Skip to content

Daily

Get only the security news that affects your tech stack

Every morning you get one email with the security news items that match the tools and systems you actually use.

Runs
Daily
Apps
Gmail, Pinecone
AI
Yes, uses the built-in AI allowance
Access
Pinecone read; gmail.send

Send this to your assistant

Create a ClickRuntime automation: every morning at 7, check these security news feeds, keep only items that match my tech stack stored in Pinecone, and email me the list with a line on why each matters.

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

Security feeds publish dozens of advisories a day, and most concern software you do not run. Reading them all is impossible, but skimming risks missing the one patch that matters to you.

IT managers, developers and small security teams use it to see only the advisories that touch their own stack, every morning.

What you get out of it

  • Signal, not noise

    Only items that match your stack reach your inbox.

  • Matching by meaning

    An advisory about a library you use is caught even if your stack list names it differently.

  • Why it matters, in a line

    Each item comes with a short note on which part of your stack it affects.

  • Never the same item twice

    Items already sent are remembered.

How it works

What happens, step by step

  1. Every morning, ClickRuntime reads the new items in the security feeds you chose.

  2. Each item is compared with the entries describing your tech stack in Pinecone.

  3. Items that closely match are kept, and AI writes a line on why each matters to you.

  4. You get one email from your Gmail with the matching items and links.

Before it runs live

  • Connect Google through your own Google app (a one-time, 10-minute setup), so it works with your own Gmail
  • Connect Pinecone

What you get

RunsDaily
Get only the security news that affects your tech stacktoday, 9:00Succeeded
Email · Security news2 security items for your stack Critical flaw in PostgreSQL 16 logical replication: you run PostgreSQL 16 for the Acme orders database.

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 Gmail and Pinecone 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.
relevant_news_filter_emailed_daily.pyexample
import base64
import feedparser
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from clickruntime import on_trigger, credentials, http, state, ai

ME, FEEDS = "me@example.com", ["https://www.cisa.gov/cybersecurity-advisories/all.xml", "https://example.com/security/feed"]
HOST, NS = "https://kb-abc123.svc.aped-1234.pinecone.io", "stack"  # your index host and namespace
def send(to, subject, body):
    raw = f"To: {to}\r\nSubject: {subject}\r\nContent-Type: text/plain; charset=utf-8\r\n\r\n{body}"
    build("gmail", "v1", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False).users() \
        .messages().send(userId="me", body={"raw": base64.urlsafe_b64encode(raw.encode()).decode()}).execute()

@on_trigger
def run(event):
    seen = set(state.get("seen") or [])
    items = [e for url in FEEDS for e in feedparser.parse(http.get(url).content).entries if e.link not in seen][:60]
    hits = []
    for e in items:
        r = http.post(f"{HOST}/records/namespaces/{NS}/search", json={"query": {"inputs": {"text": e.title}, "top_k": 1}}, headers={
            "Api-Key": credentials.secret("PINECONE_API_KEY"), "X-Pinecone-API-Version": "2025-04"}).json()["result"]["hits"]
        if r and r[0]["_score"] > 0.82:
            hits.append(f"{e.title} | matches: {r[0]['fields']['chunk_text']} | {e.link}")
    if hits:
        notes = ai.generate("For each line, write the title, then one line on why it matters for the matched tool:\n"
                            + "\n".join(hits), max_output_tokens=800).text
        send(ME, f"{len(hits)} security items for your stack", notes + "\n\nLinks:\n" + "\n".join(h.split(" | ")[-1] for h in hits))
    state.set("seen", sorted(seen | {e.link for e in items})[-3000:])
    return {"checked": len(items), "matched": len(hits)}

FAQ

Common questions

How do I describe my stack?
Store a list of the tools, versions and services you run in your Pinecone index, one entry each. Update it when your stack changes.
Which feeds can I use?
Any RSS or Atom feed, such as vendor advisories, national security agencies or security news sites.
What if nothing matches?
No email is sent that day.
What permissions does it need?
Pinecone read; gmail.send. 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.

Set up “Get only the security news that affects your tech stack” from your assistant

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