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 HubSpot, 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.

Logging the QBR outcome in HubSpot

After every QBR, the CSM saves a structured note on the customer's HubSpot company record and updates four custom properties. Downstream forecasts and dashboards then reflect the new state of the account immediately.

Tags

qbrhubspotcompany-recordstructured-noteproperties

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

Once the Gainsight Sentiment override is saved, the customer success manager opens the customer’s HubSpot company record, adds a note with the strict header format ‘QBR | Q[N] [Year] | [Outcome]’, pastes the Action Items tracker output from Gong into the body and updates four custom company properties: next_qbr_date (90 days out), qbr_outcome (enum), qbr_health_band (Green/Yellow/Red) and champion_changed (boolean).

Reasoning

The HubSpot company record is the audit trail the wider business reads, including the AE on the renewal, finance on the forecast and product on roadmap escalations. None of those readers will open Gainsight or Gong, so the company record has to carry the full QBR signal in a way other systems can parse. The note header format is not stylistic. The renewal forecast report and the executive QBR-coverage report both regex on the exact ‘QBR |’ prefix, so anything off-format is invisible to the rest of the business. The four custom properties exist because each of them powers a different downstream report (next_qbr_date powers QBR coverage, qbr_outcome powers retention forecasts, qbr_health_band powers exec dashboards, champion_changed flags accounts for the leader’s relationship review).

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

The Gainsight Sentiment override has been saved and the QBR cycle now needs the cross-functional record on the company.

Outcome

The HubSpot company record carries a structured QBR note that other teams can find via search or report, and four custom properties are set so downstream forecasts and dashboards reflect the new state of the account immediately.

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.

HubSpot

Open HubSpot, search for the customer by company name and open their company record.

Always go to the company record, not the deal record, for QBR logging. The company record is the parent surface and the deal will inherit the activity. Logging on the deal makes the QBR invisible from the AE’s account view.

Expected: The customer’s HubSpot company record is open with the activity timeline visible.

HubSpot

Click ‘Note’ in the activity composer and type the header ‘QBR | Q[N] [Year] | [Outcome]’ on the first line.

The header format is the contract. Examples: ‘QBR | Q1 2026 | On track’, ‘QBR | Q4 2025 | At risk’, ‘QBR | Q1 2026 | Expansion’. The two reports that depend on the regex are the renewal forecast and the executive QBR-coverage report. A note with no header or a different header drops out of both, even though the QBR happened.

Expected: The note opens with the strict header on the first line and a blank body below, ready for the action items.

HubSpot

Paste the Action Items tracker output from Gong into the body of the note as a bulleted list, attribute each item to a customer-side owner and add a target date.

Format every line as ‘· [Owner] · [Action] · [Date]’. The Action Items tracker on Gong outputs a candidate list. Edit it for accuracy before pasting. CSMs trust their own ears more than the auto-extract, so always cross-check at least the owner attribution.

Expected: The note body contains a clean bulleted list of action items, each owned and dated.

HubSpot

Set the company property ‘next_qbr_date’ to 90 days from today.

90 days, not ‘next quarter’ or ‘three months’. The QBR coverage report uses a rolling 90-day window. Setting ‘next quarter’ to 1 April when today is 6 January will under-count coverage in the report.

Expected: next_qbr_date is set to today plus 90 days and the company will appear in the QBR coverage report on the right date.

HubSpot

Set qbr_outcome (enum), qbr_health_band (Green/Yellow/Red) and champion_changed (boolean) to match the QBR.

qbr_outcome enum values are: On track, At risk, Expansion, Renewal-only, Lost. qbr_health_band must match the Gainsight tier post-override. champion_changed is true if Sponsor Tracking flagged a sponsor change in the last 90 days. Each property powers a different downstream report. Setting champion_changed to true triggers the leader’s daily relationship-review email at 8am the next morning.

Expected: All four QBR-related properties on the company record are set and the downstream reports will update on their next refresh.

HubSpot

Click ‘Save note’ to commit the activity to the timeline.

Do not associate the note to the deal as well as the company. Double-association duplicates the activity in the deal feed and the AE has already complained about that twice this quarter.

Expected: The structured QBR note is saved on the company timeline only and is discoverable by any colleague viewing the account.

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

Updating Gainsight from a QBR recording

Often next

Creating a Risk CTA after a health drop 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.

Logged ‘QBR | Q1 2026 | On track’ note on Monarch Foods company record

Set next_qbr_date to 2026-08-04 on Cascadia Bank company record

Flipped champion_changed to true on Juniper Retail (Priya Patel new sponsor)

Pasted 5 Action Items from Gong tracker output into Helios Energy QBR note

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 24 times across 5 connections
Applications	HubSpot
First seen	26 Jan 2026, 13:48
Last seen	5 May 2026, 11:38

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