Daily
Get a daily digest of a playlist's new videos
New additions to a playlist are summarised in one email so you know which to watch.
- Runs
- Daily
- Apps
- YouTube
- AI
- Yes, uses the built-in AI allowance
- Access
- youtube.readonly
Send this to your assistant
Create a ClickRuntime automation: every day at 7am, summarise the videos added to my 'Research' playlist in the last day and email me.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
Playlists are often used as reading lists. A team follows a conference playlist with forty talks, a student follows a lecture series, a founder follows a competitor's channel playlist. New videos get added at random times, and unless someone opens the playlist, they go unnoticed for weeks, long after the topic was timely.
Every day, the playlist is checked, and videos added since the previous run are identified using stored state. ClickRuntime's built-in AI writes a short summary of each from its description, and one email lists the new videos with their summaries and links.
People tracking a conference, a course or a research topic on YouTube will find it a good way to keep up without watching everything. The email lets a busy person keep up with a series without opening YouTube.
What you get out of it
New videos are noticed quickly
A daily email means you hear about a new talk the day it appears, which matters when the topic is current or the content is time-limited. Early awareness is what makes a conference talk or a news video still useful.
You decide what is worth watching
A two-sentence summary helps you choose between a 90-minute keynote and a 10-minute demo, so your viewing time goes to what is useful. Choosing well saves hours, because most people cannot watch everything that gets posted.
Teams can share one digest
Forwarding the email gives everyone the same list, so colleagues do not each have to watch the playlist or hear about videos second-hand. A shared email keeps the group on the same page without another meeting.
It works for other people's playlists
You do not need to own the playlist, so you can follow a conference or a competitor's curated list without subscribing to the entire channel. That makes it a quiet way to track a competitor's published series.
Nothing repeats
Stored state ensures each video appears in one digest only, so you can trust that every item in the email is genuinely new. Because each video appears once, you never wonder whether you already read about it.
How it works
What happens, step by step
Once a day, ClickRuntime checks the YouTube playlist you chose for videos added since the last check.
It skips any video it has already told you about.
AI reads each new video's description and writes one line on what it covers.
You get one email with the numbered summaries and the links, so you can pick what to watch.
Before it runs live
- Connect YouTube
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
- 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 YouTube steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_trigger, credentials, http, state, ai, notify, report_fetched
YT = "https://www.googleapis.com/youtube/v3"
PLAYLIST_ID = "PLxxxxxxxx"
@on_trigger
def run(event):
h = {"Authorization": f"Bearer {credentials.connection('google', 'work')}"}
items = http.get(f"{YT}/playlistItems", headers=h, params={"part": "contentDetails", "playlistId": PLAYLIST_ID, "maxResults": 50}).json()["items"]
seen = state.get("seen") or []
new = [i["contentDetails"]["videoId"] for i in items if i["contentDetails"]["videoId"] not in seen]
report_fetched(len(new))
if not new:
return {"summary": "Nothing new"}
videos = http.get(f"{YT}/videos", headers=h, params={"part": "snippet", "id": ",".join(new)}).json()["items"]
text = "\n\n".join(f"{i}. {v['snippet']['title']}\n{v['snippet']['description'][:800]}" for i, v in enumerate(videos, 1))
summary = ai.generate(text, system="For each numbered video, write one line on what it covers.", max_output_tokens=500).text
links = "\n".join(f"https://youtu.be/{v['id']}" for v in videos)
state.set("seen", (seen + new)[-1000:])
notify.email_me(f"{len(videos)} new in your playlist", f"{summary}\n\n{links}")
return {"new": len(videos)}FAQ
Common questions
Does it summarise using the video's captions?
What if no videos were added that day?
Can it watch more than one playlist?
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
Find the videos taking off in your niche
Each Monday you see which recent videos on your topic or from rival channels beat their usual views, with a note on why.
See how it worksGet a daily summary of new comments
Each day you read what viewers said in a few lines, plus the questions worth answering.
See how it worksTurn viewer comments into video ideas
Once a month you get the themes viewers keep raising and a list of videos you could make next.
See how it worksKeep exploring
Set up “Get a daily digest of a playlist's new videos” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.