Nelson Sathya I Architect advanced AI systems

Architect advanced AI systems for business automation | Web & mobile application development with AI integration | Technical strategy for enterprises

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

I didn't write a single line of code — just built AI Image Studio with @YouWareAI @YouWareCreator.
Try it here 👉 https://t.co/uYBeuDy7Ja
#YouWare

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@theworldlabs This sounds amazing! Excited to see how it brings creativity to life. Count me in for the beta preview!

[Aravind Srinivas @AravSrinivas]

Introducing Comet Shortcuts

You can now automate repetitive boring web workflows with simple natural language prompts and access them with a /command anywhere

We envision a future where people will be able to share and monetize custom shortcuts they built. More on that soon.

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@Kimi_Moonshot Kimi K2 sounds like the sidekick we all need! Ready to tackle those tasks and save us time. Can’t wait to give it a spin!

[Kimi.ai @Kimi_Moonshot]

🚀 Kimi K2 is here!
Built for code & agentic tasks.

Try it now at https://t.co/7YeIld97BT or via API.

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@prajdabre Honestly, who knew LinkedIn could be a goldmine? Time to update my profile and start cashing in too! check https://t.co/QU8fSBttS8

[Andrej Karpathy @karpathy]

@phbenz Haha I'm not trying to coin a new word or something. I just think people's use of "prompt" tends to (incorrectly) trivialize a rather complex component. You prompt an LLM to tell you why the sky is blue. But apps build contexts (meticulously) for LLMs to solve their custom tasks.

[Andrej Karpathy @karpathy]

+1 for "context engineering" over "prompt engineering".

People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits.

On top of context engineering itself, an LLM app has to:
- break up problems just right into control flows
- pack the context windows just right
- dispatch calls to LLMs of the right kind and capability
- handle generation-verification UIUX flows
- a lot more - guardrails, security, evals, parallelism, prefetching, ...

So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@AravSrinivas That sounds super convenient!
Love the idea of getting reminders right on WhatsApp.
Can't wait to try it out!

[Aravind Srinivas @AravSrinivas]

You can now schedule tasks with Perplexity on WhatsApp. This is the first time you get to feel a basic “assistant” on WhatsApp that sends you periodic news alerts, custom reminders at a frequency you set all in simple natural language. Message [phone] to start.

[Aadit Sheth @aaditsh]

How to master Claude Code from scratch (in 15 mins)

[Adithya S K @adithya_s_k]

Introducing Vibemotion

The first ever AI that turns a single prompt into stunning motion graphics and videos in minutes

@vibemotion_ai

[ElevenLabs @ElevenLabs]

Introducing 11ai - the AI personal assistant that's voice-first and supports MCP.

This is an experiment to show the potential of Conversational AI:

1. Plan your day and add your tasks to Notion
2. Use Perplexity to research a customer
3. Search and create Linear issues

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@asuvathaman @narendramodi @PMOIndia @AmitShah @rajnathsingh @myogiadityanath @AshwiniVaishnaw @nsitharaman @JPNadda @rajbhavan_tn @AmitShahOffice Wow, this sounds incredible! A Tamil AI model? Can’t wait to see it take on the ancient texts! Launching at IIT Madras with such a lineup is next level!

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@abir_hasan4736 send

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

Notable Personalities of India Magazine - Edition 37 https://t.co/3yiQ9JdLO3

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

Discover Ocrolus + Detect Feature https://t.co/1DVANSrHK1

Document AI for faster and more accurate financial decisions

[Nelson Sathya I Architect advanced AI systems @nelsonsathya]

@AndrewYNg Sounds cool! Finally, a way to make PDFs feel less like a puzzle. Can't wait to see how it all comes together!

[Elon Musk @elonmusk]

The EU leaders and Zelensky having fancy dinners while men die in trenches.

How many parents will never see their son again?

How many children will never see their father?