When does an AI agent use this pattern?

When the trigger described above matches the situation the agent is handling. The agent queries FusedFrames at runtime, this pattern is returned and the agent follows the recorded reasoning and steps to reach the recorded outcome.

How were the steps captured?

By the desktop app on the machine of someone who actually does this work. It records clicks, keystrokes, copy and paste, drag and drop, selected text and screen regions across PagerDuty and Datadog, then groups them into the meaningful steps shown above.

Where does the reasoning come from?

From the operator. When the desktop app sees a decision the action alone cannot explain, it asks why in the moment. The operator's answer is recorded and becomes the reasoning attached to the pattern, so the AI agent gets the thinking and not just the steps.

What if my team handles this differently?

Capture how your team actually does it. The desktop app records what your operator does on your tools and the web app distills that into a pattern shaped by your team. Each team's library reflects their own approach rather than the example shown here.

What if a case looks like this pattern but does not quite fit?

The pattern is linked to 2 alternatives. The agent can follow the connections shown on this page to a related pattern that matches the case more closely.

How does my AI agent actually call this pattern?

Through the read-only REST API or the npm CLI. Create an API key in the dashboard, choose whether it accesses all libraries or specific ones and have your agent query at runtime. The response is structured JSON ready for tool use.

Is the data shown on this page from a live customer?

No. Example libraries on this site are illustrative. Patterns in your own account are built from your team's captured actions and stay private to your workspace.

How do I build a pattern like this for my team?

Install the desktop app on the machine of the person who already does this work, ask them to handle a real case end to end, then distill the captured action into a pattern in the web app. The pattern you end up with mirrors how your team actually operates.

Acknowledging a PagerDuty page

The on-call engineer's first action on any page is to acknowledge in PagerDuty so the escalation timer stops. They post a status update naming the service under investigation and pivot to the linked Datadog monitor in a new tab.

Tags

on-callpagerdutyacknowledgefirst-responseincident-timeline

Lets your agent filter to the right pattern

Categories and tags scope the retrieval set, so your agent receives only the patterns relevant to the task instead of scanning the full library.

What and why

The observed behaviour and the reasoning behind it.

Behaviour

When the on-call engineer receives a page in PagerDuty, they open the incident detail page in a browser, click Acknowledge to stop the escalation timer, then add a status update on the incident timeline naming the service they are about to investigate. They keep the PagerDuty tab open in the background and pivot to the linked monitor in a new tab rather than closing PagerDuty.

Reasoning

Acknowledging halts the 15 minute auto-escalation to the secondary, but a bare acknowledgement gives the rest of the team no signal that the page is being worked. Posting a short status update on the PagerDuty timeline doubles as an audit trail for the post-mortem, so the team avoids reconstructing the timeline from memory later. Keeping the PagerDuty tab open also means the ack can be revoked quickly if the responder gets pulled into a parallel page mid-triage.

Gives your agent an operator's reasoning

Behaviour records the action; reasoning records the rationale. Your agent applies both to handle cases that diverge from the captured examples.

Cause and effect

What initiates this pattern and what it produces.

Trigger

A PagerDuty incident has been triggered by a Datadog monitor and the on-call engineer is the first responder named on the active rotation.

Outcome

The PagerDuty incident moves to the Acknowledged status with a named responder and a short status update describing the service under investigation, and the linked Datadog monitor is open in a new browser tab.

Tells your agent when to act and what to verify

Your agent stays within the scope set by the trigger and outcome, so it doesn't extend beyond the work or finish before the outcome is met.

Standard operating procedure

Step-by-step instructions to reproduce this pattern.

PagerDuty

Open the incident detail page from the PagerDuty notification email or push.

Use the link in the email or push notification rather than navigating from the incidents list. The link carries the incident ID, the originating monitor and the time the page fired, all of which the manual route loses.

Expected: The incident detail page loads showing the alert payload, the originating monitor and the current escalation timer.

PagerDuty

Click Acknowledge in the top right of the incident detail page.

If the page came in on the phone first, re-acknowledge from the desktop within 5 minutes. The mobile ack records you as responder but the timeline note in the next step requires a desktop session.

Expected: The incident status changes to Acknowledged, your name appears as the responder and the auto-escalation countdown stops.

PagerDuty

Click 'Add Status Update' on the incident timeline and write one short line naming the affected service and your immediate next step.

Example: 'Investigating elevated 5xx on api-gateway, opening Datadog now.' Keep it under 120 characters so it fits the timeline preview without truncation.

Expected: The status update appears as a timeline entry with your name and a timestamp, visible to anyone who opens the incident.

PagerDuty

Click the 'View in Datadog' link in the alert details and let it open in a new tab.

Use ⌘ click or middle click so the PagerDuty tab stays open. The Datadog link carries the exact monitor, the alert time and a 1 hour scope. Navigating to Datadog from the bookmarks bar loses all three and you end up looking at the wrong dashboard.

Expected: The Datadog monitor detail page opens in a new tab, scoped to the time the page fired.

Hands your agent your team's exact steps

Your agent executes the documented procedure in order, against the applications named at each step, producing consistent output across human and agent runs.

Book a demo

Related patterns

How this pattern connects to other patterns in the library.

Often next

Triaging a page from the linked Datadog monitor Escalating a page to the secondary on-call

Alternative to

Escalating a page to the secondary on-call Silencing a noisy Datadog monitor during investigation

Lets your agent confirm the match and its scope

Alternative patterns let your agent compare candidates and select the closest match. Previous and next patterns define position in the workflow, so the agent operates within the scope of this one.

Supporting actions

Actions that provide evidence for this pattern.

Acked PD-PT4ZXKR for api-gateway 5xx spike

Status update on PD-PT4ZXKR: investigating, Datadog open

Acked Q9HK22N from mobile, re-acked at desktop a minute later

Acked PD-PT5MN8L on the checkout-service latency monitor

Acked payments-service page, posted 'looking now' on timeline

Shows your agent the evidence behind the pattern

Each pattern is derived from captured action sequences. Your agent can reference the source actions to verify any field, so nothing it acts on is authored by hand or hallucinated.

Metadata

Timestamps and identifiers.

Evidence	Observed 67 times across 5 connections
Applications	PagerDuty, Datadog
First seen	22 Jan 2026, 08:14
Last seen	6 May 2026, 22:41

Helps your agent rank patterns by confidence

Action count and last-seen timestamp weight each pattern by frequency and recency, so your agent selects the highest-scoring match rather than the first returned.

Questions

Frequently asked questions

Book a demo View all examples

Speak to the founder

Get a demo. Watch a live capture, then an AI agent query the result.

Ask anything. Pricing, security or integrating with your stack.

No purchase obligation

Book a call

Start capturing

Record in minutes. Install once and work as normal.

Plug AI agents in. One API call from any AI agent stack.

Refund on unused credits if you cancel