Ish Rajesh Shelley

Agent Builder for SaaS| Founder at Ginger Labs | IIT Ropar

[Ish Rajesh Shelley @ishrajesh28]

@harisahmad59 https://t.co/xeC93X1d9J - give your users an AI assistant that completes tasks inside your product, not a support bot.

[Ish Rajesh Shelley @ishrajesh28]

@aseniordesigner Hey man, shall be nice to connect!

[Ish Rajesh Shelley @ishrajesh28]

@sridharfyi Shall be nice to attend, do share once it is final.

[Ish Rajesh Shelley @ishrajesh28]

@venky_gg would love to try, have dm'ed you

[Delba @delba_oliveira]

Fable is back 🦋

[Udayan Walvekar @udayan_w]

a global wave starts tomorrow

[Ish Rajesh Shelley @ishrajesh28]

building at the growthx buildathon 🛠️

I'm building a way to run AI agents at a fraction of frontier model cost — without losing the experience.
same quality, way cheaper.

stay tuned for progress 👀

@GrowthX_Club

[Addy Osmani @addyosmani]

https://t.co/0DyFIXJueI

[sanket patel @realsanketp]

This makes sense:

Spawning agents is not the skill. Anyone can run 20. The real skill is designing the system around the one serial resource that cannot be cloned or parallelized. That resource is your attention.

[Alex Stauffer @alexstauffer_]

We post-trained a 3B model with RL to beat Opus on spreadsheet retrieval. Faster, cheaper, more accurate.

- If a piece of your agent loop is narrow, verifiable, and highly repeatable, a tiny trained model might beat the frontier.
- The application layer is still early and new verticals are opening fast. Cheap domain specialists orchestrated by a frontier model that only spends tokens on judgment is a bet worth watching.

[Aakrit Vaish @aakrit]

Huge congrats @jumbld @ayushgarg_xyz and the entire Portkey team. @miten and I are proud to be early backers with @peercheque.

This is an awesome outcome for the entire Indian AI ecosystem. @kpowerinfinity has put it beautifully:

"For everyone in the corridor doing the 24-hour flights, the 6am customer calls, the cold LinkedIn outreach that goes nowhere, the late nights debugging on call while your kids sleep one timezone over: today is a good day. It's harder, but sometimes it's worth it :)"

[Shashank Kumar @shashank_kr]

Great news to start off the new financial year. @Razorpay is now embedded natively inside @OpenAI’s Codex, an industry-first for any Indian payments company.

A developer prompts "build me a fitness app with a ₹499 one-time payment." Codex builds it. Razorpay handles the payments. No separate integration, no dashboard-hopping.

If AI makes creation effortless, monetisation should be just as simple.

India has 6 million developers & weekly Indian users of Codex 4x'd in two weeks this February. We’re building for this shift where more people can create, launch, and earn without friction.

We have always enabled businesses so that their payments are smoother, easier, simpler & faster and Codex just got added to that already illustrious list.

[Ben James @BenJames_____]

I made a USB-Clawd who gets my attention when Claude Code finishes a response

[Yasser Dahou @dahou_yasser]

I used Gemma4 + Falcon Perception from this mlx-vlm release to build a grounded reasoning agent runs fully local on M3

the idea: VLMs are great at reasoning but not great at measuring. Falcon Perception is great at segmentation but cant reason. so you loop them: Gemma4 decides what to look for, FP segments it and returns pixel-accurate coordinates, Gemma4 reasons on the numbers

ask "is the blue player offside?" �� it grounds the players, finds the second-to-last defender, compares centroid positions, applies the rule. check the video for some examples
@Prince_Canuma I can submit a PR with this demo if you want

[shirish @shiri_shh]

generalists are about to win big

If you understand a little of tech, business, and people, and can connect everything fast.

you're sitting on a goldmine right now.

[Omar Khattab @lateinteraction]

I find it disappointing to see how much progress comes daily from late interaction, DSPy/GEPA, and RLMs but our slow industry only catches up after a lab person slaps a name like “autoresearch” or “deep research” on it lol. The future is already here, just not equally distributed

[Activate @ActivateSignal]

Building the next generation of real-world AI systems!

Here’s a look back at AI Engineers Day! We spent the day with India’s top AI developers, technical founders and engineers, moving from deep technical sessions and insightful keynotes straight into hands-on build hours focused on voice agents, developer tooling and agent orchestration.

A huge thank you to OpenAI and Peak XV Partners for partnering with us to make this happen.

Hit play to see the builder ecosystem in action ▶️👇
@aakrit @177pc @OpenAI @peakxvpartners

[Ish Rajesh Shelley @ishrajesh28]

@StockSavvyShay We are here with autonomous agents now!

[Naval @naval]

Pure software is rapidly becoming un-investable.

[Raymond Weitekamp @raw_works]

out of curiosity after reading this, i started benchmarking rlm and dspy.rlm on longmemeval

tl;dr - i think i might have a new "sota memory system" by the end of the day.

cc @DSPyOSS @a1zhang @lateinteraction