Ritesh Shrivastav

@Jodo_in Eng Director by day, Dad in evening, hacker at night.

[Ritesh Shrivastav @codingdash]

This is part of a larger series on building systems on top of Claude: https://t.co/th2AqYCC3D

#Claude #AIEngineering #AgentDesign

[Ritesh Shrivastav @codingdash]

While working with Claude, I spent some time understanding how compaction works. The short version is: the system doesn’t really “remember” everything, it rewrites the conversation into something shorter.

[Ritesh Shrivastav @codingdash]

I’ve written this down properly with examples and what this means in practice: https://t.co/PELcipL5y6

[Ritesh Shrivastav @codingdash]

Most teams are still treating Claude like a smarter autocomplete.

That works until it doesn't, and when it breaks, it breaks in ways that are genuinely hard to debug. Not errors. Inconsistency. Context drift. Outputs that were fine yesterday and aren't today.

I've been thinking about why some teams compound on this and most don't. Turns out it comes down to one thing they do differently from the start.

Wrote it up: https://t.co/eQkbTyrBPp

#claudecode #softwareengineering @AnthropicAI

[Ritesh Shrivastav @codingdash]

5/ I wrote the full piece. Field report from inside the infrastructure.

The graveyard of correct ideas. The concurrency problem. The India opportunity. The pricing model that's being made obsolete.

https://t.co/dZCYhZpXpj

[Ritesh Shrivastav @codingdash]

1/ During the 2015 Chennai floods, our data centre went dark. What I remember most isn't the outage. It's what Vishnu and I built in response.

[Ritesh Shrivastav @codingdash]

4/ 10 years later the ideas we tried and shelved at Exotel are now funded product categories.

Sentiment analysis on calls. SOP to workflow automation. Voice biometrics.

The vision always existed. The capability layer just arrived.

But the infrastructure layer hasn't caught up. 95% of AI voice pilots are failing. Less than 1% of contact centres have autonomous agents in production.

[Ritesh Shrivastav @codingdash]

I started blogging on https://t.co/slF74nYSlG in 2014 as a college student. Same blog. Still running.

The name came from @codinghorror's Coding Horror, named after an icon in Steve McConnell's Code Complete, used to flag cautionary examples of bad code. That lineage felt right, and codingdash stuck. It's been my corner of the internet since.

Shipped a redesign this week. The second one since starting, the first redesign I did in 2020, inspired by @Stammy's site. This one was overdue not because something broke, but because the site had quietly fallen behind the person writing it.

Short note on what changed: https://t.co/yWH0sfzwxA

[Ritesh Shrivastav @codingdash]

Full writeup on why I built it and where it's headed: https://t.co/JJ3MVdfUKM

[Ritesh Shrivastav @codingdash]

I spent a long time looking for an AI code review tool that actually fit how my team works. Tried a few. None felt complete.

Hidden costs. No control over which model runs. Guidelines that were either too generic or too rigid to customise. And when things broke, no visibility into why.

So I built one over a weekend and open sourced it.

PRLens — bring your own Claude or GPT-4o key, bring your own guidelines, runs as a GitHub Action in your own pipeline. No new vendor. No black box.

Still early, lots to build. But the foundation is there and I'd love collaborators who've felt the same frustrations.

https://t.co/hT7iSDpoVK

[Ritesh Shrivastav @codingdash]

Most AI-powered products hide their real cost structure. They bundle model inference into a flat subscription or per-seat price, the same way early SaaS bundled AWS costs. But there's a key difference: AI model pricing is dropping 50-200x per year and the provider landscape shifts every few months.

When your cost base is that volatile, bundling it creates problems:

- You can't pass savings to customers as models get cheaper
- You can't let customers bring their own API keys (which they increasingly want)
- You can't give enterprises the compliance visibility they'll legally need by August 2026

The question every AI builder should ask: what is my product worth independent of the model running underneath it?

If the answer is clear, decouple the burn and prove it.

https://t.co/f8yV6w16nc

[Ritesh Shrivastav @codingdash]

The Joel Test turned 26, @spolsky.

Source control? That's oxygen now. Daily builds? Elite teams deploy hourly.

Here's the 2026 version—12 new questions for modern engineering teams.

https://t.co/LQsPtgplpd

[Ritesh Shrivastav @codingdash]

If you start behind, you cannot walk at the same pace as those who began ahead. The train is moving. You have to run.

#GrowthJourney #StartBehind #CatchTheTrain #Mindset #BlogPost

https://t.co/ISkt9WvvHA

[Ritesh Shrivastav @codingdash]

I usually refresh my workspace every February, but this year I moved the upgrade forward to November. A cleaner desk, better setup, and a more organized reading corner.

As always, my junior auditor stopped by for a quick quality check. 💛📚

[Ritesh Shrivastav @codingdash]

Work from home setup as of 2021 Feb.

[Ritesh Shrivastav @codingdash]

Another year. As of Feb 2025, the journey continues—every upgrade, every tweak, still feels like day zero. #WorkstationEvolves #DeskSetup 🚀

[Ritesh Shrivastav @codingdash]

@koolhead17 this is super interesting! Which book is this from?

[Ritesh Shrivastav @codingdash]

Published a new article: Invisible Bugs https://t.co/lh3dTDP65t

#CodeReview #TechDebt #InvisibleBugs #AI #SystemDesign #DeveloperVelocity #BlogPost