Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Millie Marconi

Aug 26 • 14 tweets • 4 min read • Read on X

If you're not getting incredible results from AI, the problem isn't the AI.

It's your prompts.

These 4 frameworks fix that problem permanently.

Here're the frameworks I use (Steal them):

Today, most people prompt like this:

“Write me a marketing plan for my product.”

And then they wonder why the result feels vague, boring, and unusable.

The problem isn’t AI.

It’s your approach.

AI is like an engine.

Your prompt is the steering wheel.

But without a framework, you’re just spinning it randomly.

Frameworks turn prompting into a repeatable system.

Let’s break down 4 of the best: 👇

1. APE Framework

APE = Action → Purpose → End Goal

Instead of:

“Write a LinkedIn post.”

Use APE:

“Write [Action: a LinkedIn post] [Purpose: to explain AI frameworks simply] [End Goal: so readers feel confident to try them today].”

Result? Clear. Targeted. Useful.

2. PECRA Framework

PECRA = Persona → Example → Context → Request → Adjustments

Example prompt:

“You are a productivity coach.
Show me 3 examples of AI frameworks.
Context: audience = beginners.
Request: keep it under 200 words.
Adjust: make it friendly + engaging.”

PECRA = consistent precision.

3. OSCAR Framework

OSCAR = Objective → Scope → Constraints → Action → Reflection

Example:

“Objective: Create a study plan.
Scope: 30 days, 1 hour/day.
Constraints: for a working professional.
Action: Build week-by-week schedule.
Reflection: Suggest improvements.”

You don’t just get answers → you get refined answers.

4. TAG Framework

TAG = Task → Audience → Goal

Example:

“Task: Write a newsletter.
Audience: busy founders.
Goal: Explain why prompt frameworks matter in under 300 words.”

AI now knows what, who, why.

That’s the difference between fluff and focus.

Notice something?

All these frameworks do the same thing:
They give AI structure.

And when you give AI structure → it gives you outputs that feel human, specific, and valuable.

Frameworks also make AI work for you at scale:

Want 20 tweets? Use PECRA.
Want research with critique? Use OSCAR.
Want copy tailored to an audience? Use TAG.
Want clarity in goals? Use APE.

No more “re-rolling” prompts endlessly.

AI is powerful.

But raw power without a framework = chaos.

Once you learn to prompt with frameworks, AI goes from:

❌ hit-or-miss toy → ✅ predictable partner.

The best part?

You don’t need to memorize 100 prompts.

You just need a few frameworks you can apply to any situation.

That’s how pros get unfair results while everyone else struggles.

Prompt frameworks are the difference between “AI feels mid” and “AI feels magical.”

Start with these 4:

1. APE
2. PECRA
3. OSCAR
4. TAG

Master them → and AI will finally deliver shockingly good outputs.

Here's what I'm building for you...

Most people publish and hope their content resonates.

TestFeed flips that...it shows you exactly how your audience will respond before you ever hit publish.

👉 Join the waitlist here: testfeed.ai

https://twitter.com/1909092495734235136/status/1960280423592014221

I hope you've found this thread helpful.

Follow me @Yesterday_work_ for more.

Like/Repost the quote below if you can:

https://twitter.com/1909092495734235136/status/1960280423592014221

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @Yesterday_work_

Millie Marconi

@Yesterday_work_

Aug 20

If you’re building or investing in AI and don’t understand agents… you’re flying blind.

Here’s your shortcut: 10 core concepts every founder should know:

1/ Agentic AI

This is AI that doesn’t just answer questions it gets shit done.

Basically, It can plan, make decisions, and act without you babysitting it.

Think of the difference between asking a human for advice…

And having someone who actually takes the action for you.

2/ Agent

The basic unit of Agentic AI.

An agent is a piece of software that can see what’s going on, think about it, and do something to reach a goal.

Example: an ecommerce agent notices a product is almost sold out, checks sales data, and automatically places a reorder.

Read 12 tweets

Millie Marconi

@Yesterday_work_

Aug 19

R.I.P McKinsey.

You don’t need a $300k consultant anymore.

You can now run full competitive market analysis using ChatGPT, Gemini, and Grok deep research features.

Here are the exact 3 mega-prompts I use to replicate McKinsey-style insights for free:

Let me tell you what McKinsey consultants actually do:

1. Analyze industry trends and competitive dynamics
2. Benchmark companies and products
3. Identify strategic risks and opportunities
4. Package it all in fancy slides and charge 6 figures

But guess what?

AI can now do 90% of that instantly.

Let me show you how:

We use these 3 mega prompts for different tasks:

1/ The Consultant Framework

Prompt: "You are a world-class strategy consultant trained by McKinsey, BCG, and Bain. Act as if you were hired to provide a $300,000 strategic analysis for a client in the [INDUSTRY] sector.

Here is your mission:

1. Analyze the current state of the [INDUSTRY] market.
2. Identify key trends, emerging threats, and disruptive innovations.
3. Map out the top 3-5 competitors and benchmark their business models, strengths, weaknesses, pricing, distribution, and brand positioning.
4. Use frameworks like SWOT, Porter’s Five Forces, and strategic value chain analysis to assess risks and opportunities.
5. Provide a one-page strategic brief with actionable insights and recommendations for a hypothetical company entering or growing in this space.

Output everything in concise bullet points or tables. Make it structured and ready to paste into slides. Think like a McKinsey partner preparing for a C-suite meeting.

Industry: [INSERT INDUSTRY OR MARKET HERE]"

Read 10 tweets

Millie Marconi

@Yesterday_work_

Aug 16

MCP is one of the most important things to learn right now.

• powers next-gen AI workflows
• core to building useful agents
• rapidly becoming industry standard

Here’s the complete roadmap I followed to learn it in 30 days:

Most people still have no idea what MCP is.

Model Context Protocol is the missing layer between LLMs and tools.

It’s how you make an AI agent:

• Talk to any API
• Use any tool
• Do it safely & consistently

Why you should care:

Without MCP, you’re relying on brittle hacks custom integrations, prompt tricks, and API glue code.

With MCP, you get a standard way to define tools, call them from any model and scale without rewriting everything.

Read 13 tweets

Millie Marconi

@Yesterday_work_

Aug 1

you don’t need a cofounder anymore

ChatGPT, Claude, and Gemini will now:

• analyze your skills
• scan market gaps
• return scalable startup ideas

this prompt is pure gold (steal it now)👇

Traditional idea generation is broken.

You either:

- scroll Twitter for hours
- copy what’s trending
- wait for “founder inspiration” to strike

Now?

You just tell an LLM what you’re interested in and it does the rest.

Here’s what it can give you:

- Business ideas tailored to your skills
- Trend-backed opportunities
- Pain-point-based products
- Ideas based on AI, SaaS, ecom, B2B, or niche industries
- Monetization breakdowns and GTM plans

Here’s the exact mega prompt we use:

"You are a world-class entrepreneur, market analyst, and product strategist.
Your task is to generate 10 startup ideas based on my input.

For each idea, include:

– A 1-sentence elevator pitch
– Target user or customer segment
– Key pain point it solves
– Monetization method
– Unique angle or moat

Make the ideas specific, creative, and executable.
Ask follow-up questions to refine if needed."

Read 7 tweets

Millie Marconi

@Yesterday_work_

Jul 31

What is an AI agent?

The most misunderstood concept in tech right now.

Everyone’s using the term, but few know how they actually work.

Here’s the real breakdown (plus 10 tools to build your own):

1. What is an AI agent?

Think of it as an LLM that doesn’t just respond but acts.

It can:

- Decide what to do
- Use tools
- Manage its own workflow
- And iterate toward a goal autonomously

You’re not building a chatbot. You’re building a co-worker.

2. Agent ≠ Workflows

Workflows are predefined paths. Agents are adaptive.

Workflows follow a script.

Agents write their own steps in real time.

The difference?

One executes instructions.

The other thinks, decides, and acts.

Read 10 tweets

Millie Marconi

@Yesterday_work_

Jul 30

WOW… your messy notes can now turn into mind maps automatically

Fluig AI just dropped a tool that turns scribbles into diagrams, tables, and flowcharts

visual thinkers are gonna love this

Fluig Al swiftly transforms your ideas into mind maps, flowcharts, cards, tables, timelines, fishbone diagrams, and even code.

Think faster, organize information visually, and inspire clearer, more creative thinking.

Fluig AI helps you turn any documents or creative ideas into clear, professional diagrams quickly, and you can change the diagram format with just one click!