Daily

Build a research library in Notion

Every morning, new articles or papers on your topics are summarised, filed in Notion, and listed in Slack.

Runs: Daily
Apps: Notion, Slack
AI: Yes, uses the built-in AI allowance
Access: Notion insert; Slack chat:write

Send this to your assistant

Create a ClickRuntime automation: every morning, check these RSS feeds for new articles about climate tech, summarise and tag each one, add them to my Research database in Notion and post the list to #research.

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 team that tracks a fast-moving field, such as AI research, regulation or a competitor's product line, has two problems. Reading everything is impossible, and what one person reads never reaches the others. Someone shares a link in chat on Tuesday, it scrolls away by Thursday, and three months later a new hire asks whether anyone looked at that paper. The knowledge exists but it was never filed.

Each day ClickRuntime fetches your chosen feeds or pages, skips any links it has seen before, and uses its built-in AI to write a short summary and assign a category such as Models, Policy or Tooling. Each item becomes a page in a Notion database, and a digest of the day's items is posted to Slack.

It is useful for research teams, product groups and consultancies that need a searchable record of what happened in their field.

What you get out of it

Reading is shared, not repeated
One automated pass through the sources replaces a dozen people skimming the same feeds. The team reads a short digest in Slack and only opens the items that matter to them.
Every item is filed and searchable
Summaries land in a Notion database with their category and link. Months later you can filter for Policy items from March instead of searching chat history. Months later you can filter for Policy items from March instead of searching chat history for a half-remembered link.
Categories show where the field is moving
With items labelled by topic, a growing number of Tooling entries stands out. Strategy discussions can refer to what has actually been published rather than impressions. Strategy discussions can point to what has been published rather than to impressions.
New hires get context quickly
A person joining the team can browse the database to see what the group has tracked. Onboarding on a topic takes an afternoon rather than weeks of asking colleagues. Onboarding on a topic takes an afternoon of reading instead of weeks of asking around.
Duplicates are filtered out
Stored links ensure an article reposted by three outlets creates one page. The database stays clean, and the Slack digest never repeats yesterday's items. The database stays clean, and nobody sees the same story twice in Slack across several days.

How it works

What happens, step by step

Every morning, ClickRuntime checks the news feeds you chose for new articles, skipping any it has already filed.
AI writes a short summary of each article and picks a category for it.
Each article is saved as a page in your Notion research database with its summary, category and link.
A digest of the day's articles is posted to your #research Slack channel.

Before it runs live

Connect Notion and share the database you want it to use
Connect Slack, then invite the app to the channel (type /invite @ClickRuntime there)

What you get

RunsDaily

Build a research library in Notiontoday, 9:00Succeeded

Slack · #research🌍 Climate tech today • [funding] Acme Grid raises $40M for home batteries: Series B led by…

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 Google Sheets
Combine it with other Notion and Slack 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_news_research_digest_saved_to_notion_and_posted_to_slack.pyexample

import feedparser
from clickruntime import on_trigger, credentials, http, state, ai, notify, report_fetched

FEEDS = ["https://www.canarymedia.com/rss", "https://techcrunch.com/category/climate/feed/"]
DATABASE_ID = "your-research-database-id"

@on_trigger
def run(event):
    seen = set(state.get("seen") or [])
    new = [e for url in FEEDS for e in feedparser.parse(url).entries[:15] if e.link not in seen]
    report_fetched(len(new))
    if not new:
        return {"new": 0}
    lines = []
    for e in new:
        r = ai.generate(f"{e.title}\n{e.get('summary', '')[:1500]}", max_output_tokens=120,
                        json_schema={"type": "object", "properties": {"summary": {"type": "string"},
                                     "tag": {"enum": ["energy", "transport", "carbon removal", "policy", "funding", "other"]}}}).json
        http.post("https://api.notion.com/v1/pages",
                  headers={"Authorization": f"Bearer {credentials.secret('NOTION_TOKEN')}", "Notion-Version": "2022-06-28"},
                  json={"parent": {"database_id": DATABASE_ID}, "properties": {
                      "Name": {"title": [{"text": {"content": e.title[:200]}}]}, "URL": {"url": e.link},
                      "Summary": {"rich_text": [{"text": {"content": r["summary"][:2000]}}]},
                      "Tag": {"select": {"name": r["tag"]}}}})
        lines.append(f"• [{r['tag']}] <{e.link}|{e.title}>: {r['summary']}")
    notify.slack("🌍 Climate tech today\n" + "\n".join(lines), channel="#research")
    state.set("seen", (list(seen) + [e.link for e in new])[-1000:])
    return {"new": len(new)}

FAQ

Common questions

Which sources can it follow?

RSS and Atom feeds, arXiv listings, blog index pages and other pages where each item has a link. You list them during setup, and sources can be added later by editing the list. It can read the same sources daily without sending you repeats.

How are categories decided?

The built-in AI assigns one from a list that you provide, using the title and text of each item. Choose categories that match how your team talks, and refine the list if items land in the wrong one.

Does it need a Notion database already set up?

Yes, with properties such as Title, URL, Summary, Category and Date. The Notion integration must be shared with that database. If the properties are not there yet, your AI assistant can describe what to add.

What permissions does it need?

Notion insert; Slack chat: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 (daily). 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