The moment it happens
Draft answers to new support tickets and share them in Slack
When a support ticket arrives, a draft answer based on your knowledge base is posted in Slack for the team to review.
- Runs
- The moment it happens
- Apps
- Pinecone, Slack
- AI
- Yes, uses the built-in AI allowance
- Access
- Pinecone read; Slack chat:write
Send this to your assistant
Create a ClickRuntime automation: when a support ticket is sent to this link, find relevant answers in my Pinecone knowledge base, draft a reply and post the ticket and draft to #support.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Support teams answer the same questions every day from the same knowledge base, yet each agent searches it from scratch. New team members take longest, and customers wait while they look.
Support teams at software companies and online shops use it so each new ticket arrives in Slack with a suggested answer and the articles it came from.
What you get out of it
A head start on every ticket
Agents begin from a draft rather than a blank reply.
New agents answer like old hands
Drafts draw on the knowledge base, so consistency does not depend on experience.
Visible to the whole team
Posting in Slack lets anyone pick up a ticket or improve the draft.
Sources shown
Each draft lists the articles it used, so agents can check them quickly.
How it works
What happens, step by step
When a ticket is created, your help desk sends it to your automation's link.
Your Pinecone knowledge base is searched for articles that match the ticket.
AI drafts a reply using those articles, or notes that none matched.
The ticket, the draft and the article titles are posted to your Slack support channel.
Before it runs live
- Connect Pinecone
- Connect Slack, then invite the app to the channel (type /invite @ClickRuntime there)
- Paste your automation's link into the other app's webhook settings
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 Google Sheets
- Combine it with other Pinecone and Slack steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_event, credentials, http, notify, ai
HOST, NS = "https://kb-abc123.svc.aped-1234.pinecone.io", "help-center"
def search(text, k=5):
r = http.post(f"{HOST}/records/namespaces/{NS}/search", json={"query": {"inputs": {"text": text}, "top_k": k}}, headers={
"Api-Key": credentials.secret("PINECONE_API_KEY"), "X-Pinecone-API-Version": "2025-04"}).json()
return [h["fields"] for h in r["result"]["hits"]]
@on_event
def handle(event):
t = event.json or {}
text = f"{t.get('subject', '')}\n{t.get('message', '')}".strip()[:2000]
if not text:
return {"skipped": "empty ticket"}
hits = [h for h in search(text, 4)]
kb = "\n\n".join(f"[{h.get('title', 'article')}] {h['chunk_text']}" for h in hits)
draft = ai.generate(f"Draft a friendly support reply using only these articles. If none apply, say 'No matching article.'"
f"\n\n{kb}\n\nTicket:\n{text}", max_output_tokens=400).text
notify.slack(f"🎫 *#{t.get('id', '?')}* {t.get('subject', '')} ({t.get('email', 'unknown')})\n>{t.get('message', '')[:300]}\n"
f"*Draft:*\n{draft}\n_Sources: {', '.join(sorted({h.get('title', 'article') for h in hits}))}_", channel="#support")
return {"ticket": t.get("id")}FAQ
Common questions
Which help desk tools work?
Is the draft sent to the customer?
What if the knowledge base has nothing relevant?
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
Summarise new App Store reviews for your product team in Slack
Each day new App Store reviews are stored in Pinecone and a summary of the main complaints and praise is posted to Slack.
See how it worksGet error alerts with a plain-English explanation
When one of your jobs or systems fails, #ops gets the error and a one-line guess at the cause, without the same error twice in an hour.
See how it worksSend your best leads to sales straight away
Every contact form message is scored, and the promising ones reach #sales while they're still warm.
See how it worksKeep exploring
Set up “Draft answers to new support tickets and share them in Slack” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.