On a schedule

Add a daily research digest to a Doc

Each morning a dated section with a short digest of your source is added to a running Doc.

Runs: On a schedule
Apps: Google Docs
AI: Yes, uses the built-in AI allowance
Access: read+write (doc shared with the service account as Editor)

Send this to your assistant

Create a ClickRuntime automation: every morning at 7am, take the top 10 Hacker News stories, summarise each in two lines and add today's section to the end of my Research Digest doc.

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 investor wants a daily read on what Hacker News is talking about, how a particular stock moved and whether new filings landed. He used to open several tabs each morning, skim, and forget what he saw by lunchtime. There is no memory of the earlier digests, so patterns across weeks, like a rising topic or a company filing repeatedly, never become visible.

Each day, ClickRuntime fetches the source data over HTTP, hands it to its built-in AI for analysis and appends a dated section to the end of your Google Doc. Over weeks the Doc becomes a research journal with one entry per day, written in the same format each time.

Founders, analysts and students use it to follow a topic or a company without checking the sources by hand.

What you get out of it

A daily briefing you do not assemble
The analysis is written before you start your day. You spend the time reading and thinking instead of opening tabs and copying out the interesting items. That leaves your morning free for thinking about what it means.
A searchable history of the topic
Every entry stays in the Doc, so you can look for a company or a theme across months. That is impossible when you only skim live pages that change by the hour. That long memory is the real value of a daily log.
Trends emerge from repetition
When the same topic shows up in ten daily entries, you notice it. A rising theme or a company filing repeatedly is a signal you would miss reading one page at a time.
Consistent format makes skimming fast
Each section follows the same layout, so you find the key point in seconds. That consistency matters when you read many entries in a row to catch up after a trip.
Source data is fetched for you
Live prices, filings or ranked lists are retrieved at the scheduled time. The entry reflects the same moment each day, which makes day-to-day comparisons fair. Because the data is pulled at the same hour each day, the entries line up and trends are real.

How it works

What happens, step by step

Every day ClickRuntime fetches the current top 10 stories from Hacker News.
AI summarises them in a short numbered list.
The summary is added to the end of your research Google Doc under today's date, so the Doc becomes a running archive.

Before it runs live

Connect Google Docs

What you get

RunsOn a schedule

Add a daily research digest to a Doctoday, 9:00Succeeded

Google Docs · Research DigestMonday 19 October 2026 1. Acme open-sources its vector database – benchmarks show 2x faster writes…

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 Docs 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.

scheduled_research_digest_written_to_a_doc.pyexample

from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from datetime import date
from clickruntime import on_trigger, credentials, http, ai

DOC_ID = "research-digest-doc-id"

@on_trigger
def run(event):
    ids = http.get("https://hacker-news.firebaseio.com/v0/topstories.json").json()[:10]
    stories = [http.get(f"https://hacker-news.firebaseio.com/v0/item/{i}.json").json() for i in ids]
    listing = "\n".join(f"{s['title']} ({s.get('url', 'https://news.ycombinator.com/item?id=' + str(s['id']))})" for s in stories)
    summary = ai.generate("Summarise each story in two lines, keeping its link:\n" + listing, max_output_tokens=900).text
    docs = build("docs", "v1", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    end = docs.documents().get(documentId=DOC_ID).execute()["body"]["content"][-1]["endIndex"] - 1
    docs.documents().batchUpdate(documentId=DOC_ID, body={"requests": [
        {"insertText": {"location": {"index": end}, "text": f"\n{date.today():%A %d %B %Y}\n{summary}\n"}}]}).execute()
    return {"stories": len(stories)}

FAQ

Common questions

Which sources can it follow?

Any source reachable over HTTP, such as public pages, JSON feeds and APIs. Hacker News, stock prices and filing indexes are common choices. Sources behind a login or with strict limits on automated access may not work, so check the terms of each site.

Is the analysis investment advice?

No. It summarizes the data it is given and does not know your situation or the full market. Treat the entry as a reading aid, and do your own research or speak to a licensed adviser before making financial decisions.

Does the Doc get messy after months of entries?

Each day adds a dated heading, so the Doc's outline lets you jump straight to a date. If it grows too large, start a new Doc each quarter and keep the old one as an archive. Pointing the entry at the new Doc is a quick change.

What permissions does it need?

read+write (doc shared with the service account as Editor). 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.

DailyAI