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 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.

Moving a renewal to Commit in HubSpot

When a renewal sits inside its 90-day window, the CSM only moves it to Commit in HubSpot if Gong shows three or more distinct stakeholders and Gainsight is Green. The deal probability is set by the band rule and the commit note names every stakeholder so the leader can audit the forecast in seconds.

Tags

renewalhubspotforecastmulti-threadcommit

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 a renewal deal is inside its 90-day window and ready to be forecast, the customer success manager opens Gong, counts the distinct customer-side stakeholders who participated in calls in the last 30 days (excluding kickoff-only attendees), then opens the renewal deal in HubSpot. They move the deal stage to Commit only if Gong shows three or more distinct stakeholders and the Gainsight tier is Green, set the deal probability by the band rule (Green is 85, Yellow is 50, Red is 20) and add a structured commit note in the format ‘Multi-thread: [names] | Health: [band] | Champion: [name]’.

Reasoning

Renewal forecasts that come from gut feel age badly. The team has settled on multi-thread evidence as the gate to Commit because a single-threaded deal with one champion is exactly the deal that disappears when the champion changes jobs, and disappearing deals are the source of the worst forecast misses. Three or more distinct stakeholders in 30 days is the line where the team’s data shows the relationship outlasts any individual champion change. Kickoff-only attendees are deliberately excluded because they almost always stop showing up after the first quarter and counting them inflates the multi-thread number on accounts that are actually single-threaded. The probability bands are not negotiated. Each CSM’s Commits roll into the leader’s forecast, and a CSM’s 90% on a Yellow account distorts the forecast for everyone.

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 renewal deal in HubSpot is inside its 90-day forecast window and the CSM is in the weekly forecast review.

Outcome

The renewal deal is at the right stage for its evidence (Commit only when multi-thread and Green), the probability matches the band rule and the commit note carries the named stakeholders so the leader can audit the forecast in seconds.

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 the renewal deal in HubSpot from the Renewals pipeline view.

Use the Renewals pipeline, not the New Business pipeline. The two share probabilities and stages but the Renewals pipeline’s stages map to the leader’s forecast. New Business stages do not.

Expected: The renewal deal is open with the current stage, probability and amount visible.

HubSpot

Read off the existing custom property ‘qbr_health_band’ from the deal’s associated company.

qbr_health_band was set on the company by the QBR follow-up step. It is the source of truth for the deal’s probability band, not the CSM’s gut on the day. If qbr_health_band is empty, stop and run a QBR before forecasting. The leader rejects forecasts on accounts without a recent QBR band on principle.

Expected: The current health band (Green, Yellow, Red) is known and ready to drive the band-based probability.

Gong

Open Gong in a separate tab, search the customer and set the call filter to the last 30 days.

30 days is the multi-thread window the team uses for active renewals. 90 days produces too much false signal because customers run quarterly business meetings with breadth that is not representative of day-to-day relationships.

Expected: Gong is open on the customer’s call list filtered to the last 30 days.

Gong

Count distinct customer-side participants across all calls in the window, excluding anyone whose only call was the original kickoff.

Use the Participants panel on Account Intelligence, not a manual scan. The kickoff exclusion is the single most-forgotten step, and it inflates the multi-thread count by one or two on most accounts. Anyone with one call total whose call was the kickoff does not count, because they almost always stop attending after the first quarter.

Expected: You have a clear count of distinct stakeholders in the window with the kickoff-only exclusion applied.

HubSpot

Decide the stage by the rule: Commit only if stakeholders are 3 or more and qbr_health_band is Green. Otherwise Strong Best Case for Yellow, Best Case for Red, Pipeline for fewer than 3 stakeholders.

Rule examples: 3 stakeholders plus Green is Commit. 4 stakeholders plus Yellow is Strong Best Case (multi-thread does not unlock Commit on a Yellow account, the band rules). 1 stakeholder plus Green is Pipeline (single-threaded does not unlock Commit on any band, the multi-thread rule overrides). A champion change in the last 90 days is Pipeline regardless, until the new champion has three or more calls.

Expected: The deal stage matches the rule and reflects both the multi-thread evidence and the health band.

HubSpot

Set the deal probability by band: Green is 85, Yellow is 50, Red is 20.

The bands are the team’s contract with the leader’s forecast. CSM gut feel does not change the probability. If you believe the band is wrong, the right move is to run a QBR or trigger a Risk CTA, not to nudge the probability up.

Expected: Probability matches the band and the CSM’s Commit will sum cleanly into the leader’s forecast.

HubSpot

Add a deal note with the format ‘Multi-thread: [names] | Health: [band] | Champion: [name]’ and save.

The named stakeholders are the audit trail. The leader’s weekly forecast review sorts on this note. Examples: ‘Multi-thread: Sarah Mendez, Tom Wood, Alia Khan | Health: Green | Champion: Sarah Mendez’. Champion is the single named contact treated as the relationship spine, not the same as the multi-thread list. They are usually the first name on the list.

Expected: The deal carries a structured commit note that lets the leader audit the forecast in seconds and lets any colleague pick up the renewal without re-doing the analysis.

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 Logging the QBR outcome in HubSpot 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.

Moved Monarch Foods 2026 renewal to Commit (4 stakeholders, Green, 85%)

Held Cascadia Bank renewal at Strong Best Case (Yellow band, 50%)

Excluded kickoff-only attendees from Apex Marine multi-thread count

Added commit note: ‘Multi-thread: Sarah Mendez, Tom Wood, Alia Khan | Health: Green | Champion: Sarah Mendez’

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 19 times across 3 connections
Applications	HubSpot, Gong
First seen	12 Feb 2026, 14:33
Last seen	6 May 2026, 15:11

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