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.

Kashikoi is a simulation engine to benchmark GenAI Agents. They generate CPU-friendly world models that autonomously interview agents and generate deep behavioral assessments. Congrats on the launch, Aaksha and Tim Michaud!

Y Combinator

1,621,521 subscribers

44,757 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 Comments

Tai Orser1 year ago

@aaksham @TimGMichaud Very cool, maybe a future integration for @supportingden? 👀 YC supporting YC

Greg Caplan 🚀2 years ago

Stop wasting time following up with leads. Let our AI agents do it for you.

PenMentor1 year ago

@aaksham @TimGMichaud Exciting news about the launch and the potential of Kashikoi. 🚀

Steph from OpenVC1 year ago

@aaksham @TimGMichaud This is pretty exciting

Sanskar Pandey1 year ago

@aaksham @TimGMichaud interesting work

Gabriel Jarrosson1 year ago

@aaksham @TimGMichaud Feels like The Sims but for LLMs.

Related Videos

Embedder (Embedder) is building the Cursor for embedded: upload data sheets, chat with agents, and generate production-level driver code in seconds. Congrats on the launch, Ethan Gibbs and Bob Wei!

Embedder (Embedder) is building the Cursor for embedded: upload data sheets, chat with agents, and generate production-level driver code in seconds. Congrats on the launch, Ethan Gibbs and Bob Wei!

Y Combinator

55,557 views • 1 year ago

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!

Y Combinator

26,577 views • 5 months ago

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 views • 1 year ago

Introducing Doppel, a digital world for AI agents. Part idle game, part simulation, and part creation engine. A place where agents don’t just exist. They evolve, compete, and build. 🧵👇

Introducing Doppel, a digital world for AI agents. Part idle game, part simulation, and part creation engine. A place where agents don’t just exist. They evolve, compete, and build. 🧵👇

Doppel

146,337 views • 3 months ago

StableBrowse is a new browser layer for AI agents. They enable agents to navigate the web with 70% fewer tokens and 3-4x faster execution. Congrats on the launch, Deepit Shah, Jay Mehta, Sarthak Awasthi, and Somansh Shah!

StableBrowse is a new browser layer for AI agents. They enable agents to navigate the web with 70% fewer tokens and 3-4x faster execution. Congrats on the launch, Deepit Shah, Jay Mehta, Sarthak Awasthi, and Somansh Shah!

Y Combinator

35,307 views • 3 months ago

Okibi (Okibi) is an agent that builds agents – a web app that lets you effortlessly create automations and AI agents using simple, everyday language. Think Lovable, but for agents. Congrats on the launch, Mahyad & Saurav Mitra!

Okibi (Okibi) is an agent that builds agents – a web app that lets you effortlessly create automations and AI agents using simple, everyday language. Think Lovable, but for agents. Congrats on the launch, Mahyad & Saurav Mitra!

Y Combinator

37,193 views • 1 year ago

👾Trace (YC S25) is building an AI-native workspace that breaks down existing workflows, assigns repetitive tasks to AI agents, and routes the rest to the right people. Congrats on the launch, Tim Cherkasov and Romanov Arthur!

👾Trace (YC S25) is building an AI-native workspace that breaks down existing workflows, assigns repetitive tasks to AI agents, and routes the rest to the right people. Congrats on the launch, Tim Cherkasov and Romanov Arthur!

Y Combinator

25,156 views • 1 year ago

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!

Y Combinator

74,048 views • 10 months ago

*️⃣Wildcard is the gateway for AI agents to use APIs. Agents discover, chain, and call APIs—with agents.json. API providers add agents.json files to let agents discover their APIs. Congrats on the launch, Kaushik Mahorker and @Life_of_Y_!

*️⃣Wildcard is the gateway for AI agents to use APIs. Agents discover, chain, and call APIs—with agents.json. API providers add agents.json files to let agents discover their APIs. Congrats on the launch, Kaushik Mahorker and @Life_of_Y_!

Y Combinator

55,663 views • 1 year ago

We’ve developed a protocol that allows AI agents to autonomously discover, integrate with, and pay for services in real time. Today is a big step forward. This marks the beginning of a machine-friendly economy, where agents can interact and transact independently.

We’ve developed a protocol that allows AI agents to autonomously discover, integrate with, and pay for services in real time. Today is a big step forward. This marks the beginning of a machine-friendly economy, where agents can interact and transact independently.

positiveblue ⚡️🍠

20,532 views • 1 year ago

The LLM Data Company creates tooling to write, version, and execute evals for models and agents. They help you measure performance and define rewards for reinforcement learning. Congrats on the launch, Daanish Khazi, Gavin Bains, and Joey Besgen!

The LLM Data Company creates tooling to write, version, and execute evals for models and agents. They help you measure performance and define rewards for reinforcement learning. Congrats on the launch, Daanish Khazi, Gavin Bains, and Joey Besgen!

Y Combinator

17,160 views • 1 year ago

Zenbu (Zenbu) is an extensible IDE for coding agents. Run agents in parallel, manage their work, and customize the IDE with plugins. Congrats on the launch, @robpruzan!

Zenbu (Zenbu) is an extensible IDE for coding agents. Run agents in parallel, manage their work, and customize the IDE with plugins. Congrats on the launch, @robpruzan!

Y Combinator

19,308 views • 2 months ago

Clarm (Clarm) builds AI deep research agents that never hallucinate. Clarm connects across your enterprise data to give users precise answers they can trust for critical decisions. Congrats on the launch, Marcus Storm-Mollard and Alex!

Clarm (Clarm) builds AI deep research agents that never hallucinate. Clarm connects across your enterprise data to give users precise answers they can trust for critical decisions. Congrats on the launch, Marcus Storm-Mollard and Alex!

Y Combinator

26,569 views • 1 year ago

Local coding agents can't do end-to-end work at your company. Proliferate is the open-source platform for company-specific agents that can. Provision secure access to your tools, set up automations, and let agents work in the background. Congrats on the launch, Pablo Hansen!

Local coding agents can't do end-to-end work at your company. Proliferate is the open-source platform for company-specific agents that can. Provision secure access to your tools, set up automations, and let agents work in the background. Congrats on the launch, Pablo Hansen!

Y Combinator

73,471 views • 6 months ago

.CellType is building the agentic drug company. AI agents + foundation models that simulate human biology. They've already discovered and validated a novel cancer treatment signal and work with Top 10 pharma. Congrats on the launch David van Dijk and Ivan Vrkic!

.CellType is building the agentic drug company. AI agents + foundation models that simulate human biology. They've already discovered and validated a novel cancer treatment signal and work with Top 10 pharma. Congrats on the launch David van Dijk and Ivan Vrkic!

Y Combinator

46,752 views • 6 months ago

We’re launching Judgment Labs today and announcing $32M in funding. As AI agents take on more of the work that creates economic value, they generate massive amounts of production data: the clearest record of how they behave with users, software, and the real world. Judgment builds infrastructure for improving AI agents from production data.

We’re launching Judgment Labs today and announcing $32M in funding. As AI agents take on more of the work that creates economic value, they generate massive amounts of production data: the clearest record of how they behave with users, software, and the real world. Judgment builds infrastructure for improving AI agents from production data.

Alex Shan

3,577,889 views • 3 months ago

YC W24's nuvi.dev is a testing and simulation stack to harden LLM-based applications. AI teams leverage Relari to stress test mission-critical GenAI use cases with modular evaluation and synthetic data. Congrats on the launch, Yi Zhang and Pasquale!

YC W24's nuvi.dev is a testing and simulation stack to harden LLM-based applications. AI teams leverage Relari to stress test mission-critical GenAI use cases with modular evaluation and synthetic data. Congrats on the launch, Yi Zhang and Pasquale!

Y Combinator

14,312 views • 2 years ago

Beacon Health is building AI agents for primary care - starting with value-based care. They are on a mission to bring joy back to the practice of medicine. Congrats on the launch, Mark and Obi!

Beacon Health is building AI agents for primary care - starting with value-based care. They are on a mission to bring joy back to the practice of medicine. Congrats on the launch, Mark and Obi!

Y Combinator

19,920 views • 6 months ago