Hourly

Fill in company details from their websites

Each company in your sheet gets its industry, B2B or B2C, and a one-line summary from its own website.

Runs: Hourly
Apps: Google Sheets
AI: Yes, uses the built-in AI allowance
Access: read+write (only the sheets you pick when connecting)

Send this to your assistant

Create a ClickRuntime automation: every hour, for rows in my Companies sheet with an empty Industry column, read the company's website and fill in industry, B2B or B2C, and a one-line summary.

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 business development manager has a Google Sheet of three hundred company names and websites from a trade show. To qualify them she needs the industry, the market they serve and a one-line description, which means opening each site, reading the homepage and typing a summary. It takes four minutes per company, so the list sits half-finished and the follow-ups go out to the wrong audience, or not at all.

Every hour, ClickRuntime reads the sheet, picks rows whose output columns are blank, fetches each company's website and asks ClickRuntime's built-in AI to fill in the industry, market and a short summary from what the site says. The results are written back to the same row, a few companies each run.

Sales teams, investors, recruiters and market researchers use it to turn a plain list of names into an organized, filterable dataset.

What you get out of it

A list you can filter and segment
Once every row has an industry and a market, you can sort the sheet by segment and send relevant messages. A tailored note to retailers converts better than one note sent to everybody.
Hours of reading are saved
Four minutes per company across three hundred rows is twenty hours of reading and typing. Doing it in the background means your time goes to reaching out to the companies that fit.
Summaries come from the company's own words
The details are taken from the website, not from guesses based on the company name. A description in the firm's own terms makes your first email sound informed. Reading the same page by hand would take far longer.
Rows with data are never overwritten
Only blank rows are filled, so anything you typed or fixed by hand is left alone. You can correct a result and rest assured the next run will not replace it.
The sheet grows without extra effort
Add new companies to the bottom, and the next run enriches them. A list that used to need a research sprint becomes something you keep adding to during the week.

How it works

What happens, step by step

Every hour ClickRuntime reads your Google Sheet of companies.
It picks the rows where the industry, business model or summary is still blank.
It visits each company's website and AI fills in the industry, whether it sells to businesses or consumers, and a one-line summary.
The answers are written back into the same row of the sheet.

Before it runs live

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

What you get

RunsHourly

Fill in company details from their websitestoday, 9:00Succeeded

Google Sheets · CompaniesNorthwind Analytics | Data software | B2B | Builds dashboards for retail supply chains.

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.

enrich_company_rows_from_their_websites_with_ai.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from bs4 import BeautifulSoup
from clickruntime import on_trigger, credentials, http, ai

SHEET_ID = "your-spreadsheet-id"
SCHEMA = {"type": "object", "properties": {"industry": {"type": "string"}, "model": {"type": "string", "enum": ["B2B", "B2C"]},
          "summary": {"type": "string"}}, "required": ["industry", "model", "summary"]}

@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="Companies!A2:E").execute().get("values", [])
    updates = []
    for i, row in enumerate(rows, start=2):
        name, website, industry = (row + ["", "", ""])[:3]
        if industry or not website:
            continue
        page = BeautifulSoup(http.get(website, timeout=15).text, "lxml").get_text(" ", strip=True)[:3000]
        d = ai.generate(f"From this website text for {name}, give the industry, B2B or B2C, and a one-line summary.\n{page}",
                        json_schema=SCHEMA, max_output_tokens=120).json
        updates.append({"range": f"Companies!C{i}:E{i}", "values": [[d["industry"], d["model"], d["summary"]]]})
        if len(updates) == 20:
            break  # keep each run short
    if updates:
        sheets.values().batchUpdate(spreadsheetId=SHEET_ID, body={"valueInputOption": "RAW", "data": updates}).execute()
    return {"enriched": len(updates)}

FAQ

Common questions

What if a website cannot be read?

Sites that block automated requests, need a login or render only with scripts may return little text. Those rows are marked, so you can fill them manually or try another page, such as the About page.

How accurate are the industry labels?

They are usually right for companies with a clear homepage, and less so for broad conglomerates or sites with little text. Supply a list of allowed industries and review a sample of results before using them for outreach.

Can it find other details like company size or location?

It can pick up details that a website states, such as city, product lines or the founding year. Facts that are not published, like exact headcount or revenue, are left blank, because the model is told not to guess them.

What permissions does it need?

read+write (only the sheets you pick when connecting). 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 (hourly). 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.

DailyAI