AI-assisted copy critique, editing, and refinement

Quick Rant - I don’t like when I see an AI image in my feed.

I don’t like that I have to zoom in and analyze an image or video to figure out if what I’m looking at is real.

And I don’t love when my clients want to use AI-generated images in their social media or ads.

They all know my opinion on it. 😂

Ultimately, it’s their business and they can do what they want.

But here’s where I sound like a hypocrite:

I LOVE AI.

I use it constantly.

I use it to build project plans and Gantt charts.

Research local events and audiences.

Organize ideas.

Tweak copy.

And my personal favourite?

Writing reports. Because if a robot wants to help me turn 17 tabs of data into something a human actually wants to read, have at it!

The difference for me is where AI sits in the process.

I want AI behind the scenes helping us work faster, research deeper, organize better and get through the tedious stuff.

I don’t want it replacing the human part people actually came to see.

Your face.
Your product.
Your customers.
Your ideas.
Your weird little creative decisions.
Your actual point of view.

Maybe that’s my line with AI:

Let it do the work. Don’t let it become the personality.

I’m actually going to start qualifying new clients this way so we’re aligned.

What’s your take? AI images or nah?

How I actually use AI for content: I write the messy first draft myself - real opinion, real example, real experience.

Then I use AI to tighten it.

Never the other way around.

When AI goes first, the output sounds like AI went first.

When I go first, it sounds like me - just edited.

The order matters more than the tool.

Most marketing teams aren't short of ideas. They're short of time to execute them.

That's where AI has genuinely changed how I work. It doesn’t replace strategic thinking, but it does remove the friction (and bandwidth!) between having a good idea and getting it out into the world.

Here's how I use it to build and maintain a content calendar without it becoming a full-time job:

Start with strategy, not a blank page!
Before prompting anything, I define the themes that matter: what problems our audience is trying to solve, what conversations we want to own, and where we want to show up. AI accelerates the execution. You ABSOLUTELY still have to do the thinking. And you must be deeply prescriptive when setting up the AI project or platform. If you don't. You'll fail.

Turn one insight into many formats
A single strong point of view can become a LinkedIn post, a short article, a talk track for sales, and a question for a survey. AI helps me think across formats quickly. And anyone who knows me will know how I will insist on “sweating an asset”!

Use AI as an editorial sparring partner
I don't just use it to write. I use it to challenge a draft, punch up a headline, or sense-check whether something will actually resonate. It's the fastest way I've found to get from a rough idea to something publishable. Top tip is setting up how you want the tool to respond and giving it a personality and also importantly, making sure it has the right voice for your brand.

Build in advance, stay flexible
Having a week, or more of content shaped ahead of time means you're never scrambling. But the best content often comes from what's happening right now, so the calendar is a foundation, not a fixed map to execute against.

The marketers who will win aren't the ones who post the most. They're the ones who are most intentional about what they say and why.

AI just makes it faster to be intentional.

How are you using AI in your content process? I'd genuinely like to know what's working.

My CMO gave me three weeks to fix a campaign that had a 0.8% click-through rate.

I didn’t hire a consultant. I didn’t run another A/B test. I opened Claude.ai and treated it like the most senior marketing strategist I’d ever worked with.

The campaign hit 4.3% CTR. We added 2,100 leads in 18 days.

This is not a “AI is amazing, go use it” article. This is the actual playbook — the prompts, the frameworks, the mistakes, and the surprising moments when Claude did things no human marketer had thought to suggest.

Been experimenting with AI for marketing over the past year and the biggest shift for me was stopping the one-prompt-one-output approach. Most people open ChatGPT, type something, get something mediocre, and conclude AI is overhyped for marketing. The real unlock is chaining prompts together — using the output of one as the input for the next.

Quick example: I start by having AI interview me about my customer's frustrations (not their demographics, their actual language). Then I use that output to write the ad. Then I run the ad copy through a "devil's advocate" prompt that pokes holes in it before I publish.

The result is copy that sounds like a customer wrote it, not a robot.

I have been doing digital marketing for 12 years and only in the last 18 months has AI genuinely changed how I work at a strategy level, not just a speed level. I am running a live online workshop on March 22 for anyone who wants to see the full workflow in real time.

It is ₹199 and covers four areas: copywriting, competitive research, customer intelligence, and building a repeatable AI system. Recording included. Happy to answer any AI marketing questions in the comments regardless. Let me know if you are interested.

My mom asked me how I use AI at work.

“For everything” wasn’t a very helpful answer. 😅

So I typed up these steps I often go through (this specific list was for creating web pages, but the process is often similar for other deliverables).

Nobody asked except my mom 😉, but here is my process:


WRITING WEB COPY WITH AI

1. Start with my brain: no AI yet
Dig up existing documents on the topic I need to write about, jot down notes that come to mind, review competitor pages, roughly map page structure...

2. Generate a first draft with AI
- Have AI make a “web page copy brief” based on my notes/outline, plus our Domo product positioning doc
- Using that brief, generate a first draft of the page via a Web Copywriter Agent I made
- Go back & forth with the agent to iterate on messaging

3. Switch into research mode with AI
To confirm I’m on the right track, switch gears and use:
- Gemini’s Deep Research Agent for additional market & competitive context
- My own Voice-of-Customer Agent trained on real customer comments

4. Go back and critique the draft with AI
Feed those findings back into the Copy Agent. Ask it to critique the draft against things like market direction, analyst framing, and customer language. Make adjustments accordingly.

5. Critique the draft with humans
Align with PMs and other stakeholders, and refine again.


I find the best outputs come when I alternate between using AI for creation and critique.

I like breaking the project up into several steps, wiping the context between chats, and using my *very own human brain* heavily throughout the process.

It takes more time, but I think it’s worth it. :)


Any other favorite AI tricks I should add to the list? (It’s for my mom, I promise !!)

hese are my current top 5 AI marketing tools that I actually use in my daily workflow:

1. ChatGPT - I use it for general queries, brainstorming ideas, research, and even some basic coding help. It’s kind of my go-to assistant for quick problem solving.

2. Tagshop AI - I use this for generating AI video ads. It saves me a lot of time on video creation and helps me quickly turn ideas into ad creatives.

3. Grammarly - Mainly for grammar correction and polishing my writing. It helps keep emails, posts, and content professional.

4. ElevenLabs - Great for generating realistic voiceovers when I need audio for videos or ads.

5. Claude - I use it mostly for longer content generation and refining drafts when I want something more structured.

Curious what everyone else is using daily, any tools I should try?