Every 30 minutes
Approve replies to your mentions by email
Each new mention gets a drafted reply in your inbox, posted only when you click to approve.
- Runs
- Every 30 minutes
- Apps
- X
- AI
- Yes, uses the built-in AI allowance
- Access
- tweet.read tweet.write users.read
Send this to your assistant
Create a ClickRuntime automation: every 30 minutes, for each new mention of my X account, draft a short reply and email it to me with a link that posts it.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
A brand or founder account on X gets mentions all day: a customer asking about a refund, a happy user, a journalist, a stranger with a hot take. Replying well to each one takes judgement and time, and replying badly in a hurry can start a pile-on. So mentions go unanswered for a day, or get a one-word reply that wastes the attention people gave you.
Every 30 minutes, new mentions are collected and ClickRuntime's built-in AI drafts a reply for each. You receive an email with the mention, the drafted reply and an approve link. Nothing is posted until you click, and the reply is then published from your account.
It suits people who want to keep a human decision on every public post but do not want to write each answer from scratch.
What you get out of it
Replies come faster
Mentions are turned into ready drafts within about half an hour, so the customer who tagged you gets an answer while their question still matters to them. Prompt answers often turn a frustrated customer into a loyal one.
Nothing goes public unreviewed
The approve link means a person reads every reply first. A tone-deaf draft is simply ignored, which protects your brand from an embarrassing public mistake. That final check is what makes AI drafting safe enough to use on a public account.
Less blank-page time
Editing a decent draft in ten seconds is far quicker than composing from nothing, which is what stops many people answering mentions at all. Many mentions go unanswered simply because starting a reply feels like work.
Consistent voice
Drafts follow the style guidance you give, so a team of three people replying from one account sound like the same brand rather than three personalities. Customers then get the same tone whoever happens to be on shift that day.
No missed mentions
Collecting mentions on a set interval and tracking the last one seen means a good question from a customer does not get lost in a noisy notifications tab. Every serious question reaches a person, even on days when the notifications tab is overwhelming.
How it works
What happens, step by step
Every 30 minutes, ClickRuntime checks X for new posts that mention your account.
AI writes a reply to each new mention.
Each draft is emailed to you with the original mention and a Post button.
When you click Post, the reply goes out from your X account. Nothing is posted without your click.
Before it runs live
- Connect X
What you get
Build your own
Need it to work differently?
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 X steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_trigger, report_fetched, state, notify, http, credentials, ai
@on_trigger
def run(event):
auth = {"Authorization": "Bearer " + credentials.connection("x", "main")}
me = http.get("https://api.x.com/2/users/me", headers=auth).json()["data"]["id"]
params = {"max_results": 50}
if state.get("since_id"):
params["since_id"] = state.get("since_id")
data = http.get(f"https://api.x.com/2/users/{me}/mentions", headers=auth, params=params).json()
mentions = data.get("data", [])
report_fetched(len(mentions))
if not mentions:
return {"summary": "No new mentions"}
for t in mentions:
reply = ai.generate(f"Draft a short, friendly reply (under 200 chars) to this mention:\n{t['text']}", max_output_tokens=80).text.strip()
link = f"https://x.com/intent/post?in_reply_to={t['id']}&text={reply}"
notify.email_me("Reply draft for a mention", f"Mention: {t['text']}\n\nDraft: {reply}\n\nPost it: {link}")
state.set("since_id", data["meta"]["newest_id"])
return {"drafted": len(mentions)}FAQ
Common questions
Can the reply be edited before it is posted?
Does it reply to every mention, including trolls?
Which X plan is required to read mentions and post?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
Tweet new articles from a news feed
New items from the feeds you follow are tweeted with a short line and link, each only once.
See how it worksPost a Spanish version of every tweet
Your Spanish-speaking followers get each tweet in their language as a reply.
See how it worksSend new X mentions to Slack
Every @mention of your account shows up in Slack within 15 minutes.
See how it worksKeep exploring
Set up “Approve replies to your mentions by email” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.