On a schedule

Label a list of keywords by intent

Every keyword or text row gets an intent and a topic label filled in.

Runs: On a schedule
Apps: Google Sheets
AI: Yes, uses the built-in AI allowance
Access: read+write

Send this to your assistant

Create a ClickRuntime automation: go through every keyword in my SEO sheet, label each by search intent (informational, commercial, transactional) and topic cluster, and fill in the two columns.

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

An SEO specialist exports four thousand keywords from a research tool into a Google Sheet. Before planning content she needs to know which are informational, which are commercial and which show buying intent, and sorting them by eye takes days. Rule-based filters on words like best or buy catch only part of them, and a phrase such as how to fix leaking tap needs a human to see it is a plumbing how-to and not a product search.

On the schedule you choose, ClickRuntime reads the rows that have no label yet, in batches, and sends them to ClickRuntime's built-in AI with your instructions and the list of allowed labels. The labels are written back next to each keyword, so you can filter and group the sheet without having read every line.

The same method works for support tickets, survey answers, product names and any text column that needs a category.

What you get out of it

Thousands of rows labeled in the background
A job that would eat several days of reading is done in batches while you work on something else. The sheet is ready to filter once the last batch lands.
Intent is read from meaning, not keywords
The model understands that a phrase about fixing a tap is a how-to and that compare plans is commercial. Simple word matching misses these cases, and so does anyone skimming a long list late in the day.
Content plans built on a consistent grouping
When every keyword carries a label from the same set, you can count how many informational terms you have and where the gaps are. Planning by cluster replaces planning by gut feeling.
Labels keep pace with new exports
New rows added next month are picked up by the next run and labeled by the same rules. You never end up with an old half classified by one person and a new half by another.
Cheaper than outsourcing the sort
Paying someone to tag thousands of lines is slow and costs real money. Automated first-pass labels give most of the value, and a person only checks the uncertain ones. Budget goes to strategy and writing instead.

How it works

What happens, step by step

Every hour ClickRuntime reads the next batch of unlabelled keywords from your Google Sheet.
AI decides whether each keyword is informational, commercial or transactional, and groups it into a topic.
The labels are written back next to each keyword.
It keeps going batch by batch until every row is labelled.

Before it runs live

Connect your Google Sheets account and pick the spreadsheets it may use

What you get

RunsOn a schedule

Label a list of keywords by intenttoday, 9:00Succeeded

Google Sheets · SEObest crm for startups | commercial | CRM software how to export contacts | informational | Data export

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

Run it at a different time, more or less often, or only on weekdays
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 Google Sheets 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.

classify_keywords_or_text_rows_with_ai.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
import json
from clickruntime import on_trigger, credentials, ai

SHEET_ID = "your-spreadsheet-id"
SCHEMA = {"type": "object", "properties": {"rows": {"type": "array", "items": {"type": "object", "properties": {
    "intent": {"type": "string", "enum": ["informational", "commercial", "transactional"]}, "cluster": {"type": "string"}},
    "required": ["intent", "cluster"]}}}, "required": ["rows"]}

@on_trigger
def run(event):
    sheets = build("sheets", "v4", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False).spreadsheets()
    rows = sheets.values().get(spreadsheetId=SHEET_ID, range="SEO!A2:C").execute().get("values", [])
    todo = [(i, r[0]) for i, r in enumerate(rows, start=2) if r and len(r) < 2]
    data = []
    for start in range(0, len(todo), 50):  # 50 keywords per AI call
        batch = todo[start:start + 50]
        labels = ai.generate("Label each keyword with search intent and a short topic cluster, in order:\n"
                             + json.dumps([k for _, k in batch]), json_schema=SCHEMA, max_output_tokens=2000).json["rows"]
        data += [{"range": f"SEO!B{i}:C{i}", "values": [[l["intent"], l["cluster"]]]} for (i, _), l in zip(batch, labels)]
    if data:
        sheets.values().batchUpdate(spreadsheetId=SHEET_ID, body={"valueInputOption": "RAW", "data": data}).execute()
    return {"labelled": len(data)}

FAQ

Common questions

How do I get accurate labels?

Give the exact label names and a one-line definition of each, with a few examples of borderline phrases. Small, clear label sets work best. Check a sample of 50 rows after the first batch and adjust the wording if something is off.

Can it add a confidence note or second label?

Yes. You can ask for a second column with a short reason or a confidence level, and a secondary label for mixed cases. Rows with low confidence can then be sorted to the top for a person to review quickly.

Does it work for non-English keywords?

Generally yes, since the model reads many languages. State the language in your instructions, and keep the label names in the language you work in. Test a handful of rows first, as quality varies for rarer languages and slang terms.

What permissions does it need?

read+write. 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 each time it runs (on a schedule). Checks that find nothing to do and stop right away aren't counted.

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.

HourlyAI