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 Intercom and 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 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.

Converting an Intercom conversation into a Zendesk ticket

Once an Intercom conversation has crossed three messages, includes an error screenshot or carries the bug intent tag, the support rep uses Intercom's integration to spin up a matching Zendesk ticket. The customer is set as requester, the Intercom URL is pinned in an internal note and a single closing line in chat points the customer at the new thread.

Tags

intercomzendeskconversionchannel-switch

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 an Intercom conversation has crossed three back-and-forth messages, includes an error screenshot or carries the bug intent tag, the support rep uses Intercom's 'Create Zendesk ticket' integration to spin up a ticket from the conversation. They paste the customer's account email as the requester (looking it up if Intercom only shows an internal user ID), copy the Intercom conversation URL into the Zendesk internal note, set the ticket form to match the intent tag and reply once in Intercom with a single line telling the customer the conversation is moving to email so they have the new thread to follow.

Reasoning

Long Intercom conversations are difficult to read for the next support rep and impossible to attach to a Linear issue cleanly. Moving them to Zendesk early gives the case a stable URL, a proper requester record and the ability to be put on hold while engineering investigates. Using the integration rather than copy-pasting matters: it preserves the message history, keeps the Intercom conversation linked from inside the Zendesk ticket and stops the customer from having to repeat anything. The single line back in Intercom prevents the customer wondering why the chat went silent.

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

An Intercom conversation has more than three messages, contains a screenshot of an error or has been tagged as a bug.

Outcome

A Zendesk ticket exists for the case with the customer set as requester, the Intercom conversation URL pinned in an internal note and the ticket form matched to the original intent. The Intercom conversation has a single closing message pointing the customer at the new thread.

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.

Intercom

Open the conversation and copy the Intercom conversation URL from the address bar.

The conversation URL contains the Intercom conversation ID, which is the only stable link back from Zendesk. Copy the full URL rather than the short ID, since the ID alone is not navigable from inside Zendesk.

Expected: The Intercom conversation URL is on the clipboard.

Intercom

Find the customer's account email in the conversation sidebar. If Intercom only shows an internal user ID, click through to the customer profile to reveal the email.

Some customers come in via the in-product widget which only carries the internal user ID. The Zendesk ticket needs the email or the requester record will be wrong and downstream automations will fail.

Expected: You have confirmed the customer's account email and it is visible in the profile sidebar.

Intercom

Click 'Create Zendesk ticket' from the conversation actions menu. Choose the ticket form that matches the intent tag (Bug Report, Billing, Account).

Use the integration rather than copy-pasting the transcript. The integration preserves the message order and avatar metadata that copy-paste loses, and it puts the Intercom URL in the new ticket automatically.

Expected: A new Zendesk ticket is opened in a side panel with the conversation history attached and the form pre-set to the chosen type.

Zendesk

Confirm the requester field shows the customer's account email and the subject line summarises the ask in under ten words.

If the requester defaulted to the Intercom internal user ID, paste the account email into the requester field manually. Edit the subject if the integration auto-generated something vague like 'New conversation from <name>'.

Expected: The Zendesk ticket has the right requester and a clear, scannable subject line.

Zendesk

Add an internal note containing the Intercom conversation URL so any support rep can jump back to the original chat.

Type 'Intercom: <URL>' as the first line of an internal note. The Intercom integration usually populates this, but on slow days the link can be missing. Adding it manually makes sure the original chat is one click away.

Expected: The Zendesk ticket has an internal note with the Intercom conversation URL.

Intercom

Reply in Intercom with one line telling the customer the conversation is moving to email and a follow-up will arrive shortly. Then mark the Intercom conversation as closed.

Keep the message short. 'Moving this to email so we can dig in properly. You'll get a reply from us at the same address shortly.' Customers expect chat to be fast, so silence after a switch causes anxiety.

Expected: The Intercom conversation is closed with a clean hand-off message and the customer knows where to expect the next reply.

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

Triaging an Intercom conversation by topic and intent

Often next

Triaging a new Zendesk ticket and assigning a priority

Alternative to

Resolving an Intercom conversation with a help article

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.

Converted Beacon Health chat to Zendesk #82441 with screenshot

Spun Eastview Studios chat to Zendesk #82398 (login loop)

Moved Atlas Energy CSV-export chat into Zendesk #82355

Converted Sundermark Capital chat after fifth message to Zendesk #82310

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 31 times across 4 connections
Applications	Intercom, Zendesk
First seen	9 Feb 2026, 11:42
Last seen	5 May 2026, 15:20

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