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 Gong, 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.

Mining Gong sentiment for at-risk signals

Twice a week, the CSM scans Gong for concerning moments on accounts the health score still rates Green or Yellow. Saved clips land in a shared 'Hidden risks' folder so the daily 5pm digest can surface them to the wider team.

Tags

gongtrackersat-riskearly-signalcompetitor

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

On Tuesday and Friday mornings, the customer success manager opens Gong, switches to the team-shared ‘Concerns + Competitor + Champion-at-risk (last 7 days)’ saved view, filters to accounts the Gainsight integration marks as Green or Yellow health and clicks into any call where two or more of the three trackers fired. They listen to the flagged moments at 1.4× speed, save the meaningful clips into the ‘Hidden risks’ shared library folder and tag the account name in the description so the daily 5pm digest picks it up.

Reasoning

Gainsight’s health score is a lagging indicator. By the time it goes red, the customer has usually already started shopping. Gong tracker hits are leading indicators because customers say what they think on a call before they reflect it in usage or in NPS. Restricting the filter to Green and Yellow accounts is intentional because Red accounts are already on a Risk CTA, so this scan is purely about catching the silent ones. The two-or-more-in-a-week threshold has been tuned over six months of false positives and consistently catches accounts that are silently shopping competitors before any health-score component reflects it.

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 Tuesday or Friday morning following the team’s twice-weekly Gong scan cadence, or a CSM has heard a hallway concern about a ‘looks-fine’ account they want to validate against the call evidence.

Outcome

Every Green or Yellow account with two or more concerning tracker hits in the last week has a saved clip set in the ‘Hidden risks’ folder, ready for the 5pm digest to surface to the wider team.

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.

Gong

Open the saved view ‘Concerns + Competitor + Champion-at-risk (last 7 days)’ from My Library, Shared with Team.

The view combines three trackers tuned over the last six months. ‘Concerns’ (objection language), ‘Competitor’ (named competitor mentions, currently five) and ‘Champion-at-risk’ (phrases like ‘we’re restructuring’, ‘I’m leaving’, ‘new team’). The CSM lead owns the tracker definitions and only the lead edits them.

Expected: The view loads showing every call in the last 7 days where any of the three trackers fired at least once.

Gong

Apply the ‘Account Health’ filter for Green and Yellow only.

Gainsight tier syncs into Gong’s Account Health filter via the integration. Excluding Red is deliberate because Red accounts already have a Risk CTA running. The whole point of this scan is the silent ones the score has not caught yet.

Expected: The list narrows to calls on Green and Yellow accounts only.

Gong

Sort by ‘Tracker Hits’ descending and click into any call with two or more hits across the three trackers.

Single hits are noise. A customer saying a competitor name once does not mean they are switching. Two or more hits in the same call, or one across two calls in the same week, is the line worth listening to.

Expected: The call opens at the call summary view with the tracker chips visible in the timeline.

Gong

Click each tracker chip in the timeline to jump to the flagged moment and listen at 1.4× speed.

The first 30 seconds of the moment usually contain the actual concern. If it is contextual (‘we evaluated Salesforce three years ago’), discard it. If it is present-tense (‘we’re looking at Salesforce again’), it is real signal worth saving.

Expected: Each flagged moment has been listened to and you have a clear judgement on whether the signal is real or contextual.

Gong

For each real signal, click ‘Save to Library’ and choose the ‘Hidden risks’ folder.

The folder is shared with the CS Lead and the Renewal Manager. Saving here triggers the daily 5pm digest of new hidden-risk clips so colleagues do not have to refresh the folder manually.

Expected: The clip is saved and visible in the shared library folder, ready to feed the 5pm digest.

Gong

In the clip description, type the account name in square brackets followed by a one-line plain-English summary.

Format: ‘[Account name] · one-line plain-English summary’. Resist the urge to write a paragraph. The point of the clip is the audio. Colleagues trust 30 seconds of listening more than three sentences of summary, every time.

Expected: The CSM owner has a one-click way to listen to the clip and a tight account label so the digest reads cleanly.

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

Triaging daily account health

Often next

Creating a Risk CTA after a health drop Escalating to the exec sponsor

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.

Saved 4 hidden-risk clips for Apex Marine and Helios Energy from Tuesday Gong scan

Listened to Champion-at-risk moments on Rivermark Health Q2 sync at 1.4×

Tagged [Northwind Logistics] in clip description after Salesforce mention (present-tense)

Handed Apex Marine signal to @tom.reilly via the 5pm Hidden risks digest

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 36 times across 3 connections
Applications	Gong
First seen	3 Feb 2026, 10:15
Last seen	5 May 2026, 11:23

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