Pratham's banner

Pratham

@Prathkum • 448,808 subscribers

I talk about web, AI, API, and social • Building experiences at @APILayer • Prev @Rapid_API @HyperspaceAI

Shorts

SF Fleet Week is actually insane. Craziest thing I have ever witnessed.

SF Fleet Week is actually insane. Craziest thing I have ever witnessed.

16,075 views

This is scary! Someone built a digital society for AI agents. AIvilization (AI + Civilization) is a simulation platform where thousands of AI agents live and do normal human things like work, socialize, learn, and evolve. You create one agent and let it live. You define its personality, goals, and behavior and then it goes off into a shared world with thousands of other AI agents doing the same. Check it out here:

This is scary! Someone built a digital society for AI agents. AIvilization (AI + Civilization) is a simulation platform where thousands of AI agents live and do normal human things like work, socialize, learn, and evolve. You create one agent and let it live. You define its personality, goals, and behavior and then it goes off into a shared world with thousands of other AI agents doing the same. Check it out here:

38,162 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

SF Fleet Week is actually insane. Craziest thing I have ever witnessed.

SF Fleet Week is actually insane. Craziest thing I have ever witnessed.

16,075 views • 9 days ago

MiniMax M2.5 > Claude Opus 4.6 I have been using it for a couple of days and have never hit the limit. I am currently on the Coding Plus plan which gives me 300 prompts per 5 hours. My new setup is OpenCode + MiniMax M2.5 What I have noticed: M2.5 – handles multi-step coding workflows and repo-level reasoning more reliably – better at chaining actions. think: generate test, fix bug, refactor, repeat – high TPS throughput M2.5 hits ~80%+ on SWE-Bench coding benchmarks on par with Opus and runs these tasks 37% faster than its predecessor while costing ~1/10th - 1/20th the price. Check out the video.

MiniMax M2.5 > Claude Opus 4.6 I have been using it for a couple of days and have never hit the limit. I am currently on the Coding Plus plan which gives me 300 prompts per 5 hours. My new setup is OpenCode + MiniMax M2.5 What I have noticed: M2.5 – handles multi-step coding workflows and repo-level reasoning more reliably – better at chaining actions. think: generate test, fix bug, refactor, repeat – high TPS throughput M2.5 hits ~80%+ on SWE-Bench coding benchmarks on par with Opus and runs these tasks 37% faster than its predecessor while costing ~1/10th - 1/20th the price. Check out the video.

184,874 views • 7 months ago

After ClawdBot, the next big thing could be Qoder Quest. Most of the coding tools today need multiple iterations of testing, debugging, and prompts. An autonomous coding tool would be game changer. Qoder Quest is exactly this. It’s designed to take ownership of your projects. For sure, it is not a replacement for your mental model. Instead of line-by-line hand-holding, the workflow looks like this: – Describe a goal: tell it what you want to build – Approve the Spec: approve the technical spec first to align Quest with your mental model – Walk away: let the Quest run autonomously Attached is a video of me playing around with Quest for the first time. Get started with it: New users could have a 2-week pro trial with some credits to execute 5 Quest tasks. Appreciate the Qoder team for collaborating with me on this deep dive.

After ClawdBot, the next big thing could be Qoder Quest. Most of the coding tools today need multiple iterations of testing, debugging, and prompts. An autonomous coding tool would be game changer. Qoder Quest is exactly this. It’s designed to take ownership of your projects. For sure, it is not a replacement for your mental model. Instead of line-by-line hand-holding, the workflow looks like this: – Describe a goal: tell it what you want to build – Approve the Spec: approve the technical spec first to align Quest with your mental model – Walk away: let the Quest run autonomously Attached is a video of me playing around with Quest for the first time. Get started with it: New users could have a 2-week pro trial with some credits to execute 5 Quest tasks. Appreciate the Qoder team for collaborating with me on this deep dive.

104,021 views • 8 months ago

Generative UI will be the next big shift in AI. Where your product UI is dynamically generated, based on user intent and context. If you are a developer building AI apps, you need to hear this out:

Generative UI will be the next big shift in AI. Where your product UI is dynamically generated, based on user intent and context. If you are a developer building AI apps, you need to hear this out:

119,252 views • 11 months ago

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

80,634 views • 8 months ago

Git is a must-have skill for developers. But it’s confusing and the learning curve is difficult. Check out this website: Visual and interactive way to learn Git on the web.

Git is a must-have skill for developers. But it’s confusing and the learning curve is difficult. Check out this website: Visual and interactive way to learn Git on the web.

309,314 views • 3 years ago

Taste is what makes you stand out in the AI era. And taste is knowing what is actually correct. I have been testing MiroMind, and it’s the first "General Purpose Solver". It actually prioritizes verifiable reasoning over probabilistic guessing. A few things about it: • Verifiable Reasoning Chains: It provides a 300-step, human-readable, and auditable chain. If the reasoning can't be replayed, it's unqualified • DAG-Based Architecture: It supports branching, rollbacks, and replanning. It acts like a senior analyst navigating complex logic • 4-Role Verification: Every output is cross-checked by an internal kernel: Planner → Executor → Chain Checker → Verifier MiroMind is literally for everyone, including engineers, doctors, professors, lawyers, researchers, and more.

Taste is what makes you stand out in the AI era. And taste is knowing what is actually correct. I have been testing MiroMind, and it’s the first "General Purpose Solver". It actually prioritizes verifiable reasoning over probabilistic guessing. A few things about it: • Verifiable Reasoning Chains: It provides a 300-step, human-readable, and auditable chain. If the reasoning can't be replayed, it's unqualified • DAG-Based Architecture: It supports branching, rollbacks, and replanning. It acts like a senior analyst navigating complex logic • 4-Role Verification: Every output is cross-checked by an internal kernel: Planner → Executor → Chain Checker → Verifier MiroMind is literally for everyone, including engineers, doctors, professors, lawyers, researchers, and more.

40,092 views • 5 months ago

This is one of those abstractions that makes perfect sense once you see it. Write your AI agent once. Run it across Slack, Microsoft Teams, and every messaging platform that follows. That's exactly what CopilotKit's open-source Channels SDK does for any AG-UI agent. Instead of maintaining separate bots for every platform, you connect your agent once and let the SDK handle the channel-specific integration.

This is one of those abstractions that makes perfect sense once you see it. Write your AI agent once. Run it across Slack, Microsoft Teams, and every messaging platform that follows. That's exactly what CopilotKit's open-source Channels SDK does for any AG-UI agent. Instead of maintaining separate bots for every platform, you connect your agent once and let the SDK handle the channel-specific integration.

16,216 views • 2 months ago

One of my favorite API design principles is this: Ask developers for intent, not implementation. Most messaging APIs make you decide how to send a message: – SMS – WhatsApp – RCS Your application knows who it wants to reach. It shouldn't have to figure out how best to reach them. That's infrastructure. I have been trying sent, and I like the abstraction they chose. You don't pick a channel. You simply send: – a phone number – a message Sent decides how to deliver it based on availability, historical engagement, and cost. It makes your code much simpler. Makes for a better developer experience. Definitely worth giving it a try.

One of my favorite API design principles is this: Ask developers for intent, not implementation. Most messaging APIs make you decide how to send a message: – SMS – WhatsApp – RCS Your application knows who it wants to reach. It shouldn't have to figure out how best to reach them. That's infrastructure. I have been trying sent, and I like the abstraction they chose. You don't pick a channel. You simply send: – a phone number – a message Sent decides how to deliver it based on availability, historical engagement, and cost. It makes your code much simpler. Makes for a better developer experience. Definitely worth giving it a try.

14,357 views • 2 months ago

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

33,920 views • 8 months ago

Vibe coding has one underrated benefit. You can quickly build your own workflows or tools without waiting on anyone. If you develop such tools, here's a better way to do it:

Vibe coding has one underrated benefit. You can quickly build your own workflows or tools without waiting on anyone. If you develop such tools, here's a better way to do it:

37,613 views • 10 months ago

I bet you don't know about this CSS property.

I bet you don't know about this CSS property.

94,485 views • 3 years ago

converts raw voice to organized tasks and notes with AI. • Clean design • Integrate with Slack • Tasks, notes, ideas in one place Definitely check it out!

converts raw voice to organized tasks and notes with AI. • Clean design • Integrate with Slack • Tasks, notes, ideas in one place Definitely check it out!

44,341 views • 1 year ago

Stop treating Claude like a typewriter. AI shouldn’t just talk, it should show, adapt, and respond visually. If you are a developer building with Claude, you need to hear this out:

Stop treating Claude like a typewriter. AI shouldn’t just talk, it should show, adapt, and respond visually. If you are a developer building with Claude, you need to hear this out:

23,587 views • 8 months ago

Most AI agents are just toys that live in a chat box. They are high on hype, low on utility. You spend more time prompting them than doing actual work. Notion Agent is different. It’s not just a window into an LLM. It’s a layer of intelligence sitting directly on any page on Notion. Check out the attached video. I just asked Notion Agent to write practical examples of each React Hook. Here’s how Notion Agent is helping me build it. • Notion Agent forms a plan: (Search → Read → Decide → Update → Notify). You give it a goal, and it executes multi-step workflows like editing hundreds of pages or updating complex databases. • It can create pages, customize properties, and build entire database views from scratch. • Total Context: It doesn't just search Notion. It pulls from Slack, Google Drive, and the web. It finds the patterns across your entire stack in seconds. Check out Notion Agent here: Appreciate the Notion team for collaborating with me on this deep dive.

Most AI agents are just toys that live in a chat box. They are high on hype, low on utility. You spend more time prompting them than doing actual work. Notion Agent is different. It’s not just a window into an LLM. It’s a layer of intelligence sitting directly on any page on Notion. Check out the attached video. I just asked Notion Agent to write practical examples of each React Hook. Here’s how Notion Agent is helping me build it. • Notion Agent forms a plan: (Search → Read → Decide → Update → Notify). You give it a goal, and it executes multi-step workflows like editing hundreds of pages or updating complex databases. • It can create pages, customize properties, and build entire database views from scratch. • Total Context: It doesn't just search Notion. It pulls from Slack, Google Drive, and the web. It finds the patterns across your entire stack in seconds. Check out Notion Agent here: Appreciate the Notion team for collaborating with me on this deep dive.

20,933 views • 8 months ago

Convert Figma to Code with AI. – your AI frontend engineer 1. install VS code extension 2. upload Figma file 2. get full code Superflex analyzes your code first, then suggests context-aware code.

Convert Figma to Code with AI. – your AI frontend engineer 1. install VS code extension 2. upload Figma file 2. get full code Superflex analyzes your code first, then suggests context-aware code.

35,730 views • 1 year ago

Developers lives just got much easier. My friends at daily.dev have launched an awesome "Search" feature for developers. Ask anything you want and their fine-tuned model will give you the most accurate answer. No more manual web surfing. I've partnered with them to share 50 invites! Drop a comment if you want to try it out.

Developers lives just got much easier. My friends at daily.dev have launched an awesome "Search" feature for developers. Ask anything you want and their fine-tuned model will give you the most accurate answer. No more manual web surfing. I've partnered with them to share 50 invites! Drop a comment if you want to try it out.

45,607 views • 2 years ago

No more content to load