Every 15 minutes
Get new comments by email with spam marked
You hear about each new comment, and the obvious spam is flagged so you can deal with it in one go.
- Runs
- Every 15 minutes
- Apps
- WordPress
- AI
- Optional
- Access
- read (+write to moderate)
Send this to your assistant
Create a ClickRuntime automation: every 15 minutes, email me new WordPress comments with the post they're on, and mark any that are obviously spam as spam.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Comments on a WordPress site are a mix of genuine questions and junk. Without a prompt, the moderation queue sits unread for days, a customer's real question waits behind forty link-stuffed casino comments, and spam that slipped past the filter goes live under your best post.
Every 15 minutes the automation lists comments made since the last check and emails you each one with the author, post and text. If you turn on the optional AI check, ClickRuntime's built-in AI judges whether a comment looks like spam, labels it in the message, and can set the comment's status to spam in WordPress.
Site owners who want to approve comments personally use the alert alone, while busy blogs rely on the spam check to keep the queue clean. Either way, nothing sits unseen between visits to the dashboard of your WordPress site.
What you get out of it
Real questions are seen quickly
A reader's genuine question reaches your inbox within a quarter of an hour, so a reply goes out while they are still interested in the topic. Good replies in that window show readers that real people run the site.
Spam is dealt with before it shows
Marking obvious junk as spam straight away keeps promotional links off your posts, which protects reader trust and avoids search penalties for linking to bad sites. Readers who see junk links under your posts tend to lose trust in everything else.
The moderation queue stays short
With spam removed automatically, the comments that remain in the queue are the ones that need a human decision, rather than an overwhelming mixed list. That leaves your attention for the small number of comments that deserve a considered answer.
You decide how aggressive to be
The AI check is optional and can start as a label only. Once you trust its judgement, you can allow it to change the status and spare yourself the manual clicking.
Context is in the email
Each alert shows the post title, author name and comment text, so you can judge the comment without logging into the WordPress admin first. That saves a round trip to wp-admin just to decide whether a comment is worth opening.
How it works
What happens, step by step
Every 15 minutes, ClickRuntime checks WordPress for comments since its last check.
If you turn it on, AI reads each comment and flags the obvious spam.
You get one email listing each comment with the author and link, with spam clearly marked.
If you choose, flagged comments are also moved to spam in WordPress for you.
Before it runs live
- Connect WordPress
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 WordPress steps into one automation
Under the hood
The code that runs this automation
import re
from clickruntime import on_trigger, credentials, http, state, ai, notify, report_fetched
SITE = "https://blog.example.com"
def wp(method, path, **kw):
resp = http.request(method, f"{SITE}/wp-json/wp/v2/{path}", **kw,
auth=("admin", credentials.secret("WP_APP_PASSWORD")))
resp.raise_for_status()
return resp.json()
@on_trigger
def run(event):
last_id = state.get("last_id") or 0
comments = [c for c in wp("GET", "comments", params={"status": "all", "context": "edit", "per_page": 50,
"orderby": "id", "order": "asc"}) if c["id"] > last_id]
report_fetched(len(comments))
if not comments:
return {"summary": "Nothing new"}
lines = []
for c in comments:
text = re.sub(r"<[^>]+>", "", c["content"]["raw"])[:1000]
try:
spam = ai.generate(text, max_output_tokens=5, system="Answer SPAM or OK only.").text.strip().upper() == "SPAM"
except (ai.AINotIncluded, ai.AILimitReached):
spam = text.count("http") > 2
if spam:
wp("POST", f"comments/{c['id']}", json={"status": "spam"})
lines.append(f"{'[SPAM] ' if spam else ''}{c['author_name']} on {c['link']}\n{text[:300]}")
notify.email_me(f"{len(comments)} new comments", "\n\n".join(lines))
state.set("last_id", comments[-1]["id"])
return {"new": len(comments)}FAQ
Common questions
Does the AI ever mark a real comment as spam?
Can I get alerts only for comments on certain posts?
Do pingbacks and trackbacks count as comments?
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
Rewrite feed articles into draft posts
New articles from feeds you follow are rewritten, or translated, into original drafts with a link back to the source.
See how it worksTag and categorise new posts automatically
Posts that go up without tags get sensible ones and a category picked from those you already use.
See how it worksReply to new comments on your blog
Approved comments get a short, polite reply written for that comment and posted under your name.
See how it worksKeep exploring
Set up “Get new comments by email with spam marked” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.