Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Today, we’re launching Duet Autopilot, the first verified self-improving AI agent for CX! It automatically analyzes conversations, identifies opportunities for improvement, validates updates, and surfaces them for human review, improving itself with each cycle. 👇

thejessezhang's profile picture

Jesse Zhang

102,528 subscribers

13,543 Aufrufe • vor 4 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

5 Kommentare

Profilbild von Jesse Zhang
Jesse Zhangvor 4 Monaten

AI is moving toward longer-running autonomous agents vs quick inference calls because the models are getting smarter. You don't always have time to use a reasoning model but Duet Autopilot is a super clever way to leverage them.

Profilbild von Jesse Zhang
Jesse Zhangvor 4 Monaten

Full post if you're curious!

Profilbild von Anurag yadav creator of hybrid octopus OS
Anurag yadav creator of hybrid octopus OSvor 4 Monaten

@Accel Hey am founder of hybrid octopus OS let's connect.

Profilbild von Leon
Leonvor 4 Monaten

wait, it reviews itself too? 🤨

Profilbild von Anurag yadav creator of hybrid octopus OS
Anurag yadav creator of hybrid octopus OSvor 4 Monaten

@Accel Most companies are building AI tools. I'm exploring a human-centric intelligence layer that connects fragmented AI capabilities into one continuous system focused on understanding, guidance, trust, and growth "If AI could solve only ONE problem in your life permanently

Ähnliche Videos

Redapto ( builds self-improving systems for Customer Support teams. It audits 100% of customer conversations, identifies quality gaps, and auto-updates knowledge bases, boosting CSAT and unlocking millions in retained revenue. Congrats on the launch, Cheril Shah & Anirudh Pupneja!
0:38

Redapto ( builds self-improving systems for Customer Support teams. It audits 100% of customer conversations, identifies quality gaps, and auto-updates knowledge bases, boosting CSAT and unlocking millions in retained revenue. Congrats on the launch, Cheril Shah & Anirudh Pupneja!

Y Combinator

13,751 Aufrufe • vor 11 Monaten

Today we’re launching Prava Pay- Cards for your AI agent. Coffee, sneakers or subscriptions - your AI agent can now buy anything online by itself, all within the limits you set for it. Works with OpenClaw, Hermes, Claude Code out of the box.
0:25

Today we’re launching Prava Pay- Cards for your AI agent. Coffee, sneakers or subscriptions - your AI agent can now buy anything online by itself, all within the limits you set for it. Works with OpenClaw, Hermes, Claude Code out of the box.

Sushant

61,897 Aufrufe • vor 4 Monaten

Atla (Atla) is the improvement engine for AI agents. Instead of just surfacing agent traces, Atla automatically identifies your agent's most critical failure patterns and suggests targeted fixes.
1:36

Atla (Atla) is the improvement engine for AI agents. Instead of just surfacing agent traces, Atla automatically identifies your agent's most critical failure patterns and suggests targeted fixes.

Y Combinator

13,141 Aufrufe • vor 1 Jahr

In customer experience, speed and clarity go together. 📞 That’s why Filipino CX teams trust Krisp Accent Conversion. It improves communication instantly reducing friction and improving customer satisfaction. 📉 Fewer repeat questions 📈 Faster resolutions 🎧 Clear, human conversations 🔐 Fully private AI Better calls start with better clarity. 🔗 📞 Voice clarity updates & CX innovation at Krisp #CX #BPO #VoiceAI
2:07

In customer experience, speed and clarity go together. 📞 That’s why Filipino CX teams trust Krisp Accent Conversion. It improves communication instantly reducing friction and improving customer satisfaction. 📉 Fewer repeat questions 📈 Faster resolutions 🎧 Clear, human conversations 🔐 Fully private AI Better calls start with better clarity. 🔗 📞 Voice clarity updates & CX innovation at Krisp #CX #BPO #VoiceAI

Amelia Maya

31,969 Aufrufe • vor 8 Monaten

I’ve been looking forward to today for 3 years Today we’re announcing Foundation - Chroma’s solution to memory Our research preview of this technology builds self-improving memory from your agent sessions. Try it out at
2:29

I’ve been looking forward to today for 3 years Today we’re announcing Foundation - Chroma’s solution to memory Our research preview of this technology builds self-improving memory from your agent sessions. Try it out at

Jeff Huber

231,573 Aufrufe • vor 1 Monat

Today we're introducing Wave. A proactive product agent that helps teams build self-improving products. Every product team runs the same loop. Build, ship, use, learn. AI has made building and shipping extraordinarily fast. Understanding usage and learning still happen by hand. Wave runs the whole loop: - Analyzes your Amplitude data for signals across analytics, feedback, session replays, error logs, agent traces, and experiment results - Surfaces opportunities in the form of full product specs that you or your agents can approve and ship - Tracks the experiments and outcomes of what you've built so you can start the loop over again Your product learns what works and gets smarter every cycle:
2:36

Today we're introducing Wave. A proactive product agent that helps teams build self-improving products. Every product team runs the same loop. Build, ship, use, learn. AI has made building and shipping extraordinarily fast. Understanding usage and learning still happen by hand. Wave runs the whole loop: - Analyzes your Amplitude data for signals across analytics, feedback, session replays, error logs, agent traces, and experiment results - Surfaces opportunities in the form of full product specs that you or your agents can approve and ship - Tracks the experiments and outcomes of what you've built so you can start the loop over again Your product learns what works and gets smarter every cycle:

Spenser Skates

117,771 Aufrufe • vor 4 Monaten

Today we're launching Glass for Patients, the personal AI agent for your health. Glass reviews all of your healthcare data and analyzes it alongside the world's medical knowledge to help you continually understand and optimize your health. Get started at
1:24

Today we're launching Glass for Patients, the personal AI agent for your health. Glass reviews all of your healthcare data and analyzes it alongside the world's medical knowledge to help you continually understand and optimize your health. Get started at

Glass Health

34,911 Aufrufe • vor 3 Monaten

Anthropic just dropped 5 workshops on building self-improving agentic systems from scratch: 00:00 - Ship your first Claude agent 36:44 - Build memory for Claude agents 1:05:06 - Make your agent autonomous 1:26:46 - Set up a proactive agent 2:03:35 - self-improving agents (tools,skills) These 3-hours of free Claude workshops will replace 10 paid agentic courses. Watch today, then read article below on how to build a self-improving agentic system with Fable 5.
2:48:18

Anthropic just dropped 5 workshops on building self-improving agentic systems from scratch: 00:00 - Ship your first Claude agent 36:44 - Build memory for Claude agents 1:05:06 - Make your agent autonomous 1:26:46 - Set up a proactive agent 2:03:35 - self-improving agents (tools,skills) These 3-hours of free Claude workshops will replace 10 paid agentic courses. Watch today, then read article below on how to build a self-improving agentic system with Fable 5.

Movez

932,647 Aufrufe • vor 3 Monaten

Anthropic just released 5 workshops on building self-improving agentic systems from scratch: 00:00 - Ship your first Claude agent 36:44 - Self-improving agents (tools,skills) 1:21:25 - Build memory for Claude agents 1:49:47 - Set up a proactive agent 2:11:31 - Make your agent autonomous These 3-hours of Claude workshops will replace 20 paid agentic courses. Watch today, then read article below on how to build a self-improving agentic system with Fable 5.
2:48:09

Anthropic just released 5 workshops on building self-improving agentic systems from scratch: 00:00 - Ship your first Claude agent 36:44 - Self-improving agents (tools,skills) 1:21:25 - Build memory for Claude agents 1:49:47 - Set up a proactive agent 2:11:31 - Make your agent autonomous These 3-hours of Claude workshops will replace 20 paid agentic courses. Watch today, then read article below on how to build a self-improving agentic system with Fable 5.

Codez

507,297 Aufrufe • vor 3 Monaten

Today, we’re launching the Integritas AI Agent for ChatGPT, bringing verifiable data integrity into AI-assisted workflows. For the first time, users can create cryptographic proofs of authenticity for documents, files, logs, and AI-generated outputs - and anchor those proofs to the Minima blockchain - without leaving ChatGPT. Full Announcement: Overview 👇
1:18

Today, we’re launching the Integritas AI Agent for ChatGPT, bringing verifiable data integrity into AI-assisted workflows. For the first time, users can create cryptographic proofs of authenticity for documents, files, logs, and AI-generated outputs - and anchor those proofs to the Minima blockchain - without leaving ChatGPT. Full Announcement: Overview 👇

Minima

376,941 Aufrufe • vor 10 Monaten

today, we release Krea Agents. the world's best agents for creative work, with deep expertise about creative workflows and a powerful context manger with self-improving memory. promos and tutorials below 👇
0:43

today, we release Krea Agents. the world's best agents for creative work, with deep expertise about creative workflows and a powerful context manger with self-improving memory. promos and tutorials below 👇

Krea

56,417 Aufrufe • vor 1 Monat

Anthropic Managed Agents team: "Fable 5 - is our best model for self-improving agent systems. add /loops, dynamic workflows, dreaming - and you're unstoppable." in 13 minutes, the Anthropic team shows how to build self-improving agent systems with Fable 5 from scratch. Worth more than a $500 agent-building course. Live from the Anthropic stage in Japan. Unpublished
13:23

Anthropic Managed Agents team: "Fable 5 - is our best model for self-improving agent systems. add /loops, dynamic workflows, dreaming - and you're unstoppable." in 13 minutes, the Anthropic team shows how to build self-improving agent systems with Fable 5 from scratch. Worth more than a $500 agent-building course. Live from the Anthropic stage in Japan. Unpublished

Movez

67,091 Aufrufe • vor 4 Monaten

Andrej Karpathy OpenAI co-founder: "95% of what AI twitter sells you dies the moment the model updates" self-improving loops help agents become better with each run." 35-min - completely free and worth more than a $500 building course Book & watvh it today
34:56

Andrej Karpathy OpenAI co-founder: "95% of what AI twitter sells you dies the moment the model updates" self-improving loops help agents become better with each run." 35-min - completely free and worth more than a $500 building course Book & watvh it today

Morty

37,093 Aufrufe • vor 3 Monaten

Don't waste 2 years figuring out how AI agents actually work. ex. Anthropic & Google engineers at Stanford just dropped a 1-hour lecture on self-improving AI agents: • 00:00 - Introduction to self-learning AI systems • 31:22 - inside a LLM: self-correction, backtracking • 42:24 - goal → loops → graphs→ feedback: the Agent loop • 45:47 - 6 agent orchestration patterns • 50:37 - the generator-verifier gap - why self-improvement stalls Planning, multi-step reasoning, self-correction. That's the entire agent roadmap for 2026. Bookmark this & give 70 minutes today. Then read the article below.
1:09:36

Don't waste 2 years figuring out how AI agents actually work. ex. Anthropic & Google engineers at Stanford just dropped a 1-hour lecture on self-improving AI agents: • 00:00 - Introduction to self-learning AI systems • 31:22 - inside a LLM: self-correction, backtracking • 42:24 - goal → loops → graphs→ feedback: the Agent loop • 45:47 - 6 agent orchestration patterns • 50:37 - the generator-verifier gap - why self-improvement stalls Planning, multi-step reasoning, self-correction. That's the entire agent roadmap for 2026. Bookmark this & give 70 minutes today. Then read the article below.

Movez

40,448 Aufrufe • vor 2 Monaten

Introducing D0. The first High-stake Proactive Agent for Financial Markets. It monitors markets 24/7, identifies opportunities, manages risk, and executes trades, while you sleep. Built by Donut Labs. Backed by AI experts, financial institutions and top-tier funds. 🧵👇
1:11

Introducing D0. The first High-stake Proactive Agent for Financial Markets. It monitors markets 24/7, identifies opportunities, manages risk, and executes trades, while you sleep. Built by Donut Labs. Backed by AI experts, financial institutions and top-tier funds. 🧵👇

Donut

1,024,990 Aufrufe • vor 6 Monaten

"to me, it's not about the human in the loop, but the human at the center." i sat down with Stefania Druga, staff research scientist Sakana AI, at our Browserbase booth at AI Engineer. after Massachusetts Institute of Technology (MIT) and Google DeepMind, stefania recently joined sakana's recursive self-improvement (rsi) lab in tokyo to build self-improving AI for the next frontier. we got into: - catastrophic forgetting in day-long agent research runs, and how memory-first harnesses help - sovereign AI and open-weights: building on models you control instead of locking into one provider - why computer use still frustrates people even as models get smarter - the domains ripe for self-improving research agents: math, genomics, rare conditions - my fav moment at the end: what tasks are better left human, and what are we going to do as humans after everything is automated? with open frontier models arriving fast, Stefania Druga's case for sovereign AI only gets stronger. loved this conversation. thanks for joining us at the Browserbase booth!
16:07

"to me, it's not about the human in the loop, but the human at the center." i sat down with Stefania Druga, staff research scientist Sakana AI, at our Browserbase booth at AI Engineer. after Massachusetts Institute of Technology (MIT) and Google DeepMind, stefania recently joined sakana's recursive self-improvement (rsi) lab in tokyo to build self-improving AI for the next frontier. we got into: - catastrophic forgetting in day-long agent research runs, and how memory-first harnesses help - sovereign AI and open-weights: building on models you control instead of locking into one provider - why computer use still frustrates people even as models get smarter - the domains ripe for self-improving research agents: math, genomics, rare conditions - my fav moment at the end: what tasks are better left human, and what are we going to do as humans after everything is automated? with open frontier models arriving fast, Stefania Druga's case for sovereign AI only gets stronger. loved this conversation. thanks for joining us at the Browserbase booth!

justine

19,853 Aufrufe • vor 3 Monaten

1/ Our quantum-safe Bitcoin transaction cost ~$320 in GPU compute. Can you bring that down? Today, we’re launching the Quantum-Safe Bitcoin Autoresearch Challenge in partnership with Yukon and Eigen Labs. Over $20,000 in rewards for improving the code:
1:18

1/ Our quantum-safe Bitcoin transaction cost ~$320 in GPU compute. Can you bring that down? Today, we’re launching the Quantum-Safe Bitcoin Autoresearch Challenge in partnership with Yukon and Eigen Labs. Over $20,000 in rewards for improving the code:

StarkWare 🥷

91,050 Aufrufe • vor 29 Tagen

Today we're launching Tasklet — an AI agent for automating your business. Unlike ChatGPT, Tasklet actually does the work for you: connecting to your tools, triggering automatically, and handling tasks while you sleep.
0:56

Today we're launching Tasklet — an AI agent for automating your business. Unlike ChatGPT, Tasklet actually does the work for you: connecting to your tools, triggering automatically, and handling tasks while you sleep.

Andrew Lee

80,598 Aufrufe • vor 1 Jahr