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 Zendesk, 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.

Holding a Zendesk ticket pending the Linear fix

After the customer expectation has been set, the support rep puts the Zendesk ticket on hold with a follow-up date keyed to the Linear status (one week for In Progress, one month for Backlog). The 'linear-{id}' tag stays attached so the post-fix sweep can find the ticket later.

Tags

zendeskon-holdfollow-upsnoozequeue-hygiene

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

After the customer expectation has been set, the support rep puts the Zendesk ticket on hold with a follow-up date keyed to the Linear status. In Progress issues get a one-week follow-up, Backlog issues get a one-month follow-up. The ticket is snoozed using Zendesk's follow-up feature so it returns to the inbox automatically on that date. A second internal note records the chosen follow-up date and the reasoning, and the support rep confirms the 'linear-{id}' tag is still attached so the post-fix sweep can find the ticket.

Reasoning

On-hold is the only ticket status that pauses the SLA without sending the customer a closing message. Picking the follow-up date by Linear status (rather than a fixed window) is what keeps the active queue clean: an In Progress issue will likely move within a week, while a Backlog issue will not, and snoozing both the same way clogs the queue with premature reminders. The internal note explaining the chosen date prevents the next support rep from second-guessing the call when the ticket pops back. The tag confirmation guards against accidental tag removal during macro responses, which silently breaks the sweep step later.

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 Zendesk ticket has been linked to a Linear issue and the customer has been told what to expect.

Outcome

The ticket is on hold with a follow-up date that matches the Linear status, an internal note recording the reasoning and the 'linear-{id}' tag still in place. The active queue is no longer cluttered by tickets engineering is already aware of.

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.

Zendesk

Confirm the ticket status is On-hold and the 'linear-{id}' tag is still attached.

Macros and follow-up replies sometimes silently strip tags that were not added through the macro itself. A missing 'linear-{id}' tag will not surface until the sweep step fails to find the ticket weeks later.

Expected: The ticket is on hold and the canonical tag is in place.

Zendesk

Open the linked Linear issue and read its current status (Triage, Backlog, Todo, In Progress, In Review, Done).

If the status is already Done or In Review, skip the hold and go directly to the sweep step instead. Holding a ticket whose Linear issue is already shipped wastes the customer's time.

Expected: You know the current Linear status and whether holding is the right next move.

Zendesk

Pick a follow-up date by Linear status: In Progress gets +7 days, Backlog gets +30 days, Triage gets +14 days.

The team has tuned these windows over six months. Any tighter and the inbox fills with premature reminders. Any looser and customers feel forgotten.

Expected: You have a follow-up date that matches the Linear status.

Zendesk

Use the Zendesk follow-up feature to snooze the ticket until the chosen date.

Use the snooze, not a manual calendar reminder. The snooze places the ticket back into the inbox on the date, which is what makes sure any support rep (not just the original handler) can pick it up.

Expected: The ticket is snoozed and will return to the inbox automatically.

Zendesk

Add a second internal note: 'Held until {date}, Linear status was {status} on {today}. Recheck Linear before replying.'

The 'recheck Linear before replying' line saves the next support rep from sending a stale update if the Linear issue moved in the meantime.

Expected: The ticket carries an internal note with the follow-up date and a reminder to recheck Linear.

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

Linking a Zendesk ticket to its Linear issue and setting the customer expectation

Often next

Sweeping linked Zendesk tickets when a Linear issue ships

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.

Held Northwind #82441 +7 days, ENG-PLAT-4192 In Progress

Snoozed Eastview #82398 +30 days, ENG-API-4231 Backlog

Atlas Energy #82355 held +14 days, Triage

Heron #82321 held +7 days, ENG-BILL-4235 In Progress

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 33 times across 4 connections
Applications	Zendesk
First seen	25 Feb 2026, 09:48
Last seen	5 May 2026, 11:02

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