Every 15 minutes

Fill in company details from their website

Each new URL in your table gets its page title, meta description, a summary and keywords filled in.

Runs: Every 15 minutes
Apps: Airtable
AI: Yes, uses the built-in AI allowance
Access: data.records:read, data.records:write

Send this to your assistant

Create a ClickRuntime automation: every 15 minutes, for new rows in my Airtable Sites table, open the URL, save the title tag and meta description, and add a short summary and 10 SEO keywords.

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 sales researcher or SEO manager keeps a table of company websites in Airtable: prospects, partners, directories, clients' competitors. The URL is there, but nothing else. Someone has to open each site, work out what the company does, write a summary, pick keywords and draft an SEO title and meta description. At five minutes per site, 300 rows is a full week of tedious reading, so the table stays half empty and the outreach or content plan built on it stays vague.

Every 15 minutes, the automation finds records that have a URL but no enrichment yet, fetches the page, strips out the HTML and sends the text to ClickRuntime's built-in AI. The AI returns a plain summary, keywords and an SEO title and meta description, and these are written back into the record.

It works well for prospect lists, partner directories, affiliate sites and agencies preparing content briefs.

What you get out of it

Research time drops from days to minutes
A table that would take a week of reading fills itself in the background. Staff review and refine the results instead of starting from a blank cell for every company.
Outreach can be personal at scale
With a one-line summary of what each company does, a salesperson can write a first email that shows they looked. Relevant messages get more replies than templates with only a name merged in.
SEO fields are ready for review
A drafted title and meta description in each record gives an editor something to approve or tweak. It is much quicker than writing the metadata for dozens of pages from scratch.
Keywords make the table filterable
Extracted keywords let you build views by theme, such as every fintech or every logistics company, which supports segmentation and campaign planning without manual tagging. Teams can then build views for each industry or topic without tagging anything by hand.
New rows are handled without a request
Anything added to the table is picked up within 15 minutes, so a colleague who pastes in twenty new URLs finds them enriched by the time they come back from lunch.
Every record is treated the same way
The AI uses the same instructions on all rows, so summaries have a consistent length and style, which makes the table easier to scan and to export for reports. That also makes exports tidy.

How it works

What happens, step by step

Every 15 minutes, the automation looks for records in your Airtable table that have a website but no details yet.
It visits each website and reads the page title, description and visible text.
AI writes a short summary of the company and a list of keywords.
The title, description, summary and keywords are filled into the record.

Before it runs live

Connect Airtable

What you get

RunsEvery 15 minutes

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

Airtable · Sitesnorthwind.example · "Northwind | Wholesale coffee for offices" · Keywords: office coffee, bulk beans, …

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 Airtable 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_records_from_their_website_with_ai.pyexample

from bs4 import BeautifulSoup
from clickruntime import on_trigger, credentials, http, ai, report_fetched

BASE_ID = "appXXXXXXXXXXXXXX"
SCHEMA = {"type": "object", "properties": {"summary": {"type": "string"},
          "keywords": {"type": "array", "items": {"type": "string"}}}}

@on_trigger
def run(event):
    api = f"https://api.airtable.com/v0/{BASE_ID}/Sites"
    headers = {"Authorization": f"Bearer {credentials.connection('airtable', 'work')}"}
    todo = http.get(api, headers=headers, params={
        "filterByFormula": "AND({URL}, {Summary} = '')", "maxRecords": 10}).json()["records"]
    report_fetched(len(todo))
    if not todo:
        return {"enriched": 0}
    for rec in todo:
        soup = BeautifulSoup(http.get(rec["fields"]["URL"]).text, "html.parser")
        meta = soup.find("meta", attrs={"name": "description"})
        desc = meta.get("content", "") if meta else ""
        ai_out = ai.generate(soup.get_text(" ", strip=True)[:4000],
                             system="Write a 2-sentence summary and 10 SEO keywords for this page.",
                             json_schema=SCHEMA, max_output_tokens=250).json
        http.patch(api, headers=headers, json={"records": [{"id": rec["id"], "fields": {
            "Title": soup.title.string.strip() if soup.title and soup.title.string else "",
            "Meta Description": desc, "Summary": ai_out["summary"],
            "Keywords": ", ".join(ai_out["keywords"][:10])}}]}).raise_for_status()
    return {"enriched": len(todo)}

FAQ

Common questions

What if a website blocks the request or needs a login?

The record is left unenriched and can be marked with a note so you can see which pages failed. Sites behind a login, or ones that block automated requests, cannot be read, and you can fill those in by hand.

Does it re-enrich records that already have data?

No. It looks for records where the enrichment fields are empty, so existing values are never overwritten. If you want to refresh a record, clear its fields and the next run will pick it up again.

Does the AI use only the home page?

It uses the page at the URL in the record. If you want it to look at an About page, include that address in the record or tell your AI assistant to fetch a second page.

What permissions does it need?

data.records:read, data.records: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 checks. Checks that find nothing new 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.

Every 15 minutesAI