Jesal Gadhia
@jesalg
Followers
896
Following
8K
Media
116
Statuses
2K
Engineering Leader | Building Something New | Prev @thoughtful_ai @BetterUp
Los Angeles
Joined February 2009
So well put. Small teams win on shared context, not a zoo of services. Mothership & shuttles are the way to go: One codebase where everyone can reason end-to-end. Async and bursty work is offloaded to functions that run on serverless runtimes. Ship a great monolith first. Earn
Microservices is the software industry’s most successful confidence scam. It convinces small teams that they are “thinking big” while systematically destroying their ability to move at all. It flatters ambition by weaponizing insecurity: if you’re not running a constellation of
0
0
1
"Why should companies pay for SaaS (HR/CRM/ERP/etc.) when they could just vibe code them?" I get variations of this question or comment with some regularity (granted, it's sometimes just me talking to myself). Here are some biased (but hopefully, well-considered) thoughts: 1)
210
174
1K
We’re starting to get a clearer sign of how vast the surface area of context engineering is going to be. To build AI agents, in theory, it should be as simple as having a super powerful model, giving it a set of tools, having a really good system prompt, and giving it access to
121
121
899
The counter dynamic to the AI model doing everything is that, at least in enterprise, bridging the AI models’ capabilities to the customer’s environment still requires a tremendous amount of long tail work. The gap between an AI agent working for 90% or 95% of the solution and
My AI investment thesis is that every AI application startup is likely to be crushed by rapid expansion of the foundational model providers. App functionality will be added to the foundational models' offerings, because the big players aren't slow incumbents (it is wrong to
56
70
472
Wondering what 500+ eng leaders are doing about team performance, metrics, and AI upskilling? We’re unpacking @TheLeadDev’s 2025 report tomorrow with @OReillyMedia. 🗓️ Wed Oct 22 · 9am PT / 12pm ET 🔗 https://t.co/GPzmCac4cr Come join the discussion!
leaddev.com
Join us to learn why 500 engineering leaders still find measuring team performance a major challenge.
0
0
2
If you buy an expensive camera, your photos will suck as much as before. If you buy an expensive golf club, you won't start swinging 300-yard bombs overnight. It's not the tools. It's the person using them. Building good software has nothing to do with whether you use Claude
62
45
444
Software Engineers are not paid for writing code. They’re paid for solving problems. The faster you accept this, the better your life and career will be.
477
2K
17K
Building software is only 10% about writing code, and 90% about thinking what code to write, why you should write it, and how to do it well. You can delegate the code-writing part to an LLM, but so far, they have shown they can’t handle the thinking part. It’s called
Vibe-coders can’t build the type of software $400,000/year salaries pay today. If you believe companies pay that money to build vibe-code-able apps, you should crack a book and get off Twitter.
141
136
2K
Major life cheat code: Taking radical ownership of your outcomes. High performers don't blame secret forces, unclear direction, or market conditions. They create their reality through relentless action. Stop inventing reasons you can't and you'll start finding ways that you can.
9
10
141
The AI bull case is that we’re only scratching the surface of what AI agents are going to be capable of, and even the ones that are out there only represent a small fraction of what’s to come. Starting with the most mature ones. The vast majority of engineers using AI for coding
The AI bullcase is pretty easy: API calls/tokens are going to multiple exponentially => revenue for the top 3 models + model lock in will be more apparent especially as agent workflow such as the one OAI announced takes shape. The models dont even need to be multiples better from
59
50
390
OpenAI dropping Agent Builder today is either going to make you rich or expose that you've been selling hot air. I went deep analyzing what this actually means. Here's the $4B opportunity hiding in plain sight: The mainstream narrative: "Agent Builder democratizes AI! Anyone
the rumor is openai drops “agent builder” tomorrow and wow, if that's true thats a BIG DEAL for the 12 months, people have been stitching together tools like n8n, zapier, make, vapi, and claude workflows to simulate autonomy. it worked but it was duct tape. now IMAGINE that
52
107
2K
The biggest drain on your team isn't the impossible challenges. It's the people who turn simple tasks into complex ones. Keep the simplifiers. Avoid the complicators. It's not easy to spot, often the complicators are seen as having a great attention to detail & high care. But
9
34
446
Founders overrate vision and underrate taste. Taste is what stops you from building junk. Taste is what helps you say no to the wrong users, the wrong hires, the wrong metrics.
29
61
431
If you want to do deep research, go to a frontier AI company. If you want to do verticalized AI, go to a startup. Why? Big tech companies offer: - Boundless capex for high compute clusters - Dedicated teams for maintaining these clusters - Massive internal datasets and the
0
2
8
đź’Ż We have already deployed background agents that are doing this for various post sales workfows
The paradigm of background agents, like we've seen in AI coding, will start to arrive in all areas of knowledge work. Most areas of work have similar dynamics as AI coding agents, where it makes sense to send off a request, check in on progress or get pinged with
1
0
2
Better to build slowly on truth than quickly on trends.
95
245
2K
Well said. Working on this problem!
Context engineering is increasingly the most critical component for building effective AI Agents in the enterprise right now. This will ultimately be the long pole in the tent for AI Agents adoption in most organizations. We need AI Agents that can deeply understand the context
0
0
2
What a privilege to be tired from work you once begged the universe for. what a privilege to feel overwhelmed by growth you used to dream about. what a privilege to be challenged by a life you created on purpose. what a privilege to outgrow things you used to settle for.
74
5K
23K