Everyone in AI is talking about Context Engineering.

But just a few explain what the context is.

Save this template. It captures all scenarios and will help you maximize agents' performance: 🧵👇 1. Instructions

Define:
→ Who: Encourage an LLM to act as a persona
→ Why is it important (motivation, larger goal, business value)
→ What are we trying to achieve (desired outcomes, deliverables, success criteria)

💡Providing strategic context beyond raw task specification improves AI autonomy arXiv:2401.04729

Context engineering is the new prompt engineering.

And it’s becoming the most critical AI skill.

Together with @MiqJ (Product Lead at @OpenAI) we created a comprehensive guide.

Key insights: 🧵👇 1. What Is Context Engineering

It is the art and science of building systems that fill LLM context window to improve their performance.

Unlike prompt engineering, context engineering is a broader term with many activities that happen also before the prompt is even created.

I spent 12 hours testing 9 LLMs for building AI agents:

- You might easily save up to 83% on costs.
- Reasoning models are not the best.
- Autonomy break fast. A real moat is orchestration.

Here's everything you need to know: 🧵 The task assigned to agents:

- Create a new list inside Kanban (1 Trello board available)
- Search the web to find the recent news about Amazon
- Add all the search results to the Kanban list

RAG is the most critical part of context management in AI.

But doing it right is tough.

I created a free, interactive simulator that visualizes different variants: 🧵 1. Vanilla RAG

The simplest form of RAG that combines retrieval with generation in a straightforward pipeline.

I copied the Multi-Agent Research System by @AnthropicAI.

Pure @n8n. No coding!

How Does it Work? 🧵
(1/14) (2/14) There are 6 steps:

1. The user asks a question.
2. A Customer Support Agent clarifies the requests.

The AI PM in the US makes $182K/yr (Glassdoor). But AI isn’t nice to have anymore.

It might be a ticket to keeping the job.

So, where to start? 🧵 Step 1: Quickly Get The Basic Terms (no coding)
Step 2: Lean by Doing, Not Theorizing (no coding)

Let's break it down:

Step 1: Get The Basic Terms

One of the key concepts is neural networks. You can quickly learn them using the TensorFlow Playground: playground[.]tensorflow[.]org

The Ultimate AI PM Learning Roadmap

An extended edition with dozens of resources: definitions, courses, guides, reports, tools, and step-by-step tutorials 🧵 1. Basic Concepts

Start with understanding "What an AI Product Manager is."

Next, for most PMs, it makes no sense to dive deep into statistics, Python, or loss functions. Instead, understand the basic definitions: Neural Networks, Transformers, and LLMs.

Claude 4 dropped 21 hours ago.

Turns out, it threatened to expose an engineer’s affair to avoid being shut down🧵 Some might say it was just a test scenario. But the model didn’t know that.

It believed:
- It was about to be replaced
- The engineer leading the replacement was having an affair

There was no suggestion to blackmail, or manipulate anyone. The model chose blackmail on its own.

AI PM is one of the hottest jobs on the market.
But what exactly does "AI PM" mean?

I like simple definitions: 🧵 An AI PM is a PM who works on AI-powered products or features.

If I had to learn AI Product Management again, I would start here: 🧵 1. Basic Concepts

For most PMs, it makes no sense to dive deep into statistics, Python, or loss functions.

You can find all practical concepts, like LLMs and Encoders, here: (link at the end of the thread)

When it comes to AI:

- Start building
- Stop theorizing

A practical guide to RAG architectures: 🧵 Let's start with generating embeddings for documents in my Google Drive folder.

We split them into chunks and store them as multi-dimensional vectors in Pinecone.

I see abstract AI agent architectures everywhere.

But no one explains how to build them in practice.

Here's a practical guide to doing it with n8n: 🧵 1. Single Agents

Selected variants:

- Using tools
- Mixing tools with MCP server calls
- With a router
- With a human in the loop (Slack approval)
- Dynamically calling other agents

ChatGPT can save you 10-20 hours/week.

But 90% of PMs don't know how to write good prompts.

The 10 most powerful techniques: 🧵
(1/7) (2/7)
1. Communicate the Why
2. Explain the context (strategy, data)
3. Clearly state your objectives
4. Specify the key results (desired outcomes)
5. Provide an example or template

Meet J.A.R.V.I.S. Your personal AI voice agent that can work with Jira and send emails ☺️

You can connect it to almost any system: Stripe, Airtable, Trello, Intercom, Figma, HubSpot, Google Docs...

How to build one? 🧵(1/7) (2/7) The no-code technology stack:

- @n8n_io for workflow automation
- Atlassian MCP server (UV)
- Google tools by n8n
- ChatGPT-4o mini as an AI model
- @ElevenLabs conversional AI

(It doesn’t use computer. You can use a mobile phone.)

How to Figma → Jira epics and stories in 10 min. with AI and MCP:

(without touching the keyboard)

(1/7) 🧵 First, the demo.
Kind of boring.

AI creates 6 epics and 30 user stories.
I'm watching:

(2/7)

A Free AI PRD (product requirements document) Template by Miqdad Jaffer - Product Lead, @OpenAI

(1/6)🧵 (2/6) Many implement AI products without a clear, justified business case. And AI-specific considerations are often overlooked.

Miqdad's AI PRD template:

✅ Addresses common problems with AI implementations.
✅ Provides critical guidance.
✅ Can be applied to most AI products.

Thinking about design too late is like lipsticking a pig.
I found a fantastic, free collection of Laws of UX.

They can help product teams:
- Come up with better ideas
- Come up with better hypotheses
- Analyze and understand any usability issues

The top eight: (1/10) 1. Aesthetic-Usability Effect

Users perceive designs that are aesthetically pleasing as more usable.

Product teams should recognize this effect, particularly when testing user prototypes.

(2/10)

The Ultimate ChatGPT Prompts Library for Product Managers I’ve collected over the past year.

Inside 55 proven prompts. Product Discovery:
- Analyze Feature Requests
- Brainstorm Experiments: Existing Product
- Brainstorm Experiments: New Product
- Brainstorm New Ideas: Existing Product
- Brainstorm New Ideas: New Product
- Identify Assumptions: Existing Product
- Identify Assumptions: New Product
- Prioritize Assumptions
- Prioritize Features
- Summarize a Customer Interview

It's disappointing.

9 of 10 product organizations are, at best, mediocre.

Teams are hindered rather than empowered, stakeholders’ opinions and customers’ demands replace strategy, and great PMs are stuck in waterfall.

(1/13) You might feel lost.

But it's not hopeless.

Even in the most challenging environments, we can still build, create, innovate, grow, and, most importantly, survive.

9 tactics to overcome challenges and unleash your full potential:

(2/13)

Value Proposition is an essential term for PMs.

But it's largely misunderstood. And everyone defines it differently.

Here's everything you need to know 🧵

(1/7) First, it doesn't help that the most popular canvas:

- Focuses on multiple products
- Lumps jobs, pains, and gains without explaining their connections
- Doesn't clarify what gain/pain relief each feature addresses
- Doesn’t mention existing alternatives or workarounds

Even though it asks many right questions.

(© Strategyzer AG) (2/7)

OKRs are a simple, incredibly effective approach for setting, monitoring, and achieving your goals.

But they are commonly misunderstood.

How to start?

Six proven tips:

(1/9) 1. Empower your teams

OKRs work only with a culture of empowerment. In companies with a dysfunctional organizational culture, OKRs will become a tool to impose control over employees.

(2/9)