Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We built an auto research loop for DeFi strategy development so you can deploy winning strategies to paper trading and (soon) live execution. Inspired by Andrej Karpathy's auto research, but instead of optimizing LLM training it's optimizing backtests. The agent iterates until it finds strategies that actually work 👇

Wayfinder Foundation 🧭

108,072 subscribers

13,106 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Another week, another agent. Explorer is Sierra's agent-optimizing agent. Think of of it like ChatGPT deep research, but instead of doing research on the Internet, it's doing research over your customer conversations

Another week, another agent. Explorer is Sierra's agent-optimizing agent. Think of of it like ChatGPT deep research, but instead of doing research on the Internet, it's doing research over your customer conversations

Bret Taylor

36,938 views • 2 months ago

$Proud to announce Algostra: the first truly comprehensive algo trading platform built by a brokerage house. Algostra supports all charting methods, technical strategies, and multiple ways to implement options strategies. Run up to 500 symbols per strategy and multiple strategies running simultaneously. This makes it a one-of-a-kind algo trading platform. No coding. No integrations. Just structured, disciplined execution. Years of research, market experience, and real trader feedback have gone into building this platform.. and this is only the beginning. What you see today is just a fraction of what we plan to build. I am confident Algostra will help retail and HNI traders and investors in many meaningful ways. We are also going to collaborate with research analysts who wish to publish and deploy their strategies. Rolling out in batches. Built for traders who believe process and execution matters more than intention. Excited!$

Proud to announce Algostra: the first truly comprehensive algo trading platform built by a brokerage house. Algostra supports all charting methods, technical strategies, and multiple ways to implement options strategies. Run up to 500 symbols per strategy and multiple strategies running simultaneously. This makes it a one-of-a-kind algo trading platform. No coding. No integrations. Just structured, disciplined execution. Years of research, market experience, and real trader feedback have gone into building this platform.. and this is only the beginning. What you see today is just a fraction of what we plan to build. I am confident Algostra will help retail and HNI traders and investors in many meaningful ways. We are also going to collaborate with research analysts who wish to publish and deploy their strategies. Rolling out in batches. Built for traders who believe process and execution matters more than intention. Excited!

Prashant Shah

10,435 views • 5 months ago

We’re launching Volrix. An MCP server that lets you backtest and research trading ideas directly from Claude and Chatgpt. Connect your AI agent, describe a strategy, and run backtests across index and commodity derivatives. Link in the comments, Try it for free!

We’re launching Volrix. An MCP server that lets you backtest and research trading ideas directly from Claude and Chatgpt. Connect your AI agent, describe a strategy, and run backtests across index and commodity derivatives. Link in the comments, Try it for free!

Niraj Munot

143,771 views • 23 days ago

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Fraction AI

62,061 views • 2 months ago

Research can pay off. And Robinhood Strategies does the hard part for you.

Research can pay off. And Robinhood Strategies does the hard part for you.

Robinhood

211,110 views • 11 months ago

Far too many popular strategies for teaching reading are not actually supported by research. We sifted through to find the ones that are most effective.

Far too many popular strategies for teaching reading are not actually supported by research. We sifted through to find the ones that are most effective.

edutopia

446,980 views • 3 years ago

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Shrey Pandya

229,939 views • 2 months ago

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

Introducing Skills in SciSpace Agent. Specialized modes built for specific research workflows. Describe the task, and the right workflow activates automatically. Yes, the right Skill gets loaded based on what you need. Built to simplify multi-step research work and reduce friction around execution. Skills are now live. Try it inside SciSpace Agent.

SciSpace

43,196 views • 3 months ago

Most people want to join the crypto market but are held back by complex trading & overwhelming data. So, we’re building an AI Trading Agent 📊 Auto-analyzes market 🤖 Auto-Executes strategies ⏳ Saves your time & delivering steady returns. No coding, no screens, just one click.

Most people want to join the crypto market but are held back by complex trading & overwhelming data. So, we’re building an AI Trading Agent 📊 Auto-analyzes market 🤖 Auto-Executes strategies ⏳ Saves your time & delivering steady returns. No coding, no screens, just one click.

FOMOSCAN.ai

53,772 views • 10 months ago

Dexcelerate is LIVE! • Lightning quick trades • Fully auto trading - auto buy calls, algos and telegram. • Account abstraction • Full scanner • Trading strategies • Fastest charts • 30% of fees rev sharing (live this week) watch the video to get started 👇

Dexcelerate is LIVE! • Lightning quick trades • Fully auto trading - auto buy calls, algos and telegram. • Account abstraction • Full scanner • Trading strategies • Fastest charts • 30% of fees rev sharing (live this week) watch the video to get started 👇

Dexcelerate

13,020 views • 2 years ago

Introducing the latest version of FinTarget: Simplifying Trading Automation. On 26th Jan 2023 we launched first version of Target a free to use platform with basic automation capabilities. After 10 months of extensive development and improvements I am happy to introduce you to the latest version of FinTarget. The current version comes with the latest features of 📕Automation of Time Based Strategies 📊Automation of Strategies (Discretionary) 🚀Automated Placing of Leg based StopLoss and Target 👍Trailing Stoploss 📱Strike Selection on Closest Premium 📌Wait and Trade 📊Re-entry and Re-Execution 💡Rolling Strategies 📚Strategy level Stoploss and Target 🌐Live Monitoring of Trades 📌Trade Updates and Notifications You can now use Fintarget for free with the following brokers: 1) Firstock (Free execution of Unlimited Strategies) 2) Zerodha (Free execution of 1 Strategy/ Day) 3) Angelone (Free execution of 1 Strategy/ Day) 4) Fyers and Finvasia (Coming Soon) Start Automating your Trades with today

Introducing the latest version of FinTarget: Simplifying Trading Automation. On 26th Jan 2023 we launched first version of Target a free to use platform with basic automation capabilities. After 10 months of extensive development and improvements I am happy to introduce you to the latest version of FinTarget. The current version comes with the latest features of 📕Automation of Time Based Strategies 📊Automation of Strategies (Discretionary) 🚀Automated Placing of Leg based StopLoss and Target 👍Trailing Stoploss 📱Strike Selection on Closest Premium 📌Wait and Trade 📊Re-entry and Re-Execution 💡Rolling Strategies 📚Strategy level Stoploss and Target 🌐Live Monitoring of Trades 📌Trade Updates and Notifications You can now use Fintarget for free with the following brokers: 1) Firstock (Free execution of Unlimited Strategies) 2) Zerodha (Free execution of 1 Strategy/ Day) 3) Angelone (Free execution of 1 Strategy/ Day) 4) Fyers and Finvasia (Coming Soon) Start Automating your Trades with today

Saketh R

57,312 views • 2 years ago

The SECRET to Winning Player Prop Bets (2 Strategies That ACTUALLY Work): Video by sharp/pro sports bettor Billy C 👇

The SECRET to Winning Player Prop Bets (2 Strategies That ACTUALLY Work): Video by sharp/pro sports bettor Billy C 👇

OddsJam.com

342,767 views • 1 month ago

The real future of search marketing isn't really optimizing for LLM visibility, that's short term. It's optimizing for Agent Decisions. ADO. Agent Decision Optimization. I wrote about this a few weeks back, but I think this video from Aravind explains why this will be the case.

The real future of search marketing isn't really optimizing for LLM visibility, that's short term. It's optimizing for Agent Decisions. ADO. Agent Decision Optimization. I wrote about this a few weeks back, but I think this video from Aravind explains why this will be the case.

The Boring Marketer

34,370 views • 1 year ago

SINT is an advanced AI agent engineered to evolve and adapt to your needs. From automating daily routines and optimizing trading strategies to excelling in gaming and connecting across platforms, SINT learns and improves with every interaction. Join waitlist now! #sint #ai

SINT is an advanced AI agent engineered to evolve and adapt to your needs. From automating daily routines and optimizing trading strategies to excelling in gaming and connecting across platforms, SINT learns and improves with every interaction. Join waitlist now! #sint #ai

SINT

42,233 views • 1 year ago

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a test, and then enters a loop where it generates and iterates on the code until the tests pass source below

Steve (Builder.io)

544,171 views • 2 years ago

📚 Build Deep Research Agent: From Question to Insight Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete. 💡 Key workflow nodes include: 1) Start: capture the research topic and the loop budget 2) Exa Answer: gather background terminology 3) Intent LLM: clarify the real research goal 4) Loop: drive the iterative cycles 5) Reasoning LLM: frame better follow-up questions 6) Agent: execute searches, extract content, and reflect 7) Variable Assigner: update the state after each pass 8) Final Summary: synthesize a Markdown report with citations Teams using this template cut research time dramatically and surface insights competitors miss. Learn to implement this workflow:

📚 Build Deep Research Agent: From Question to Insight Complex research rarely fits in one search box. The Deep Research workflow built with Dify Iterates, reasons, and sources until the answer is complete. 💡 Key workflow nodes include: 1) Start: capture the research topic and the loop budget 2) Exa Answer: gather background terminology 3) Intent LLM: clarify the real research goal 4) Loop: drive the iterative cycles 5) Reasoning LLM: frame better follow-up questions 6) Agent: execute searches, extract content, and reflect 7) Variable Assigner: update the state after each pass 8) Final Summary: synthesize a Markdown report with citations Teams using this template cut research time dramatically and surface insights competitors miss. Learn to implement this workflow:

Dify

22,470 views • 1 year ago

The agentic web needs agent-ready tools. We spent a decade optimizing websites for humans. Lighthouse was built by humans to measure human experience. Ora is powered *by real world agents* that rank the real agentic experience. Instead of guessing:

The agentic web needs agent-ready tools. We spent a decade optimizing websites for humans. Lighthouse was built by humans to measure human experience. Ora is powered by real world agents that rank the real agentic experience. Instead of guessing:

Liad Yosef

24,479 views • 2 months ago

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.

ChatGPT can write you a thousand trading strategies from one sentence. 999 will quietly bleed your account dry. Every single one of them looks like a winner. One method pulls the real one out. Quant desks have run it for years. It's called loop engineering. It's not a smarter prompt. It's a loop: generate a strategy, test it, score why it failed, feed that back, and run it again until one survives data it has never seen. Man Group runs $150 billion. They built an AI that writes and tests hundreds of strategies a week. And second agent whose only job is to hunt the ones that secretly overfit and kill them before a cent goes live. > describe an idea -> backtest 5 years in 12 seconds > read why it died -> feed that back in > run it again until one survives data it never saw AI can write a thousand strategies. Loop engineering is the only thing that tells you which one was ever real. 89% of retail lost money in 2025. Almost none of it from bad ideas. All of it from trading the first guess and never running it through backtest loop. Horizon just put the whole thing in a chat box, free while the beta's open: You're not losing to smarter traders. You're losing to the ones who opened the tab. Anyone can generate a strategy now. Almost no one runs the loop that proves it. That gap is the whole edge. You'll mean to check it later. Later is a "waitlist closed" page.

cvxv666

165,663 views • 9 days ago

Advanced trading strategies without giving up your keys? Yes, actually. Smart Account on @Wallet lets you set limit orders, auto TP/SL, and copy trade. Here’s how to set it up👇

Advanced trading strategies without giving up your keys? Yes, actually. Smart Account on @Wallet lets you set limit orders, auto TP/SL, and copy trade. Here’s how to set it up👇

OKX

75,315 views • 5 months ago