The amount of money all of us startups spend on AI agents is crazy!!!

.@levie says a lot of productivity was rate-limited by how fast someone could use a computer. But once that’s no longer the constraint, jobs start to change. “Your job is now orchestration, integration of work, planning, task management, reviewing, auditing.” The individual contributor becomes a manager of agents.

the best moat at the pre-seed stage is speed

believe in somETHing

Imagine if gas stations didn't tell you how many gallons you were getting. The station built your car, but you can't look under the hood. That's the inference subscription dilemma in one image, and the reality of selling commodities on subscription models. 🧵

Context Engineering is the most important piece of making AI agents work for you but losing context repeatedly is frustrating. Problems: Using AI IDEs like Cursor or ClaudeCode, you carefully brief your project, but the next day, the session starts fresh, and you must re-explain everything. In team settings, past interactions and lessons like best practices and bug fixes remain siloed. Your colleagues' agents repeat mistakes since this knowledge isn't shared. Fixed rules like Cursor rules or a aren't enough for large codebases. Switching from one IDE (Cursor) to another (ClaudeCode, Gemini CLI) means losing all context.

AI agents with a human touch are way better than general agentic systems that try to automate everything. The human touch happens at phases like prompt design, context engineering, agent architecture, and, more importantly, evaluation. Domain expertise matters so much.

I’m excited to finally launch this. My MCP server now offers real-time stock market news. Available tools: • get news • get stock prices • get key metrics • get financial statements Took about a month to get the MCP server right, but it's working well now. More financial tools coming soon.

MCP is getting so good!

What is context engineering❓ And why is everyone talking about it...👇 Context engineering is rapidly becoming a crucial skill for AI engineers. It's no longer just about clever prompting; it's about the systematic orchestration of context. 🔷 The Problem: Most AI agents fail not because the models are bad, but because they lack the right context to succeed. Think about it: LLMs aren't mind readers. They can only work with what you give them. Context engineering involves creating dynamic systems that offer: - The right information - The right tools - In the right format This ensures the LLM can effectively complete the task. 🔶 Why Traditional Prompt Engineering not enough: Early on, we focused on "magic words" to coax better responses. But as AI applications grow complex, complete and structured context matters far more than clever phrasing. 🔷 4 Key Components of a Context Engineering System: 1️⃣ Dynamic Information Flow Context comes from multiple sources: users, previous interactions, external data, tool calls. Your system needs to pull it all together intelligently. 2️⃣ Smart Tool Access If your AI needs external information or actions, give it the right tools. Format the outputs so they're maximally digestible. 3️⃣ Memory Management - Short-term: Summarize long conversations - Long-term: Remember user preferences across sessions 4️⃣ Format Optimization A short, descriptive error message beats a massive JSON blob every time. 🔷 The Bottom Line Context engineering is becoming the new core skill because it addresses the real bottleneck: not model capability, but information architecture. As models get better, context quality becomes the limiting factor. I'll share more as things evolve and become more concrete! Stay tuned!! 🙌 ____ If you found it insightful, reshare with your network. Find me → @akshay_pachaar ✔️ For more insights and tutorials on LLMs, AI Agents, and Machine Learning!