AI Engineer building production AI systems. Sharing what I build, learn & break along the way. Capture recipes flawlessly recipes.aisolvit.com
Pune, India
- Tweets 59
- Following 73
- Followers 37
- Likes 43
Pinned Tweet
Hey, I'm Samkit.
AI Engineer.
Been working with AI for 2+ years.
Mostly worked on AI Agents, RAG, LLM fine-tuning and taking AI products from POC to production.
Currently AI Engineer at iion (Adtech startup)
Working on my own ideas after hours.
I like travelling, reading and stargazing.
That's pretty much me :)
Let's connect...
1
101
Trying something new!
I'm an AI Engineer with 2+ years of experience building production AI systems.
I've worked on RAG, AI agents, chatbots, automations, and taking AI products from 0 to 1.
I'm opening up 5 free, 30-minute consultation slots this month.
If you're building something with AI, want to add AI to your product, or simply automate a task, I'd love to hear what you're working on.
Let's connect!
calendly.com/kankariyasamkit…
3
3
98
Before GenAI, we did too much manually. It worked, but it was slow.
After GenAI, we started outsourcing too much. Everything got faster, but the quality and our involvement dropped.
Turns out, the real skill is knowing what to offload and what to own.
1
16
AI has made going from idea to product easier than ever.
But the hard part hasn't changed:
- Is this a real problem worth solving?
- Does the MVP actually solve it?
- Will people use or pay for it?
Funny enough, the answers still come back to two classic startup books:
The Mom Test : validate the problem.
The Lean Startup : validate the solution.
AI can help us build faster.
It can't validate the market for us.
2
1
33
Idea → Product time has been drastically reduced.
The bigger challenge now is everything that comes after:
• Idea validation
• MVP validation
• Marketing & distribution
AI can build a lot for us, but we still have to figure out the other half.
How are you guys upskilling in these areas?
Are you reading any books, following specific frameworks, or trying particular strategies?
I’m currently following Lean philosophy, but honestly, there’s still this fear of putting yourself out there without a clear game plan.
Would love to hear how others are approaching this.
27
AI is making builders more productive than ever.
It might also be making some of us worse at thinking.
Hear me out.
The distance from idea → research → prototype → product has collapsed.
Things that used to take weeks can now happen in hours.
That’s incredible.
But I think we're asking the wrong question.
Not: How will AI change the way we build?
But: How should we change while building with AI?
We're increasingly using AI for everything:
- Writing code
- Research
- Debugging
- Content
- Design
- Analysis
- Even deciding what to build
And that's where I think we need to be careful.
If we constantly outsource the thinking, we risk becoming very good at executing without actually understanding what we're doing.
AI can help us move faster.
But we still need to:
- Understand the problem
- Challenge assumptions
- Decide what matters
- Think through trade-offs
- Design the solution
- Ask whether anyone actually needs it
The best builders in the AI era won't necessarily be the ones who can generate the most code or ship the fastest.
They'll be the ones who can think clearly, ask better questions, and build the right thing.
AI should amplify our thinking, not replace it.
Curious if anyone else has noticed this in their own workflow.
P.S. Written by me, refined with AI.
1
38
Book I'm reading currently
The Mom Test - To validate the idea before you go all in on building.
Massive ROI on the first few chapters itself.
What you guys are reading currently?
p.s. this is my 124th book
3
67
For years I kept asking my mother to write down her recipes.
I even gave her a diary.
She wrote 2–3 recipes. Not because she didn’t care. Writing ingredients, exact steps and all the little decisions is simply work.
That unfinished diary became the reason I built Rasa
1
1
1
51
Rasa - Her Flavours Preserved Forever
recipes.aisolvit.com
1
1
35
Samkit Kankariya retweeted
A few random notes from claude coding quite a bit last few weeks.
Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.
IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.
Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.
Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.
Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.
Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.
Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.
Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.
Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?
TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.
1,629
5,568
40,708
7,861,244
