
VP Product @saviynt, Vibe PM, Product Engineer
Joined December 2008
- Tweets353
- Following130
- Followers8K
- Likes343
English as a programming language is the reality today using @Lovable and other tools. It's amazing to be able to launch a database backed website with SSO using just English, which I did for the first time 6 months ago! Try it out if you haven't already!
The most powerful programming language of the future isn’t C++ or Python. It’s English.
Jensen Huang: “Why program in Python? So weird.”
You won’t write code anymore. You’ll describe what you want. If the result isn’t right, you won’t debug. You’ll just tell it to fix itself.
The barrier to controlling computers is hitting zero.
We’re shifting from syntax to intent. You don’t need to know how to write a script to modify a system. You need to know how to explain what should happen.
Huang: “English is the best programming language of the future.”
Prompt engineering is just clear communication with a new audience. How you talk to people and how you talk to machines is becoming the same competency.
If you can articulate what you need clearly, you’re a developer. If you can refine through conversation, you can ship products.
The coder is obsolete. The orchestrator is everything.
The skill isn’t syntax anymore. It’s clarity. Knowing what to build, how to ask for it, and how to direct until it’s exactly right.
Claim your Dinq @dinq_me profile. Don't get surprised if you're roasted 😅
analysis.dinq.me/github?user…
#GitHub #developer
If your purpose literally is coding, somebody tells you what to do, you code it, maybe you're going to get replaced by the AI, but most of our software engineers, all of our software engineers. Their goal is to solve problems.
Better prompts and multi-agent teams help. We just need to make them more ubiquitous.
Replying to @levie
There's also a trust overhang. Most people (devs) have tried chatgpt, hit a hallucination and mentally filed it away. Better models help, but what really makes a difference is agents that stop and ask instead of confidently plowing ahead with wrong assumptions.
100% - it's much more software architecture for me than coding for me now, but still engineering.
AI coding tools are incredible at starting projects.
But finishing them still breaks down at:
• QA
• Docs
• Security
• Release coordination
The AI-start / human-finish gap is real.
Here’s my 6 agent team to help in @AnthropicAI Claude Code! 👇
github.com/grokify/release-a…
@claudeai can use git branches which would be a standard way of saving changes locally before merging to the origin and/or main.
Replying to @TanayLohia1 @claudeai
The 'Code Restore Point' can simply be automatic git commits, like Google Docs. @lovable automatically makes multiple git commits so it's already been thought about there. Perhaps we just need more of this, along with database backups.
Replying to @levie
All PMs need to vibe code now. This is not new. This is just the next evolution of wireframes, allowing PMs to express their thoughts.
The next step is to have the prototypes use production approved tech stacks.
John Wang retweeted
agents are just "llm + loop + tools"
I spent time breaking down a web-enabled coding agent and realized most of the complexity is optional
here's what I learned 👇
100%! Many Product Managers already come from Engineering so it's an important skill set they already have Vibe Coding makes it much easier to use. My PM team is Vibe Coding and I'm looking to align this with production tech stacks now.
#VibeCoding #ProductManagement
John Wang retweeted
We are adding a coding section to all of our Product Managers interviews at @Shopify.
We'll start with APM interviews. We expect candidates to build a prototype of the product they suggested in the case interview.
There is no excuse for PMs not building prototypes.
John Wang retweeted
I've been in crypto for over 10 years and I’ve Never been hacked. Perfect OpSec record.
Yesterday, my wallet was drained by a malicious @cursor_ai extension for the first time.
If it can happen to me, it can happen to you. Here’s a full breakdown. 🧵👇
Replying to @svpino
It depends on how good you are at cleaning it up and getting it to do what you want the first time around.
For some of my vibe coding projects, the path is: Vibe > Compile > Test (Yay!) > git commit > Add pipeline scans > Fix findings > Review code > Profit!
Replying to @mukeshbansal06
Agree fast adaptation is necessary. I just vibe coded another MCP server today. More than creating the server, it's the mindset that my AI agent needs a tool, so let's build one and move on.
The world has changed and getting in early will let you ride the wave.















