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, 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.

Triaging an Intercom conversation by topic and intent

When a new conversation lands in the team Intercom inbox, the support rep applies one intent tag (bug, billing, feature-request, login, onboarding or account-change) and assigns to the matching teammate or shared inbox. Conversations that have crossed three messages or include an error screenshot are converted to a Zendesk ticket rather than handled in chat.

Tags

intercomtriagetaggingroutingintent

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 new conversation lands in the team Intercom inbox, the support rep opens it, reads the customer's opening message in full and applies one of a small set of intent tags (bug, billing, feature-request, login, onboarding, account-change). They then assign the conversation to the matching teammate or shared inbox and write a one-line internal note summarising what the customer is asking for. If the conversation already has more than three back-and-forth messages or includes a screenshot of an error, the support rep biases towards converting it into a Zendesk ticket rather than continuing to handle it inside chat.

Reasoning

Tagging by intent at the moment of triage is what makes the rest of the workflow possible. The intent tag is the signal that drives Intercom's round-robin assignment, and a wrong tag silently routes a billing question to a teammate who only handles bugs. The bias towards converting any conversation that already has depth or a screenshot reflects a learned reality on this team: chats that have crossed three messages are rarely closed in chat, and trying to keep them there only delays the inevitable Zendesk ticket and frustrates the customer with a second hand-off later. The internal note is short on purpose so the next support rep can read it in two seconds without scrolling the full transcript.

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 new Intercom conversation arrives in the team inbox or is reassigned to the support team from the in-product help bot.

Outcome

The conversation is tagged with one intent label, assigned to the right teammate or shared inbox and accompanied by a one-line internal note. Conversations that already have more than three messages or include a screenshot of an error are converted to a Zendesk ticket instead of being kept in chat.

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 new conversation from the team inbox and read the customer's opening message in full before doing anything else.

Pay attention to urgency cues such as all-caps words, 'URGENT', exclamation marks or distress emoji. These often warrant a higher priority than the message body alone suggests, especially when the customer is on a paid plan.

Expected: You have a clear sense of what the customer is asking and how urgent the conversation feels.

Intercom

Apply exactly one intent tag from the approved set: bug, billing, feature-request, login, onboarding or account-change.

Avoid stacking more than one intent tag on a single conversation. The first one drives routing and the second one tends to be wrong. If the conversation truly straddles two intents (e.g. a login bug on a billing-only account), pick the one that determines who needs to act first.

Expected: The conversation is tagged with one intent label that matches the customer's primary ask.

Intercom

Assign the conversation to the teammate or shared inbox that owns the chosen intent.

Bug goes to the bug-triage inbox, billing goes to the billing teammate, feature-request goes to the product-feedback inbox and login, onboarding and account-change stay in the general support inbox unless a senior support rep is online.

Expected: The conversation is now visible to the right person or queue and is no longer in the unassigned pool.

Intercom

Add a one-line internal note summarising the ask so the next support rep can pick up without re-reading the transcript.

Keep it under fifteen words and lead with what the customer wants, not what they said. 'Wants invoice for March re-issued with new VAT number' beats 'Customer is asking about an invoice'.

Expected: The conversation has an internal note that explains the ask in one short sentence.

Intercom

If the conversation already has more than three back-and-forth messages or includes a screenshot of an error, stop here and trigger the Zendesk conversion flow instead of replying.

Long chats and chats with screenshots almost always become tickets in the end. Converting now saves the customer the second hand-off and keeps the support history in one place from the start.

Expected: Long or technical conversations are routed into Zendesk before any reply is sent in chat. Shorter conversations stay in Intercom for a quick 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 next

Resolving an Intercom conversation with a help article Converting an Intercom conversation into a Zendesk ticket

Alternative to

Triaging a new Zendesk ticket and assigning a priority

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.

Tagged Eastview Studios chat as 'login' and routed to Rohan

Triaged Northwind Logistics chat as 'billing', noted VAT re-issue ask

Bumped Beacon Health chat to Zendesk after fourth back-and-forth

Tagged Atlas Energy chat 'feature-request' and dropped to product-feedback inbox

Triaged Quillstone Legal chat as 'onboarding' for Eleanor

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 87 times across 5 connections
Applications	Intercom
First seen	4 Feb 2026, 08:23
Last seen	6 May 2026, 17:18

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