Skip to content

Daily

Get a cited research brief every morning

Each weekday you get a few bullet points on what changed in your topic, each with a source link, and nothing you've already seen.

Runs
Daily
Apps
Anthropic API
AI
Not needed
Access
API key (web search enabled for the org)

Send this to your assistant

Create a ClickRuntime automation: every weekday at 7am, use the Anthropic API with web search to find what's new on EU AI Act enforcement, and email me 5 bullet points with sources. Skip anything you sent me before.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A sales rep before a call, a founder tracking competitors or an analyst following a market needs fresh facts that a news feed will not surface: a new pricing page, a funding round, a hiring spree, a regulation under discussion. Doing that research by hand means a dozen searches each morning, reading through weak results and keeping track of what was already seen. Most people do it for a week and then drop it, so decisions rely on information that is months old.

Every morning, the automation asks Claude, through the Messages API with the web search tool, to research the topics you list. It collects the sources Claude cites, removes items it has already sent (using stored history) and emails you a brief with a link for every claim.

Account executives preparing for meetings, strategy teams and consultants who need current information on a handful of subjects can use it.

What you get out of it

  • Fresh facts reach you each morning

    Instead of searching yourself, you receive findings from the last day, with sources. You walk into the day knowing what changed overnight. You start the day with findings from the last day and the sources behind them, with no searching on your side.

  • Every claim has a citation

    Because the brief includes the sources, you can click through to check anything important before you repeat it to a customer or colleague. Verification takes one click, which matters before you quote anything in a meeting.

  • Old news is not repeated

    Stored history removes items already sent, so each brief adds only what is new. You are not asked to read the same funding story three days running. Each brief then adds only what is new for you.

  • Competitors are watched continuously

    A new product page or a leadership change at a rival appears in your brief the day after it is published, while there is still time to respond. A quick reaction to a rival's move is easier with a day's notice.

  • Research habits that survive busy weeks

    A scheduled brief keeps arriving when you are traveling or buried in other work, so your knowledge of the market does not lapse. Research continues without a reminder. Your picture of the market stays current without effort.

How it works

What happens, step by step

  1. Every day, ClickRuntime asks Claude to search the web for what's new on your topic, such as EU AI Act enforcement.

  2. Claude writes five bullet points, each backed by a source link.

  3. ClickRuntime remembers the links it has already sent you and skips the email if there is nothing new.

  4. When there is news, you get an email with the bullets and a list of the new sources.

Before it runs live

  • Connect Anthropic API

What you get

RunsDaily
Get a cited research brief every morningtoday, 9:00Succeeded
Email · EU AI Act brief• The AI Office opened a consultation on general-purpose model codes of practice (europa.eu)

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
  • Add an AI step, for example to summarize, sort or draft a reply
  • Add another app, for example also send it to Slack
  • Combine it with other Anthropic API 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_brief_using_claude_s_web_search.pyexample
from clickruntime import on_trigger, credentials, notify, http, state

def claude(model, prompt, **extra):
    resp = http.post("https://api.anthropic.com/v1/messages",
                     headers={"x-api-key": credentials.secret("ANTHROPIC_API_KEY"), "anthropic-version": "2023-06-01"},
                     json={"model": model, "max_tokens": 1024, "messages": [{"role": "user", "content": prompt}], **extra},
                     timeout=120)
    resp.raise_for_status()
    return resp.json()

@on_trigger
def run(event):
    sent = set(state.get("sent_urls") or [])
    msg = claude("claude-sonnet-5-5",
                 "Find what's new on EU AI Act enforcement. Give 5 bullet points, each with its source URL. "
                 f"Skip these already-reported URLs: {sorted(sent)[-50:]}",
                 tools=[{"type": "web_search_20250305", "name": "web_search", "max_uses": 5}])
    text = "".join(b["text"] for b in msg["content"] if b["type"] == "text")
    urls = {c["url"] for b in msg["content"] if b["type"] == "text" for c in b.get("citations") or []}
    if not urls - sent:
        return {"new": 0}
    notify.email_me("EU AI Act enforcement brief", text + "\n\nSources:\n" + "\n".join(sorted(urls - sent)))
    state.set("sent_urls", sorted(sent | urls)[-500:])
    return {"new": len(urls - sent)}

FAQ

Common questions

Is there an extra charge for web search?
Yes. The web search tool is part of the Anthropic Messages API, and the key you provide stays secret. Web search usage is billed by Anthropic according to their pricing. Anthropic's pricing page lists the current cost per search.
How do I stop it from drifting off-topic?
List specific topics, names and the kind of news you care about, and say what to ignore. Narrow instructions give tighter briefs than a broad request such as everything about my industry. Tell it which sources to prefer or avoid, too.
Can I trust the information in the brief?
Treat it as a lead, not a verdict. Each claim comes with a link, and for anything you will act on, such as a figure to quote, open the source and check it first. Nothing in the brief should be quoted without checking.
What permissions does it need?
API key (web search enabled for the org). Nothing else in your accounts is used.
Does it need AI?
No. It runs without AI, so it doesn't use your plan's 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.

Set up “Get a cited research brief every morning” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.