000 events and 5,000 AI Actions, Plus 50 seats, 150,000 events and 16,000 AI Actions, and Ultimate 500 seats, 1,500,000 events and 160,000 AI Actions.
What is public
Free and Professional prices are public, along with the three published PD Reliability Platform fees and their seats, event allowances and AI Actions. The Ultimate price, the PagerDuty Advance add on price and the credit pack price are not public.
Billing mechanics
Professional is a per user monthly subscription with an annual discount. The PD Reliability Platform is an annual platform fee bundling seats, Signal Intelligence Events, audit trail reporting and AI Actions, and more of each is bought with credits, at 40 credits for each added seat. Ultimate is custom.
Cost watchouts
Professional users pay separately for the PagerDuty Advance add on. Expert Services is a required add on for Essential, Plus and Ultimate, and the platform tiers cap Signal Intelligence Events and AI Actions, so event volume or heavy agent use can push a team into credit packs or a higher tier.
Variable cost rationale
Seats are metered on Professional, at $25 per user per month or $21 billed annually, so the bill grows with headcount, and PagerDuty Advance is a separate add on. The platform tiers charge a fixed annual fee that bundles a set number of seats, Signal Intelligence Events and AI Actions, from 5,000 events and 1,000 AI Actions on Starter up to 1,500,000 events and 160,000 AI Actions on Ultimate. Each Paige request uses 4 AI Actions, and growth past an allowance is bought in credit packs whose price is not published.
Additional watchouts
Professional is priced per user with a separately priced AI add on, while the platform tiers charge a fixed fee that includes AI actions, so which costs less depends on headcount and on event volume against each tier's allowance.
Overage / add-ons
Growth past a platform tier's allowance is bought in credit packs for seats, events, AI Actions and call routing lines. The credit price is not published, and credits expire each year.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free plan for up to 5 users, and a free trial on every plan
Lowest paid plan
Professional at $25 per user per month, or $21 billed annually
Commercial notes
PagerDuty is publicly traded (NYSE: PD). Base pricing is self serve with a free plan, and the AI layer is bundled into the platform tiers or bought as an add on. Plans signed by January 15, 2027 on Essential, Plus or Ultimate get additional AI Actions free for the first year.
Key ambiguities
Incident management is sold as Free and Professional only, with no Business or Enterprise plan, and the PagerDuty Advance add on price for Professional is not published.
Cancellation / refund
Professional bills monthly or annually, and the PD Reliability Platform tiers bill an annual platform fee. Ultimate terms are contracted.
Support SLA / resale
Email and chat support on Professional and the platform tiers. Expert Services is a required add on for Essential, Plus and Ultimate.
Related vendors
- AlertD — AI agents for AWS operations that run read only in the customer's…
- Anyshift — AI SRE built on a versioned knowledge graph of infrastructure, apps…
- Avesha — Obliq, Avesha's autonomous AI SRE for Kubernetes and agentic…
- Better Stack — Better Stack offers incident management with built in on call,…
- Bluebricks — Context and control layer that lets AI agents operate cloud…
- Cased — AI workflows for infrastructure and platform engineers: default and…
Alternatives to PagerDuty
The closest documented capability profiles to PagerDuty among SRE and DevOps agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Bluebricks10.5 / 14Fuller documented coverage on Observability & Auditability
- Metoro9.0 / 14A lighter documented profile than PagerDuty
- Resolve AI11.0 / 14Fuller documented coverage on Observability & Auditability and Testing, Debugging & Optimization
- Anyshift8.5 / 14A lighter documented profile than PagerDuty
- Better Stack9.5 / 14Fuller documented coverage on Observability & Auditability
- Causely9.5 / 14Fuller documented coverage on Observability & Auditability
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded