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 Gainsight, 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 1 alternative. 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.

Triaging daily account health

First thing each morning, the CSM reviews the highest-tier accounts in the Gainsight Cockpit for meaningful health drops. They either own the next step themselves or @mention the responsible CSM on the Cockpit CTA before any other meeting or task starts.

Tags

health-scoremorning-routinegainsighttier-1triage

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

First thing in the morning, the customer success manager opens the Gainsight Cockpit, jumps to the saved ‘Account Health by Tier’ widget filtered to Tier 1 and Tier 2 accounts and sorts by the 7-day score delta. They click into any account that has dropped 15 points or more, hover the score component bars in the C360 to read which component caused the drop and either own the next step or @mention the assigned CSM on the Cockpit CTA.

Reasoning

A daily morning sweep on the highest-ARR accounts catches health drops before they harden into churn risks. Sorting by 7-day delta surfaces the change rather than the steady state, and the 15-point threshold is what the team has settled on as the line between noise and real signal after three months of false positives at lower bands. Hovering the score component bars matters because adoption drops nearly always trace to a primary user being offboarded, sentiment drops to an unresolved support escalation and engagement drops to a champion going quiet. Three different signals that need three different responses.

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

It is a weekday morning and the customer success manager is starting their working day before any meetings begin.

Outcome

Every account with a meaningful health drop in the manager’s portfolio has either been actioned or handed to the responsible CSM via a Cockpit @mention before any other meeting or task starts.

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.

Gainsight

Open the Gainsight Cockpit using the team-shared bookmark in the top row of the bookmark bar.

The bookmark goes straight to /cockpit?tab=today which loads the team’s shared ‘CSM Daily’ view. Avoid the default Gainsight home dashboard. It lags behind by one overnight refresh and you will miss anything that moved overnight.

Expected: The Cockpit Today view is open with the unread CTAs and the ‘Account Health by Tier’ report widget visible at the top of the screen.

Gainsight

Open the ‘Account Health by Tier’ report widget by clicking its title.

The widget is preset to Tier 1 (>$100k ARR) and Tier 2 ($50k to $100k ARR). Tier 3 is intentionally excluded from this view because Tier 3 risk is handled by the auto-CTA playbook, not by daily human triage.

Expected: A table of accounts loads with columns for current score, 7-day delta, 30-day delta and the trend sparkline.

Gainsight

Click the ‘7-day delta’ column header to sort descending so the biggest drops appear at the top.

Drops below 15 points in a 7-day window are usually noise from a single bad ticket or a one-off NPS response. Anything 15 points or more in 7 days is real signal worth investigating before doing anything else with the day.

Expected: Accounts with the steepest negative delta in the past week sit at the top of the list, ranked by magnitude of drop.

Gainsight

For each account dropping 15 points or more, click the account name to open the C360 and hover each of the four component bars in the Health Scorecard.

Hover Adoption, Sentiment, Engagement and Outcomes one by one. The tooltip names the underlying signal. Translation rules the team has learnt: an Adoption drop almost always means a primary user got removed from the workspace. A Sentiment drop means an unresolved support ticket or a low NPS. An Engagement drop means the named champion has gone quiet on calls and product activity.

Expected: You can see which component caused the drop and have a working hypothesis for the underlying cause without having to open another tool.

Gainsight

If the account is in your portfolio, queue the next step on the same Cockpit CTA. If it is not yours, @mention the assigned CSM directly on the CTA card.

Never act on someone else’s account without flagging it first. Picking up a ticket or a Gong listen on a colleague’s account can collide with relationship work in flight that is invisible from the outside. The handoff format on the @mention is ‘Account · -X pts · component · suspected reason’.

Expected: Every flagged account has a clear next owner and a written hypothesis attached to the CTA, so the day starts with the highest-risk work already routed.

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.

Alternative to

Mining Gong sentiment for at-risk signals

Often next

Building a pre-QBR brief Creating a Risk CTA after a health drop

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.

Reviewed Tier 1 health report; flagged Monarch Foods (-22 pts, sentiment) for follow-up

@mentioned @marcus.chen on Cascadia Bank Cockpit CTA (-18 pts, adoption)

Opened C360 for Juniper Retail; engagement drop traced to champion going quiet

Sorted health-by-tier report by 7-day delta and reviewed top 6 dropping accounts

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 87 times across 5 connections
Applications	Gainsight
First seen	19 Jan 2026, 08:42
Last seen	6 May 2026, 08:36

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