funnyfoobar

Working on https://getAiNative.com

I kept seeing the same thing across engineering teams: everyone bought Copilot or Cursor seats, people used it for a few weeks, and then output didn't really change.

The tooling is good but teams are treating AI like autocomplete instead of integrating it into how they actually ship code.

My take is that AI starts making a real difference when you apply the same discipline you already have for software engineering.

Plan the work, implement, write tests, commit, open a PR, get it reviewed. If you just vibe code with no structure around it, you get messy diffs and hallucinated tests that nobody trusts.

So I'm building around that workflow. Think of it as giving AI the guardrails of your existing eng process.

I have been using AI workflows at work to increase the productvity. I have shared these workflows internally and at a couple of tech meetups I went to. I got positive response.

Some of these are present here: https://github.com/vamsipavanmahesh/claude-skills/

Planning to package this as a workshop, so companies could be benefit from AI Native SDLC.

Put together the site yesterday https://getainative.com

Couple of the people I have worked with in the past agreed to meet me for a coffee, will pitch this. Fingers crossed.

Original author here: These skill have been adding a lot of value in very less time. After debugging a knarly bug for 4 hours, you might be exhuasted to explain in it a good way, this helps with that.

I have replied to a comment adjacent to yours, for my parent comment. Please check i think if you follow the "process", it is avoidable.

To be honest, what you have described only shows lack of process.

I am not talking about vibe coding here, which is totally different and understandable. But I am talking about the professional context where the structure is already in place.

Here is my workflow, if it helps:

1. I have a system level prompt i execute(command/skill) before I start anything which says things like

    i) follow SOLID principles
    ii) follow TDD
    iii) follow these testing principles like, don't test the implementation details etc
    and 20 other things

2. I give it the context of what I need to accomplish, and toggle the plan mode ask it follow the above things I have set at system level, and generate me a document to review step by step

3. I review everything, add feedback to the generated plan, prompt again, and finally finalize the plan

4. now that the plan is finalized, I would have a small alignment with co-workers and ask it implement step by step, and then before proceeding with next step, i will tell it to ask me for feedback

each steps code is reviewed and commited, before proceeding to next step

5. once all steps are done, manual testing is done, i do a local review

6. I have a specific skill which reviews everything, and gives me feedback

7. we have human reviewers who will review the code, and coderabbit

8. then we take it to the staging and uat before taking to prod

so see we have not skipped any process of "software engineering", claude code is just an accelrant

but if you are not doing most of the above steps, i see what you are saying would happen by default

What you are saying may have made sense at the start of 2025 where people were still using github copilot tab auto completes(atleast I did) and was just toying with things like cursor, but unsure.

Things have changed drastically now, engineers with these tools(like claude code) have become unstoppable.

Atleast for me, I have been able to contribute to the codebases i was unfamiliar with, even with different tech stacks. No, I am not talking about generating ai slop, but I have been enabled to write principal engineer level code unlike before.

So i don't agree with the above statement, it's actually generating real value and I have become valuable because of the tools available to me.

I was not expecting a couple of new apps being built, when the premise of the blog post talks about replacing "mid level engineers"

the thing about being an engineer at commercial capacity is "maintaining/enhancing an existing program/software system that has been developed over years by multiple people(including those who already left) and do it in a way that does not cause any outages/bugs/break existing functionality.

while the blog post mentions about the ability of using AI to generate new applications, but it does not talk about maintaining one over a longer period of time. for that, you would need real users, real constraints, and real feature requests which preferably pay you so you can priortize them.

I would love to see such blog posts where for example, a PM is able to add features for a period of one month without breaking the production, but it would be a very costly experiment.

Yeah you are right, I am underselling myself in terms of just watering it down to LOC. But I was mostly talking about tangible outcomes that are obvious.

> AI can write 15k lines of code, but it cannot take Liability for a single one.

Thanks for writing this, I needed it.

Yes, there will be always someone who is needed to program stuff. Totally agree with that.

But my question is "how many of those will be needed", because I am not saying that programmers are not needed.

When less numbers are needed, there will be so much competition in finding those jobs, esentially would also mean not able to find the work, as there will be always someone who would be willing to the job at lower wage and come to work with more youthful energy.

Just speaking out loud.

I agree with the takes, but my only question would be.

If everyone is doing high level stuff like architecture and design, how many of "those people" will be really needed in the long term? My intuition is telling me the size of market needing number of engineers will shrink.

Thanks for the clarification.

personally it would be too difficult for me to understand large chunks of work, like in your case "a week's worth of code" at a time. just wondering how do you go about it?

second, how do you pass such large PR's to your co-workers?(if you have any)

The process you have described for Codex is scary to me personally.

it takes only one extra line of code in my world(finance) to have catastrophic consequences.

even though i am using these tools like claude/cursor, i make sure to review every small bit it generated to a level, where i ask it create a plan with steps, and then perform each step, ask me for feedback, only when i give approval/feedback, it either proceeds for the next step or iterate on previous step, and on top of that i manually test everything I send for PR.

because there is no value in just sending a PR vs sending a verified/tested PR

with that said, I am not sure how much of your code is getting checked in without supervision, as it's very difficult for people to review weeks worth of work at a time.

just my 2 cents

I don't want to come across as judgemental or anything, nor I did deep research on your background.

It appears like you became a CTO, because you co-founded the company, not because you rose to the rank.

If you were to join a different company with this approach you are taking, I doubt if you would even reach Staff level.

Location: Bengaluru/Remote

Remote: Preferred

Willing to relocate: possibly

Technologies: Ruby, Ruby on Rails, Microservices, Scaling teams/tech

Resume:https://drive.google.com/file/d/18t5X_YuQCK_zF1Ic5VJRpBHF42H...

GH: https://github.com/vamsipavanmahesh

Email: [email protected]

Accomplished Senior Engineer with over 9 years of experience designing scalable Ruby on Rails applications, RESTful APIs, and microservices for high-traffic systems.

Skilled in AI-driven solutions, including LLMs and AI Agents, with expertise in architecting robust systems and optimizing performance.

Bit late to see this, are you still hiring for project/delivery manager roles?

Hi Thomas, this is Vamsi from India.

I have been working with Rails since 2015, and have worked with several high scale Rails apps from zero to production.

Recently been dabbling with AI stuff as well.

I can work in EU timezones comfortably, previously worked as a Staff engineer at Solaris bank, Berlin. I worked remotely from India.

Please find my resume: https://drive.google.com/file/d/1dhcXqiK7gJI8ptQDdR6bKG7WrRy...

Please find my github:

https://github.com/vamsipavanmahesh

I can reached over here: gvpmahesh at gmail dot com

I am based out of India, however can work in EU timezones. Have done this in the past as well. Can I apply?

Hello there.

I have applied for the position of Ruby Developer Advocate from my email gvpmahesh at gmail dot com.

Just wondering if it has come to your notice. I would be happy to have a chat with you.

Would the local average for the compensation be a huge constraint? If I am applying from the eastern part of the world?

I am interested, however from +5:30 timezone. Last time when I emailed you, I did not get any response, would you like to consider me if I am flexible about the timing?

Dumb question: How do I cross my eyes? can someone explain this method in detail?

Wondering if you are open to hiring from India.

I have previously worked as a staff engineer for a Berlin based company remotely from India.

I am based out of India, wondering if you are open to hiring remotely from here given I am willing to match time zones?

for me, toxic positivity is basically everyone pretending that everything is running smoothly even though it's not.

could happen because of either of these two reasons:

- they really don't know the ideal state

- they are afraid of the backlash if they speak up

noob here:

but are not the public keys anyway available on block chain? that means literally every thing can be brute forced?