Loading video...

Video Failed to Load

Go Home

Launching a public agent sandbox for spatial biology. Five demo flows tailored to specific kits/machines Try it now: This is a shippable intermediary towards reliable and widely deployed agentic systems used to make expensive scientific decisions.

kenbwork's profile picture

Kenny Workman

7,275 subscribers

21,160 views • 8 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:
1:27

Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:

Kenny Workman

114,480 views • 10 months ago

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:
0:28

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:

Liquid AI

33,738 views • 2 months ago

AI is an agent able to make its own decisions and decide how it acts. Are we ready to live in a world where even our coffee machines make decisions on our behalf? With Luciano Huck. Watch the whole thing here:
1:04

AI is an agent able to make its own decisions and decide how it acts. Are we ready to live in a world where even our coffee machines make decisions on our behalf? With Luciano Huck. Watch the whole thing here:

Yuval Noah Harari

34,634 views • 3 months ago

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!
2:01

New course: Nvidia's NeMo Agent Toolkit: Making Agents Reliable, taught by Brian McBrayer 🐬 from NVIDIA. Many teams struggle to turn agent demos into reliable systems that are ready for production. This short course teaches you to harden agentic workflows into reliable systems using Nvidia's open-source NeMo Agent Toolkit (NAT). Whether you built your agent in raw Python or using a framework like LangGraph, or CrewAI, NAT provides building blocks for observability, evaluation, and deployment that turn proofs-of-concept into production-ready systems. NAT makes it easy to troubleshoot and optimize agent performance with execution traces, systematic evaluations, and CI/CD integration. Skills you'll gain: - Build configuration-driven agent workflows with REST APIs and minimal code - Add observability with tracing to visualize agent reasoning and debug performance bottlenecks - Create systematic evaluations using gold-standard datasets to measure and improve agent reliability - Deploy multi-agent systems with authentication, rate limiting, and professional web interfaces - Orchestrate agents from different frameworks to collaborate on complex tasks Join and learn how to turn agent demos into reliable systems!

Andrew Ng

64,150 views • 8 months ago

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien
3:40

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,518 views • 4 months ago

What do you think about this?? Why hasn’t Candace Owens used the same software that she used to make up her mind and convince herself and many of her fans that Emmanuel Macron’s wife is a man. So, is this software as reliable as you touted?? If it is NOT as reliable then did you just make that episode to make money for no reason regardless of who it affected? If it IS reliable, would you stop questioning if Tyler was the one that got up on that roof and not a look-a-like? Just asking questions! Go ahead and try it for yourself with those two images. 😊 Receipts to follow.
4:52

What do you think about this?? Why hasn’t Candace Owens used the same software that she used to make up her mind and convince herself and many of her fans that Emmanuel Macron’s wife is a man. So, is this software as reliable as you touted?? If it is NOT as reliable then did you just make that episode to make money for no reason regardless of who it affected? If it IS reliable, would you stop questioning if Tyler was the one that got up on that roof and not a look-a-like? Just asking questions! Go ahead and try it for yourself with those two images. 😊 Receipts to follow.

The “Good” Woman

82,295 views • 1 month ago

Experiment 34 v0.4 is now public for everyone, make sure to give it a try over here🫴✨ Link:
0:40

Experiment 34 v0.4 is now public for everyone, make sure to give it a try over here🫴✨ Link:

Hito

22,511 views • 7 months ago

This web demo lets you create a portal to your own AI-generated world 👇 The Off-Axis spatial Kit built by Johannes Tscharn and Ian Curtis now supports the import function for your own splat. To get it, make sure to reach out to Ferhan Özkan and the SensAI Hackademy team, who have been building end-to-end workflow Kits for Unity, Unreal Engine and #WebXR.
0:27

This web demo lets you create a portal to your own AI-generated world 👇 The Off-Axis spatial Kit built by Johannes Tscharn and Ian Curtis now supports the import function for your own splat. To get it, make sure to reach out to Ferhan Özkan and the SensAI Hackademy team, who have been building end-to-end workflow Kits for Unity, Unreal Engine and #WebXR.

Gabriele Romagnoli

36,773 views • 4 months ago

Here’s our application video to Y Combinator s26: agentic body count detector We built a 4 agent committee to analyze how many body count people think you have based on your appearance We are pushing the frontier of AI for Biology with the aim to increase birth rate, which is a serious problem human race is facing right now It comes with a full analysis of your body count as well as ways to increase it and therefore make sure we can have more babies in our society Try now link in comment
1:21

Here’s our application video to Y Combinator s26: agentic body count detector We built a 4 agent committee to analyze how many body count people think you have based on your appearance We are pushing the frontier of AI for Biology with the aim to increase birth rate, which is a serious problem human race is facing right now It comes with a full analysis of your body count as well as ways to increase it and therefore make sure we can have more babies in our society Try now link in comment

Allen Wang

101,045 views • 3 months ago

Hello #Datafam, I built an agent performance dashboard. This dashboard provides managers with a clear view of agent performance, resolution time and service levels, making it easy to identify trends and make better decisions. Tool used: Power BI Explore:
0:33

Hello #Datafam, I built an agent performance dashboard. This dashboard provides managers with a clear view of agent performance, resolution time and service levels, making it easy to identify trends and make better decisions. Tool used: Power BI Explore:

Sid✨

16,472 views • 11 months ago

From sequence to structure, in one sentence.⚡ Today’s Agent Spotlight: Boltz-2 Structure Prediction Agent on ASI:One. Built on Massachusetts Institute of Technology (MIT)’s cutting-edge Boltz-2 model and deployed via NVIDIA's API, this agent generates 3D biomolecular structures just from a natural language prompt. Supports proteins, DNA, RNA, ligands, constraints, and even MSA data. Ideal for drug discovery, molecular biology, and biotech research. Try now: Link to Agent: Watch 👇
2:09

From sequence to structure, in one sentence.⚡ Today’s Agent Spotlight: Boltz-2 Structure Prediction Agent on ASI:One. Built on Massachusetts Institute of Technology (MIT)’s cutting-edge Boltz-2 model and deployed via NVIDIA's API, this agent generates 3D biomolecular structures just from a natural language prompt. Supports proteins, DNA, RNA, ligands, constraints, and even MSA data. Ideal for drug discovery, molecular biology, and biotech research. Try now: Link to Agent: Watch 👇

Fetch.ai

14,034 views • 1 year ago

We are proud to announce the launch of our platform and the THREE initial agents: the Data Aggregation Agent, Sentiment Analysis Agent and Risk Manager Agent. This demo clip is a culmination of months of hard work and dedication to our vision. The platform have now entered a private alpha test which will be followed by a public beta. Tomorrow we will be doing a live streamed demo of the platform as it exists right now and will also be opening our waitlist to the general public. Thank you for your patience, belief and support. $cainam
0:39

We are proud to announce the launch of our platform and the THREE initial agents: the Data Aggregation Agent, Sentiment Analysis Agent and Risk Manager Agent. This demo clip is a culmination of months of hard work and dedication to our vision. The platform have now entered a private alpha test which will be followed by a public beta. Tomorrow we will be doing a live streamed demo of the platform as it exists right now and will also be opening our waitlist to the general public. Thank you for your patience, belief and support. $cainam

Cainam Ventures

12,101 views • 1 year ago

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?
3:29

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 views • 1 year ago

🚨 RFK Jr. just opened the floodgates for countless researchers to massively reshape the food industry “Just Because a Chemical Is Widely Used in our Food Doesn’t Mean It’s Safe”— for example, BHT & ADA” FDA will for the first time continuously review chemicals already approved in the US food supply, replacing the decades-old “set-it-and-forget-it” system with ongoing scientific oversight Agency will evaluate risks earlier, act faster to protect public health, or make findings public for full transparency and accountability Specifically re-evaluating two widely used chemicals: BHT (preservative in cereals, frozen foods, and packaged goods) and ADA (used in flour processing, bread products, and food contact materials) RFK Jr. stresses these substances are widely used but that does not establish safety, issuing a formal request for new data from researchers, industry, and the public via
2:17

🚨 RFK Jr. just opened the floodgates for countless researchers to massively reshape the food industry “Just Because a Chemical Is Widely Used in our Food Doesn’t Mean It’s Safe”— for example, BHT & ADA” FDA will for the first time continuously review chemicals already approved in the US food supply, replacing the decades-old “set-it-and-forget-it” system with ongoing scientific oversight Agency will evaluate risks earlier, act faster to protect public health, or make findings public for full transparency and accountability Specifically re-evaluating two widely used chemicals: BHT (preservative in cereals, frozen foods, and packaged goods) and ADA (used in flour processing, bread products, and food contact materials) RFK Jr. stresses these substances are widely used but that does not establish safety, issuing a formal request for new data from researchers, industry, and the public via

MJTruthUltra

31,699 views • 3 months ago

ok on why i think Tempo is the future just deployed a demo. the chain is a new paradigm if you like EVM. try it on tempai.town (link below) then mint your free NFT (first on tempo?) > passkey sign in > batch tx > one click bridge > delegate API/agent keys if you are used to ETH UX shenanigan this is next level
0:25

ok on why i think Tempo is the future just deployed a demo. the chain is a new paradigm if you like EVM. try it on tempai.town (link below) then mint your free NFT (first on tempo?) > passkey sign in > batch tx > one click bridge > delegate API/agent keys if you are used to ETH UX shenanigan this is next level

nicolette 🐈‍⬛🔪

29,678 views • 5 months ago

Agent Spotlight: Meeting Preparation Agent Today's featured agent on ASI:One is a serious upgrade for your next big meeting.⚡ Built using CrewAI, this agent works as a team of 4 specialists: researching the person you're meeting, analyzing industry trends, and generating tailored talking points and strategic questions. Just drop in the meeting details (who, why, what for), and the agent takes care of the prep. Try now: Link to agent: Watch 👇
4:34

Agent Spotlight: Meeting Preparation Agent Today's featured agent on ASI:One is a serious upgrade for your next big meeting.⚡ Built using CrewAI, this agent works as a team of 4 specialists: researching the person you're meeting, analyzing industry trends, and generating tailored talking points and strategic questions. Just drop in the meeting details (who, why, what for), and the agent takes care of the prep. Try now: Link to agent: Watch 👇

Fetch.ai

14,984 views • 1 year ago

.Timothy T. from FilOz explains that DePIN networks are changing how infrastructure is deployed. Many of them now collect, store, and monetize data, much of it used for AI training. Filecoin Onchain Cloud provides a reliable storage layer for this data.
0:43

.Timothy T. from FilOz explains that DePIN networks are changing how infrastructure is deployed. Many of them now collect, store, and monetize data, much of it used for AI training. Filecoin Onchain Cloud provides a reliable storage layer for this data.

Filecoin

116,389 views • 8 months ago