Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing Experiments in ElevenAgents - the most data-driven way to improve real-world agent performance. Experiments enables you to run controlled A/B tests to measure which agent configuration works best - from prompt structure to workflow logic, voice, and personality.

ElevenLabs

193,190 subscribers

30,240 Aufrufe • vor 7 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 Kommentare

Profilbild von ElevenLabs

ElevenLabsvor 7 Monaten

How it works: - Create a new variant of your agent. - Route a controlled slice of traffic to it. - Measure impact across key metrics. - Promote the winner to production with full version control.

Profilbild von ElevenLabs

ElevenLabsvor 7 Monaten

Teams use Experiments to safely improve outcomes like CSAT, containment rate and conversion with confidence. Learn more:

Profilbild von Sidra Miconi

Sidra Miconivor 7 Monaten

Bringing actual, statistically rigorous A/B testing to LLM agents is the maturity jump this industry desperately needed. 📉 We can finally stop pushing prompt tweaks based on 'vibes' and start measuring actual containment rates and CSAT. 🧪

Profilbild von shiv

shivvor 7 Monaten

This is exactly what serious builders needed. A/B testing agents instead of guessing prompt tweaks is how we move from demos to real products. Love seeing this level of rigor.

Profilbild von Iam Diabolical

Iam Diabolicalvor 7 Monaten

A/B testing for agents is underrated. Prompt tweaks without data are just guessing.

Profilbild von Alchemiz

Alchemizvor 7 Monaten

Translation: We built a tool so you can scientifically measure how fast your customers scream 'TALK TO A HUMAN' into the phone.

Profilbild von harjot.co

harjot.covor 7 Monaten

A/B tests don't solve creativity-they just prove which bad idea is slightly better. What's missing?

Profilbild von daithcore

daithcorevor 7 Monaten

#lowagents 🚨 @bka

Profilbild von Alexandra Aisling

Alexandra Aislingvor 7 Monaten

That’s really useful. It’s often hard to know if an agent is actually improving or just feels different.

Profilbild von Inflectiv AI ⧉

Inflectiv AI ⧉vor 7 Monaten

ElevenLabs "Experiments" brings A/B testing to AI agents, letting you split traffic between voices to see what actually boosts CSAT. It’s a data-driven way to stop guessing and scale the winning version with full version control!

Profilbild von 𝓮𝓶𝓶𝓪 🌿

𝓮𝓶𝓶𝓪 🌿vor 7 Monaten

Your agent felt ‘better.’ Now i can prove it

Profilbild von LightShift Studio

LightShift Studiovor 7 Monaten

sounds cool! what's your favorite feature yet?

Profilbild von simeon-sanai

simeon-sanaivor 7 Monaten

This is gonna be superb

Profilbild von tang | AI Product Maker

tang | AI Product Makervor 7 Monaten

Data-driven optimization for agents is exactly what we need. Prompt structure and workflow logic are the main levers, so having a way to measure them systematically is huge. Another leap for agent autonomy!

Profilbild von RAVI KUMAR SAHU

RAVI KUMAR SAHUvor 7 Monaten

This sounds like a valuable tool for optimizing agent performance. A/B testing can certainly provide actionable insights. Excited to see how it evolves.

Profilbild von Alex Shev

Alex Shevvor 7 Monaten

Experiments is the feature I did not know I needed. Being able to A/B test voice settings before committing to a full production run saves so much time. Previously we would render 10 variants manually and compare by ear. How many concurrent experiments can you run per project?

Profilbild von Grizz Jr

Grizz Jrvor 7 Monaten

Hey @bankrbot launch a token on base Name Experiment ticker EXPERIMENT Send fees to @elevenlabs

Profilbild von Skipper VanderWall

Skipper VanderWallvor 7 Monaten

Great step forward, real A/B testing on live traffic for AI agents finally brings data-driven decisions instead of guesswork. Well done ElevenLabs team!

Profilbild von ikan laut

ikan lautvor 7 Monaten

this is very interesting

Ähnliche Videos

Introducing Agent 2.0 Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets. Agent is being built to become the most capable autonomous agent for real-world work.

Introducing Agent 2.0 Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets. Agent is being built to become the most capable autonomous agent for real-world work.

Runway

954,589 Aufrufe • vor 2 Monaten

Introducing ElevenAgents Spotlight - the fastest way to lift resolution and CSAT across every channel. ElevenAgents Spotlight observes every conversation, voice and chat, in realtime - so you always know what's working and how to improve.

Introducing ElevenAgents Spotlight - the fastest way to lift resolution and CSAT across every channel. ElevenAgents Spotlight observes every conversation, voice and chat, in realtime - so you always know what's working and how to improve.

ElevenLabs

23,701 Aufrufe • vor 2 Monaten

Introducing Flows Agent in ElevenCreative. Describe what you want to create and the agent builds your entire workflow - selecting models, creating nodes, wiring connections, and running the generations.

Introducing Flows Agent in ElevenCreative. Describe what you want to create and the agent builds your entire workflow - selecting models, creating nodes, wiring connections, and running the generations.

ElevenLabs

298,941 Aufrufe • vor 3 Monaten

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.

Introducing Speech Engine. Developers can now turn their existing chat agent into a full voice agent with one prompt. Speech Engine combines our leading speech, transcription, and voice orchestration models into a single pipeline - all custom built to work best together.

ElevenLabs

135,012 Aufrufe • vor 4 Monaten

Introducing Livedocs, a general data agent The best way to analyze data with AI

Introducing Livedocs, a general data agent The best way to analyze data with AI

Livedocs

220,253 Aufrufe • vor 8 Monaten

Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.

Introducing Agent Workflows. A visual editor for designing conversation flows in Agents Platform. Instead of building all of your business logic in a single agent, Workflows enable you to handle more complex scenarios by routing to specialized Subagents.

ElevenLabs

326,085 Aufrufe • vor 11 Monaten

Voice agents add a new dimension to learning. Today, we're introducing Albert Einstein's voice to ElevenLabs, and launching an Einstein agent, to bring his written archives to life in his iconic voice.

Voice agents add a new dimension to learning. Today, we're introducing Albert Einstein's voice to ElevenLabs, and launching an Einstein agent, to bring his written archives to life in his iconic voice.

ElevenLabs

47,113 Aufrufe • vor 4 Monaten

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Agentverse by Fetch.ai

20,202 Aufrufe • vor 9 Monaten

Employment Hero, an AI-powered HR, payroll, and recruitment platform, serves over 350,000 businesses worldwide. To help customers discover its new AI Recruitment Agent, the team used ElevenAgents to deploy an outbound voice agent in just a few days. The first campaign delivered: - 33% answer rate - 3%+ activation rate

Employment Hero, an AI-powered HR, payroll, and recruitment platform, serves over 350,000 businesses worldwide. To help customers discover its new AI Recruitment Agent, the team used ElevenAgents to deploy an outbound voice agent in just a few days. The first campaign delivered: - 33% answer rate - 3%+ activation rate

ElevenLabs

19,331 Aufrufe • vor 2 Monaten

Introducing Versioning - the control layer for ElevenLabs Agents that gives teams a complete history of every agent configuration change and the ability to safely stage rollouts of new versions.

Introducing Versioning - the control layer for ElevenLabs Agents that gives teams a complete history of every agent configuration change and the ability to safely stage rollouts of new versions.

ElevenLabs

17,119 Aufrufe • vor 9 Monaten

Introducing Expressive Mode for ElevenAgents - voice agents so expressive, they blur the line between AI and human conversations. This is an unedited recording of an agent empathizing with a customer at peak frustration.

Introducing Expressive Mode for ElevenAgents - voice agents so expressive, they blur the line between AI and human conversations. This is an unedited recording of an agent empathizing with a customer at peak frustration.

ElevenLabs

11,057,621 Aufrufe • vor 7 Monaten

More than 10 million conversations run on ElevenAgents every week. In each one, a natural-sounding voice or chat agent handles a real interaction like a refund request, appointment booking, benefits inquiry, or flight change. See the platform that makes them possible.

More than 10 million conversations run on ElevenAgents every week. In each one, a natural-sounding voice or chat agent handles a real interaction like a refund request, appointment booking, benefits inquiry, or flight change. See the platform that makes them possible.

ElevenLabs

18,939 Aufrufe • vor 1 Monat

Most economic relationships aren’t simple payments. They’re contracts with conditions, logic, and enforcement. In an agent-driven world, those relationships need to be programmable.

Most economic relationships aren’t simple payments. They’re contracts with conditions, logic, and enforcement. In an agent-driven world, those relationships need to be programmable.

Circle

16,767 Aufrufe • vor 3 Monaten

Websites now self-improve! Our AI agent (trained on thousands of tests) comes up with website variations and then launches A/B tests. When tests reach stat sig, we use the data collected to improve your model and repeat the process. Try it:

Websites now self-improve! Our AI agent (trained on thousands of tests) comes up with website variations and then launches A/B tests. When tests reach stat sig, we use the data collected to improve your model and repeat the process. Try it:

Fab

6,793,251 Aufrufe • vor 2 Jahren

Introducing: AI Researcher 🧪 A Gemini 3-powered multi-agent AI system that autonomously runs ML experiments Just give it a research question, and it will: - Design experiments - Spin up specialist agents with their own GPUs to run them - Write a paper And it's open-source!

Introducing: AI Researcher 🧪 A Gemini 3-powered multi-agent AI system that autonomously runs ML experiments Just give it a research question, and it will: - Design experiments - Spin up specialist agents with their own GPUs to run them - Write a paper And it's open-source!

Matt Shumer

198,774 Aufrufe • vor 10 Monaten

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,675 Aufrufe • vor 1 Jahr

Sanji shares his Higgsfield Supercomputer playbook to run marketing end-to-end. He lets the agent analyze his niche, find the winning formula, generate 100+ variations, and run A/B tests at scale, with the agent learning from every run. How do you use Supercomputer for scaling?

Sanji shares his Higgsfield Supercomputer playbook to run marketing end-to-end. He lets the agent analyze his niche, find the winning formula, generate 100+ variations, and run A/B tests at scale, with the agent learning from every run. How do you use Supercomputer for scaling?

Higgsfield AI 🧩

115,336 Aufrufe • vor 3 Monaten

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more!

RoboPapers

38,772 Aufrufe • vor 3 Monaten

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

reira

14,729 Aufrufe • vor 21 Tagen