DEV Community: Pankaj Bisht

The Future of Software Development: What Will Developers Do When AI Codes for Them

Pankaj Bisht — Thu, 11 Jun 2026 12:56:06 +0000

Over the last decade, the software developer’s job has already been rewritten more than once. Hand-rolled infrastructure gave way to serverless. Monoliths broke into microservices on Kubernetes. We went from writing every line to watching pipelines build, test, and deploy themselves.

Now, AI-assisted coding is closing the last gap. Soon, within a couple of years, I’d guess, a model will write the service, wire up the dependencies, stand up the environment, and ship it, with a developer doing little more than writing prompts and approving the PR.

So the question is worth asking:

If the machine writes the code, what is left for me to do?

This post explores the different options available to software developers.

https://medium.com/design-bootcamp/the-future-of-software-development-what-will-developers-do-when-ai-codes-for-them-644a3e96975c

How to Build an AI Second Brain With Claude and Obsidian

Pankaj Bisht — Sat, 06 Jun 2026 14:27:05 +0000

Every time you open a fresh AI chat window, you start from zero. You re-explain the project, re-paste the background, re-describe who is involved, and by the time the model finally understands the question, half your patience is gone. Then you close the tab, and it all vanishes. Next time you have to do it all over again.

The fix to this issue isn’t a cleverer prompt; it’s giving the model something to read, and that is equivalent to creating your second brain.

I set this up recently using Claude and Obsidian. It took me about ten minutes, most of which was deciding which folder to hand over.

Link to the post - https://medium.com/ai-snapshots/how-to-build-an-ai-second-brain-with-claude-and-obsidian-5ac78f4021e0

A Hilarious Tale of an AI Transformation in a Big Enterprise (A Satire)

Pankaj Bisht — Thu, 04 Jun 2026 08:19:43 +0000

Everyone is in a race to become the AI-first organisation, which is not as easy as it sounds, especially for big enterprises. I have written a corporate satire to tickle your funny bone. I hope you read it and have a good time.

Here is the link:
https://medium.com/the-haven/merston-bank-spent-4m-on-its-ai-strategy-a-hilarious-tale-of-an-ai-transformation-fe1a995b5e05

5 AI Books That Changed My Perspective on Technology

Pankaj Bisht — Thu, 28 May 2026 06:16:30 +0000

In my recent blog post, I explored 5 books that deepened my understanding of the AI landscape.

For each book, I've given you the main takeaways, a summary, and where it's useful as AI moves on.

The Layoffs Aren’t About AI Replacing You. They’re About Funding It.

Pankaj Bisht — Sat, 23 May 2026 18:11:07 +0000

Silicon Valley is firing its future customers. Tech companies have cut 113,000 jobs in 2026 to fund AI infrastructure, betting that the rest of the economy will keep paying salaries so people still exist to buy what AI produces. Each company's logic works independently. However, the aggregate is where it falls apart.

This blog post covers the subject in detail - https://medium.com/write-a-catalyst/the-layoffs-arent-about-ai-replacing-you-they-re-about-funding-it-847ec36b58cd

Stop Writing PRDs for AI Features. Instead, Start Writing Evals.

Pankaj Bisht — Fri, 22 May 2026 12:47:40 +0000

My friend spent two weeks writing acceptance criteria for an AI summarisation feature. By the time it was signed off, the team had shipped three prompt variants, the vendor had updated the model, and the criteria described a feature that no longer existed.

Traditional product specs (PRD) assume everything behaves predictably. With AI, nothing is guaranteed. It shifts, drifts, and surprises us.

Now the question is: If PRDs don’t hold up, what replaces them?
I wrote an article recently about the importance of Evals.

Here is the link:
https://medium.com/analysts-corner/stop-writing-prds-for-ai-features-instead-start-writing-evals-a4bab4f09484

Claude Cowork vs OpenClaw: Risk and Governance (Product Lens)

Pankaj Bisht — Wed, 20 May 2026 10:54:38 +0000

I spent a good chunk of last week reading takes on Cowork versus OpenClaw.

Just to let you know, both are AI agents that do work on your local computer, not just chat about it. Cowork is Anthropic’s own product, built into the Claude desktop app.

OpenClaw is an open-source project that overtook React as the most-starred project on GitHub in about two months.

So, of course, everyone has started pitching them against each other. Which one wins? Which one should you bet your workflow on?

I think that’s the wrong question. And I think it’s wrong for a reason that has nothing to do with AI.

Here is the post that talks about the subject - https://medium.com/ai-snapshots/claude-cowork-vs-openclaw-which-ai-agent-wins-is-it-even-a-fair-debate-06e6c2e19424

As a PM, stop writing PRDs for engineers. Start writing them for your future self

Pankaj Bisht — Tue, 19 May 2026 11:59:49 +0000

Last week, I opened a PRD I had written about eighteen months ago. Someone on the audit team needed to know why we had shipped the feature the way we did.

I sat there reading my own document for ten minutes and still couldn’t tell what I had been thinking when I wrote it. The document had failed the one person who had ever come back to it. Me.

Link to read the full article:

https://medium.com/analysts-corner/as-a-pm-stop-writing-prds-for-engineers-start-writing-them-for-your-future-self-bf9ff89e2448