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 and 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 happens when a case looks like this pattern but does not quite fit?

The connections shown on this page link to related patterns that may match the case better. The agent can follow those edges to find a closer fit.

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.

Updating Gainsight from a QBR recording

Within 24 hours of a QBR ending, the CSM listens back to the Gong recording and updates the Sentiment override on the Gainsight Health Scorecard. The Gong moment URL and the QBR ID are stamped into the override comment so any colleague can verify the call.

Tags

qbrgainsightscorecardsentiment-overridegong

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

Within 24 hours of a QBR ending, the customer success manager opens the Gong recording, listens to the moments flagged by the Action Items, Concerns and Champion-at-risk trackers and writes their judgement into the Sentiment override field on the Gainsight Health Scorecard. They paste the timestamped Gong moment URL into the override comment, set the override reason to the QBR ID and leave Adoption, Engagement and Outcomes untouched.

Reasoning

Three of the four health components on Gainsight (Adoption, Engagement, Outcomes) are computed automatically from product and CRM signals, and the team has decided not to override them by hand because every override degrades the trend line’s honesty. Sentiment is the only component the team trusts a human to override, because a 60-minute QBR call carries more sentiment information than any score function can model. The override always carries a Gong moment URL with a timestamp because three months ago the team learnt that the next CSM to look at the override has no idea why it was made unless they can listen to the same 30 seconds of audio.

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 QBR has ended in the last 24 hours and the recording is processed and visible in Gong.

Outcome

The Sentiment component on the customer’s Gainsight Health Scorecard reflects the qualitative reality of the QBR, with a Gong moment URL and the QBR ID stamped into the override comment so any colleague can verify the call.

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 QBR call from the Account Intelligence page once the recording status shows ‘Processed’.

Wait for processing to finish. The trackers do not fire on a call until the transcript is ready, and you cannot jump to the moments without the trackers. Processing usually takes 20 to 40 minutes after the call ends.

Expected: The QBR call is open with the trackers visible in the timeline and the transcript fully processed.

Gong

Click each Action Items, Concerns and Champion-at-risk tracker chip in turn and listen to the moment at 1.4× speed.

Action Items confirm what the customer agreed to do, which is the spine of the follow-up note. Concerns and Champion-at-risk drive the Sentiment override. Listen to the speaker, not the words. The way a customer says ‘we’re committed’ carries more sentiment than the sentence itself.

Expected: You have a clear sentiment read on the call (positive, neutral, negative) and a single Gong moment URL that best evidences it.

Gong

Click ‘Share’ on the most evidencing moment and copy the link with the timestamp included.

The Share dialog has a ‘Start at current time’ checkbox. Tick it. The link is useless if the next person who clicks it has to scrub through 60 minutes to find the moment.

Expected: A Gong URL ending with the moment timestamp is on the clipboard, ready to paste.

Gainsight

Open the customer’s C360, click the Sentiment component bar on the Health Scorecard and choose ‘Override’.

Only override Sentiment. Do not override Adoption, Engagement or Outcomes by hand. The auto-scores on those three are accurate enough that human edits introduce more noise than signal, and any override on those components will be reverted by the CS Lead during the weekly score review.

Expected: The Sentiment override panel is open with fields for new score, reason and comment.

Gainsight

Set the new Sentiment score, choose the override reason as ‘QBR · Q[N] [Year]’ from the dropdown and paste the Gong moment URL into the comment field with a one-line summary.

Format the comment as ‘[one-line summary] · [Gong URL]’. The next colleague who lands on this customer in three months should be able to listen to the same 30 seconds and form their own view, not just trust yours.

Expected: The Sentiment override is saved with the QBR ID, the new score, the one-line rationale and the Gong moment URL all stamped on the same record.

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 previous

Mining Gong for QBR talking points

Often next

Logging the QBR outcome in HubSpot Logging an expansion opportunity in HubSpot Moving a renewal to Commit in HubSpot

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.

Listened to Champion-at-risk moment on Helios Energy QBR; updated Sentiment to 6 (was 8)

Pasted Gong moment URL into Sentiment override comment for Cascadia Bank Q1

Set override reason to ‘QBR · Q1 2026’ on Monarch Foods Sentiment update

Confirmed Action Items tracker fired 5 times on Apex Marine QBR recording

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 21 times across 5 connections
Applications	Gainsight, Gong
First seen	26 Jan 2026, 11:23
Last seen	5 May 2026, 10:11

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