Aryan Pegwar

Empowering Brands and Professionals to Achieve 10X Profit Growth through AI & Automation

[Aryan Pegwar @pegwar_aryan]

@OpenAI Can it make Phone Calls?

[Aryan Pegwar @pegwar_aryan]

@Av1dlive Will try it firsthand

[Aryan Pegwar @pegwar_aryan]

Looks like GPT Astra was just the teaser 👀. Can't wait to see what today's launch is ✨🚀

[OpenAI @OpenAI]

Get ready.

[Aryan Pegwar @pegwar_aryan]

I have gone through the complete tutorial and converted my learnings into a skill.md file so that I can easily implement it across my agentic workflows

[Residual @res1dualedge]

Andrew Ng just dropped the best 2-hour course on Graph Engineering: from single agent to full automation

9:14 - your first agent
33:11 - loop engineering
1:02:46 - graph engineering
1:30:15 - agents that rewrite themselves
1:49:05 - full graph system

two hours, and it replaces every agent tutorial you bookmarked this year

Prompts → Agents → Loops → Graphs

most people will stop after the first agent and call it automation

he saves the last forty minutes for the graph that runs it without him

same model, same tokens, completely different week

watch it today

the step-by-step guide is below, save it while it is still early ↓

[Aryan Pegwar @pegwar_aryan]

That looks cool. I've made the skill.md for it and tried it for my research agentic workflows

[Alex Prompter @alex_prompter]

R.I.P. AI that agrees with everything you say.

Charles Darwin wrote down every fact that went against his ideas the moment he found it, because those were the ones he'd forget.

This prompt makes Claude do the same to your plans.

"I want to test my plan with Charles Darwin's golden rule. He wrote down every fact that went against his ideas the moment he found it, because those were the ones he'd forget. Don't tell me what's good about my plan. Instead, act as the notebook he kept, and give me
→ the 5 strongest facts or arguments against it
→ which one I'm most likely to ignore, and why
→ what I'd see if that one turned out to be true
→ one test I can run this week to find out
Don't soften anything and don't end on encouragement. My plan [DESCRIBE YOUR PLAN, IDEA OR BELIEF]"

Run it before your next big decision.

[Aryan Pegwar @pegwar_aryan]

Yes I have experienced it. It was amazing and I have created a .md file so that for every UI design, every new UI component, it uses that to automatically creates motion design for it.

[zero @twoclipping]

opus 5.5 is f*cking cracked at motion design

this entire video is code, 0 after effects

im open sourcing the prompt template for these motion designs

steal it to recreate these ↓

<inputs>
Ask me for: 8 to 12 UI states I want the shape to become (e.g. button, loader, player, slider, toggle, tabs, chart, command palette, toast), pure black and white or one accent color, and a royalty-free song around 120 BPM (e.g. Mixkit, free for commercial use).
</inputs>

<direction>
Dribbble-level UI motion. One shape, never cut: every state is the same element morphing its size, radius and color while its content swaps with a short blur. A cursor drives every change with real clicks and drags. Light warm-gray canvas, black and white components, one clean UI font (Geist). Springs everywhere, a tiny overshoot at most. The camera zooms so each state fills the frame. The last frame is the first frame, so it loops.
Banned: bouncy easing, particle bursts, glows, gradients on UI chrome, mismatched icon strokes, dead time, anything that looks like a template.
</direction>

<structure>
120 BPM, 7 bars, something happens on every beat.
Button → loader → check → dynamic island → music player with a play/pause morph → scrub the progress bar → it becomes a volume slider that stretches when dragged past max → a toggle flips on the beat → the knob becomes a liquid tab indicator → the tabs open into a chart that draws itself, with a tooltip on hover → it collapses into ⌘K → type to filter → enter → toast → back to the button.
</structure>

<build>
1. One HTML file, square 1440x1440. Every style is computed from time inside seek(t): no CSS transitions, no timers, no state carried between frames.
2. Springs are closed-form step responses. A value that changes target many times is the sum of one spring per change, so it stays a pure function of time.
3. The tab indicator's two edges ride different springs, so the leading edge stretches ahead of the trailing one. Same trick for the toggle knob.
4. Drags are direct manipulation: while the cursor is held, the value is computed from its position. On release it springs back from wherever it was.
5. Analyze the song with numpy for the beat grid and start on a downbeat. Place every UI sound by its measured peak.
6. Render with Playwright: 4 subframes per frame, blended with ffmpeg tmix for motion blur at 60fps.
7. Render one frame per beat before the full render. Fix anything off the grid, cramped or hard to read.
</build>

<gotchas>
Never put will-change on anything the camera scales or the text renders blurry. Text that swaps inside a morphing container needs its own enter and exit timing or it overlaps. Make the last frame identical to the first, cursor position and speed included, or the loop stutters.
</gotchas>

<start>
Ask me for the inputs, then show me the state list on the beat grid before you write any code.
</start>

[Aryan Pegwar @pegwar_aryan]

@twoclipping Yes I have experienced it. It was amazing and I have created a .md file so that for every UI design, every new UI component, it uses that to automatically creates motion design for it.

[Aryan Pegwar @pegwar_aryan]

Thanks for sharing. I played it smart. I've completed the entire course and created a structured .md file that lets me implement its lessons automatically via an agent.

[Aryan Pegwar @pegwar_aryan]

@TechByArti Thanks for sharing. I played it smart. I've completed the entire course and created a structured .md file that lets me implement its lessons automatically via an agent.

[Aryan Pegwar @pegwar_aryan]

In Narmada schhipra Sangam near Indore, a lone duck is stuck @Vantara_RF @AmbaniKaVansaj please rescue

[Aryan Pegwar @pegwar_aryan]

I watched the complete amazing session on the cutting-edge harness engineering and I played it smart and created a scale.md file to implement it immediately in all my AI agentic workflows

[rari @0xwhrrari]

Google Brain founder Andrew Ng:

"Prompting will be dead in 6 months

Agent harnesses built with loops and graphs will replace it"

Agent → Harness → Feedback → Loops → Graphs → Self-Improving Systems

In this 1-hour Stanford lecture, he explains what the best engineers are building instead and how you can start today

Prompt → Run → Verify → Improve

The first 20 minutes teach what most $1,500 courses try to sell you

For free

Bookmark and watch it today

Then read the guide below on building an agent harness that improves itself

[Aryan Pegwar @pegwar_aryan]

@0xwhrrari I watched the complete amazing session on the cutting-edge harness engineering and I played it smart and created a scale.md file to implement it immediately in all my AI agentic workflows

[Aryan Pegwar @pegwar_aryan]

That's an amazing session on graph engineering. I have created a skill.md file for it and now it's already being implemented in my agentic workflows.

[Mahax @Mahaximus_]

Andrew Ng just dropped the best 2-hour course on Graph Engineering: from single agent to full automation

9:14 - Your first agent
33:11 - Loop engineering
1:02:46 - Graph engineering
1:30:15 - Agents that rewrite themselves
1:49:05 - Full graph system

Free, the best thing on graph engineering I've come across

Watch it, then build your first graph with the guide below

[Aryan Pegwar @pegwar_aryan]

@Mahaximus_ That's an amazing session on graph engineering. I have created a skill.md file for it and now it's already being implemented in my agentic workflows.

[Aryan Pegwar @pegwar_aryan]

I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.

[Ram Singh Verma @RamSingh_369]

Sam Altman, CEO of OpenAI:

“You don’t need to write prompts anymore.”

In just 27 minutes, he explains how to use ChatGPT in ways most people haven’t even explored yet.

This was a talk he gave to Stanford students. A friend sent me the recording last night.

After watching it, I realized I was barely using 15% of what ChatGPT can actually do.

Watch the full talk, then check out the guide below on how to build a system that can prompt itself.

[Aryan Pegwar @pegwar_aryan]

@RamSingh_369 I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.

[Aryan Pegwar @pegwar_aryan]

I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.

[Aryan Pegwar @pegwar_aryan]

@TechByArti I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.

[Aryan Pegwar @pegwar_aryan]

I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.

[Hanako @hanakoxbt]

Anthropic engineer:

"90% of our engineers were already using self-improving loops. Now everyone is moving toward agentic graphs."

"Prompting is basically over."

in 10 minutes she builds her full Claude Code system live from a completely empty terminal

Agents → Loops → Harness → Graphs

prompting was the old workflow, graph engineering is the next one

same model, same tokens, and the only thing that changes is the shape you run it in

watch it today, then save the full guide below

[Aryan Pegwar @pegwar_aryan]

@hanakoxbt I played smart. I have gone through the complete and created skill.md file that allows me to implement its learning in my every agentic workflow.