Skip to content

The moment it happens

Turn forwarded emails into sorted Jira tickets

Emails or requests you forward become Jira tickets with a category, priority and short summary, and you hear about the risky ones.

Runs
The moment it happens
Apps
Jira
AI
Yes, uses the built-in AI allowance
Access
write (Create issues)

Send this to your assistant

Create a ClickRuntime automation: give me a link I can forward emails to. For each one, decide if it's phishing or which team it belongs to, create a ticket in project SEC with a priority and summary, and email me if it looks high risk.

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

Employees forward suspicious emails to a security mailbox, and customers write to a general support address. Someone must read each message, decide what it is, open a Jira ticket, copy the text, set a priority and tell the team if it looks dangerous. When a phishing report sits in the queue over a weekend, others in the company may click the same link, and the security team learns about the campaign far too late.

When a forwarded email or request arrives with its subject and body, ClickRuntime has built-in AI decide the category, priority and a short summary, then creates a Jira issue with those fields filled in. If the AI judges the message to be high risk, it also emails you straight away.

Security teams, IT help desks and support teams that rely on a shared mailbox for incoming reports will find it useful.

What you get out of it

  • Dangerous reports are escalated at once

    A message that looks like active phishing triggers an email to you immediately. The team can warn colleagues and block a sender within the hour, not on Monday morning. A short delay in a real phishing case can mean several more employees click.

  • Every report becomes a trackable ticket

    Messages in a mailbox disappear from view when they are read. As Jira issues, they have owners, statuses and history, so nothing is lost and the team can measure how long reports take to handle.

  • Triage work is done before a human looks

    The category, priority and summary are filled in, so the analyst opens a ticket that is ready to act on. Handling time per report falls, which matters when volume spikes.

  • Patterns across reports become visible

    Because each report is categorized, ten reports of the same fake invoice show up as a cluster. Seeing that pattern helps the team recognize a campaign and respond to all of it, not just one email.

  • Employees get a reliable process

    People who report suspicious messages see them handled consistently. When reporting leads to a quick response, employees keep doing it, which strengthens the company's early warning system. A reliable reporting loop is one of the cheapest security controls a company can have.

How it works

What happens, step by step

  1. When you forward an email or a request form is sent in, ClickRuntime receives its subject and text.

  2. AI reads it and picks a category, a priority and writes a short summary.

  3. A Jira ticket is created with those fields filled in.

  4. If AI marks it high risk, such as a phishing attempt, you get an email straight away.

Before it runs live

  • Connect Jira
  • Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens
Turn forwarded emails into sorted Jira ticketsjust nowSucceeded
Email · High-risk email: SEC-208phishing · Highest Fake invoice from "Northwind Billing" asking to update bank details via a lookalike domain.

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 Jira 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_turns_submitted_emails_or_requests_into_classified_tickets.pyexample
from clickruntime import on_event, credentials, http, ai, notify

JIRA = "https://api.atlassian.com/ex/jira/your-cloud-id"

def jira(method, path, **kw):
    resp = http.request(method, JIRA + path, headers={
        "Authorization": f"Bearer {credentials.connection('jira', 'work')}", "Accept": "application/json"}, **kw)
    resp.raise_for_status()
    return resp.json() if resp.content else None

def search(jql, fields, limit=100):
    return jira("POST", "/rest/api/3/search/jql", json={"jql": jql, "fields": fields, "maxResults": limit})["issues"]

def adf(text):
    return {"type": "doc", "version": 1, "content": [{"type": "paragraph", "content": [{"type": "text", "text": text}]}]}

SCHEMA = {"type": "object", "properties": {
    "category": {"enum": ["phishing", "IT", "HR", "Finance", "Security", "Other"]},
    "priority": {"enum": ["Highest", "High", "Medium", "Low"]},
    "summary": {"type": "string"}, "high_risk": {"type": "boolean"}}}

@on_event
def handle(event):
    mail = event.json or {}
    out = ai.generate(f"From: {mail.get('from')}\nSubject: {mail.get('subject')}\n\n{(mail.get('body') or '')[:4000]}",
                      system="Triage this forwarded email: is it phishing, or which team owns it? Give priority and a one-line summary.",
                      json_schema=SCHEMA, max_output_tokens=120).json
    issue = jira("POST", "/rest/api/3/issue", json={"fields": {
        "project": {"key": "SEC"}, "issuetype": {"name": "Task"}, "priority": {"name": out["priority"]},
        "labels": [out["category"].lower()], "summary": f"[{out['category']}] {mail.get('subject', '')}"[:250],
        "description": adf(f"{out['summary']}\n\nFrom: {mail.get('from')}")}})
    if out["high_risk"]:
        notify.email_me(f"High-risk email: {issue['key']}", f"{out['category']} · {out['priority']}\n{out['summary']}")
    return {"issue": issue["key"], **out}

FAQ

Common questions

What does the AI decide about each email?
It reads the subject and body and assigns a category such as phishing, support request or billing, a priority, and a brief summary of what the message says. For anything that appears dangerous, it flags the risk so you are alerted.
Can I trust the AI to judge phishing correctly?
It is a first filter, not a security product. It can recognize common signs such as urgent requests for credentials, but it can miss a clever message. Treat its verdict as a prompt for an analyst to review, especially for medium risk items.
How do emails get into the automation?
Your mail system forwards the messages to the link ClickRuntime provides, sending the subject and body. Many teams set a rule on the shared mailbox for this. The link is private, so keep it to your mail administrator.
What permissions does it need?
write (Create issues). 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 for each event the app sends.
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 “Turn forwarded emails into sorted Jira tickets” from your assistant

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