Daily

Get daily post drafts in Airtable to review

Each morning fresh drafts on your topics are waiting in Airtable, marked for your review.

Runs: Daily
Apps: Airtable
AI: Yes, uses the built-in AI allowance
Access: data.records:read, data.records:write

Send this to your assistant

Create a ClickRuntime automation: every morning at 7am, take the topics in my Airtable Topics table, write 3 LinkedIn post drafts for each, and add them to my Drafts table with Status set to To review.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A small marketing team, a founder or a creator wants a steady flow of social posts or blog ideas about a handful of topics. Staring at a blank page each morning wastes the best hours. Some weeks the posting stops because there was no time to write, and the audience drifts away. Generating text with a chatbot each time works, but the drafts end up scattered across chat windows and nobody can see which topics were covered or approved.

Every day, the automation reads your topics or source rows from Airtable, asks ClickRuntime's built-in AI to write a draft for one, and creates a record in a review table with a status of Draft. It marks the topic as used in its state, so the same topic is not drafted again tomorrow.

It suits people who want a regular content pipeline but still want a human to approve every post before it goes out.

What you get out of it

There is always something to review
A fresh draft waits each morning, so the calendar does not go blank. Posting stays consistent even in weeks when nobody had time to brainstorm. A steady rhythm matters more than occasional bursts to most audiences.
Nothing is published without approval
Drafts land in a review table with a status. Your team edits, approves or rejects each one, so the AI is a first writer and a person keeps control of what goes out.
All drafts are in one place
Airtable becomes the content hub: topic, draft, status and publish date side by side. You avoid hunting through chat history to find a post you remember. Without that, the same favorite topics tend to get all the attention.
Topics are covered evenly
Because each topic is marked as used, the pipeline works through your list instead of repeating the first one. That gives a balanced mix across the subjects you care about.
Editing is faster than writing
Improving a decent draft takes minutes compared with starting from nothing, so a single editor can keep several channels supplied. One person can keep a content calendar full without writing every post from nothing, which matters when you are a team of one.
Your approval history becomes a style guide
Seeing which drafts you approved and which you rejected shows what your voice is. That helps you refine the instructions so later drafts need less editing. Drafts stay on voice over time.

How it works

What happens, step by step

Every morning, ClickRuntime picks the next topic from your list of topics in Airtable.
AI writes a few post drafts on that topic.
Each draft is added to your Drafts table with the status "To review".
The topic is marked as used, so tomorrow's drafts cover something new.

Before it runs live

Connect Airtable

What you get

RunsDaily

Get daily post drafts in Airtable to reviewtoday, 9:00Succeeded

Airtable · Drafts"Why we stopped sending weekly status emails" · Status: To review · 3 drafts for topic Async work

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

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 Airtable 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.

generate_ai_content_drafts_into_a_review_table.pyexample

from datetime import date
from clickruntime import on_trigger, credentials, http, ai, state

BASE_ID = "appXXXXXXXXXXXXXX"
SCHEMA = {"type": "object", "properties": {"posts": {"type": "array", "items": {"type": "string"}}}}

@on_trigger
def run(event):
    api = f"https://api.airtable.com/v0/{BASE_ID}"
    headers = {"Authorization": f"Bearer {credentials.connection('airtable', 'work')}"}
    topics = http.get(f"{api}/Topics", headers=headers).json()["records"]
    used = set(state.get("used_topics") or [])
    created = 0
    for topic in [t for t in topics if t["id"] not in used][:5]:
        posts = ai.generate(f"Topic: {topic['fields'].get('Topic', '')}",
                            system="Write 3 distinct LinkedIn post drafts, under 150 words each.",
                            json_schema=SCHEMA, max_output_tokens=900).json["posts"][:3]
        records = [{"fields": {"Topic": topic["fields"].get("Topic"), "Draft": p,
                               "Status": "To review", "Date": date.today().isoformat()}} for p in posts]
        http.post(f"{api}/Drafts", headers=headers, json={"typecast": True, "records": records}).raise_for_status()
        used.add(topic["id"])
        created += len(records)
    state.set("used_topics", sorted(used))
    return {"drafts": created}

FAQ

Common questions

Does it publish the drafts to social media?

No. It only creates draft records for review. Publishing is a separate step, so nothing leaves your base until a person has approved it and moved it on. You can copy approved drafts into the tool you use for scheduling.

How do I tell it what tone to use?

Describe the tone, audience and length in the instructions, for example friendly, aimed at small business owners, under 80 words. Examples of past approved posts help the AI match your style. A few approved examples are the quickest way to teach it.

What happens when all topics are used?

The automation can stop and email you to add more, or start the list again after a set number of days. Choose whichever fits how often your topics should repeat. Either option keeps the pipeline from quietly repeating itself.

What permissions does it need?

data.records:read, data.records:write. 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 each time it runs (daily). Checks that find nothing to do and stop right away aren't counted.

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.

On a scheduleAI