Shipping velocity has never been faster, but reliability can’t be the trade-off either. For engineering leaders, deploying AI for operations is no longer optional.  The question is whether you’ll lead the transformation or fall behind. 

The hard truth? Organizations can’t keep relying on humans as the first line of defense. Not when the pace of shipping has never been faster. It’s simply not scalable.

That’s why PagerDuty’s latest upcoming release is all about paving a path towards autonomous operations. Over the last few years, we’ve seen AI capabilities extend from simple chat bots to complex networks of digital teammates. With these advancements, autonomous operations is no longer a dream; we are taking the first step towards it.

Built on 16 years of operational intelligence and the experience of handling over 12 billion events and 952 million incidents annually, PagerDuty plans to develop capabilities purpose-built for the AI era to help you predict failures, automate resolution, and prevent issues from happening in the first place.

Here’s what autonomous operations looks like in practice:

For engineering leaders, it means strengthening platform reliability while boosting developer velocity without adding headcount.  For SRE teams, it means reducing toil, protecting human resources and capacity, and meeting SLOs consistently.  For developers, it means staying in flow, getting paged only when needed, and shipping confidently.

Here’s what you can expect to see from PagerDuty over the next several months:

1. SRE Agent as a Virtual Responder

To solve the challenge of the “3 AM wake-up call,” we are changing who responds first.

We are introducing SRE Agent as a virtual responder. It is an AI agent capable of acting as your first line of defense.

You will be able to add SRE Agent directly to PagerDuty’s schedules and escalation policies. It gathers signals across your tech stack to detect, triage, and diagnose incidents before paging a human. But what makes this truly powerful is control. You will be able to set agent permissions, guide its behavior, and decide if the agent should act on its recommended remediations or wait for approval.

SRE Agent utilizes “memory” that allows continuous improvement, recalling past incidents, diagnostics, and knowledge base information to improve future responses.

Coming Soon:

We are expanding the capabilities of our entire agent family to ensure you have coverage wherever you work:

• SRE Agent and Insight Agent for Microsoft Teams: Our SRE and Insight agents will support Microsoft Teams, bringing AI-powered context directly to your chat.
• Scribe Agent Enhancements: The Scribe Agent will get even smarter with conference bridge chat ingestion, periodic incident progress summaries, and enhanced transcripts.
• Web UI Availability: To ensure accessibility, AI agents will now be available directly within the PagerDuty Web UI.

2. Full Lifecycle Incident Management: Mobilizing in the Tools Users Love

To solve the challenge of “resolution taking too long,” we are attacking the friction of context switching. When an incident strikes, you shouldn’t have to toggle between monitoring dashboards, ticketing systems, and Slack.

We recently rolled out the first wave of our Modernized Slack experience with a redesigned incident card, threaded updates to reduce noise, and an improved slash command interface. These features are generally available now and allow you to manage incidents more efficiently, right in chat. Learn more by reading this blog.

But we’re not stopping here. We will be expanding the Slack experience to support the full incident lifecycle with dedicated incident channels that automatically organize the chaos of any major incident. Each incident will get its own channel, while announcement channels keep stakeholders informed without cluttering your response workflow.

And we will also be embedding SRE Agent directly in-channel. The platform intelligence learns from your operations as they happen, offering suggestions and automating tasks without you ever needing to tab-switch away from your team.

This is about meeting you where you are. By bringing the full power of the PagerDuty Operations Cloud platform into Slack, we are reducing the friction that slows down recovery and helping teams stay aligned when seconds count.

Coming Soon: 

We are committed to meeting you where you work, regardless of your tool of choice.

• Microsoft Teams Updates: We’ll bring the same level of polish to Microsoft Teams with dedicated incident channels, integrated post-incident reviews, new automated actions, and much more.
• Premium Workflow Actions: We’ll be introducing advanced workflow capabilities to handle complex logic and routing automatically.
• Web UI Post-Incident Reviews: You’ll be able to complete comprehensive Post-Incident Reviews (PIRs) directly in the Web UI, ensuring that learning from failure is seamless and standardized.

3. Shift-Left with API and MCP Integrations

Approximately 70% of incidents are caused by change. And, in a world where change happens faster than ever, this can mean more incidents than ever disrupting teams. The goal is preventing incidents from happening in the first place. 

This is easier said than done. In order to prevent incidents, developers need to build with as much context as possible. PagerDuty enables you to do this with one of our long-standing differentiators: our integrations.

Whether this is launching new API-first integrations with key developer tools like Backstage, or providing plug-and-play ways to connect AI tools with MCP, PagerDuty helps to ensure that developers have all the context they need to ship with confidence.

We’re doubling down on how we help our customers connect their AI ecosystems with MCP as a core capability of our platform. Agent-to-agent functionality, a key component to interconnected AI ecosystems, is now in early access and will reach GA by the end of H1 of FY27. Additionally, by the end of H1, all PagerDuty Incident Management actions will be available via MCP.

This means that the PagerDuty context you need, whether it’s incidents on dependent services, previous incident notes, alert details, and more can be available in your favorite AI-enabled tools, no context switching and no flow breaking.

Take a look at this demo to see an example.

Ready to reclaim your flow state?

PagerDuty’s latest and forthcoming capabilities can save teams time and prevent the context switching that kills focused productivity. If you’re ready to learn about how you can spend more time coding and less time firefighting, here are some resources:

• Launch Webinar – Learn more by registering
• Explore our new AI Integration Web Directory
• Product Tour – Explore all new features at your own pace with guided walkthroughs.
• Early Access Programs – Get first access to new features before general availability.
• Talk to Your Account Manager – If you’re a PagerDuty customer, connect with your CSM team for a personalized walkthrough.
• PagerDuty Commons (Community Forum) – Continue the conversation and connect with other users.

This blog contains forward-looking statements, including the expected availability of new functionality. These forward-looking statements are not guarantees of future performance and involve significant risks that may cause our actual results to be different from the results expressed or implied by these forward-looking statements. For a complete description of such risks, we refer you to the Company’s most recent Form 10-K and subsequent filings with the SEC, available for review at the SEC’s website at http://www.sec.gov.