The moment it happens

Tag new conversations by topic

Every new conversation gets a tag like billing, bug or how-to as soon as it starts.

Runs: The moment it happens
Apps: Intercom
AI: Yes, uses the built-in AI allowance
Access: read+write conversations, tags

Send this to your assistant

Create a ClickRuntime automation: when a new Intercom conversation starts, read the first message and tag it as billing, bug, how-to or other.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A SaaS support team has 600 Intercom conversations a week, and leadership wants to know how many are about billing, how many report bugs and how many are simply how-to questions. Agents are supposed to tag each one, but under pressure they skip it, so the tags are patchy and any report built on them is wrong. Product never learns that bug reports tripled after the last release.

When a customer sends the first message in a new conversation, ClickRuntime receives it and asks built-in AI to pick the best match from your own list of tags, such as billing, bug or how-to. It then attaches that tag to the conversation, so every new conversation is categorized before an agent has opened it.

Support leads and product managers who rely on conversation topics for planning will see the biggest effect.

What you get out of it

Reports you can trust
When every conversation is tagged, counts by topic reflect what customers actually asked. Decisions about staffing and priorities stop depending on whichever agents had time to categorize. Leadership can then answer questions about volume by topic using real numbers rather than impressions.
Product hears about bugs sooner
A rise in bug-tagged conversations after a release is an early warning. Product and engineering can see it within the day and investigate before the issue spreads to more customers.
Agents save a repetitive click
Tagging costs a few seconds per conversation, but across hundreds a week it adds up to hours. Having the tag applied before the agent opens the thread removes that step entirely.
Routing rules can use the tags
Once conversations carry reliable topic tags, you can build Intercom rules around them, such as sending billing questions to finance-trained agents. Good routing depends on categories that are always there.
Self-serve gaps become visible
A high number of how-to conversations about the same feature shows where help articles are missing or hard to find. You can write the right article and reduce future volume.

How it works

What happens, step by step

When a customer starts a new Intercom conversation, ClickRuntime reads their first message straight away.
AI picks the best match from your list of tags, such as billing or how-to.
The tag is added to the conversation, so it lands with the right team.

Before it runs live

Connect Intercom
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Tag new conversations by topicjust nowSucceeded

Intercom · Tags"How do I add a teammate?" → how-to "Charged twice for October" → billing

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Intercom steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

ai_auto_tag_new_conversations.pyexample

import re
from clickruntime import on_event, http, credentials, ai

def intercom(method, path, **kw):
    r = http.request(method, f"https://api.intercom.io{path}", headers={
        "Authorization": f"Bearer {credentials.secret('INTERCOM_TOKEN')}", "Intercom-Version": "2.11"}, **kw)
    r.raise_for_status()
    return r.json()

ADMIN_ID = "YOUR_ADMIN_ID"
TAGS = {"billing": "BILLING_TAG_ID", "bug": "BUG_TAG_ID", "how-to": "HOWTO_TAG_ID", "other": "OTHER_TAG_ID"}

@on_event
def handle(event):
    body = event.json or {}
    if body.get("topic") != "conversation.user.created":
        return {"tagged": False}
    convo = body["data"]["item"]
    text = re.sub(r"<[^>]+>", "", convo["source"]["body"] or "")[:1500]
    label = ai.generate(text, system="Reply with one of: billing, bug, how-to, other.", max_output_tokens=5).text.strip().lower()
    label = label if label in TAGS else "other"
    intercom("POST", f"/conversations/{convo['id']}/tags", json={"id": TAGS[label], "admin_id": ADMIN_ID})
    return {"tag": label}

FAQ

Common questions

Does the AI invent new tags?

No. It chooses only from the tags you list, so your Intercom workspace does not fill up with variants like Billing and billing issue. If nothing fits well, you can include an other tag for it to use instead.

What if the AI picks the wrong tag?

An agent can remove or change the tag in Intercom as normal, since it is just a tag on the conversation. Occasional misses are expected on short or vague messages, and you can refine the descriptions of your tags to improve accuracy.

Does it read the whole conversation or only the first message?

It reads the first customer message that started the conversation, which usually states the reason for contact. Later messages are not used, so a conversation that changes topic midway keeps its original tag unless an agent updates it.

What permissions does it need?

read+write conversations, tags. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens