Загрузка видео...

Не удалось загрузить видео

На главную

🚀 Big news at Zep! We're introducing Entity Types, a smarter, structured memory solution for AI agents! 🧠✨ With Entity Types, developers can now precisely structure and recall domain-specific information, significantly enhancing the accuracy, personalization, and context-awareness of AI interactions. 🌐 🔹 Default Entity Types provide ready-to-use structures like...

zep_ai's profile picture

Zep AI

1,970 subscribers

14,455 просмотров • 1 год назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 6

Фото профиля Zep AI
Zep AI1 год назад

➡️ Learn more:

Фото профиля NICE
NICE1 год назад

Gartner® report reveals how the power of AI agents can redefine your customer service.

Фото профиля Akshay 🚀
Akshay 🚀1 год назад

This looks like a major breakthrough! 🔥 Can't wait to test it!!

Фото профиля Zep AI
Zep AI1 год назад

Thanks, @akshay_pachaar !

Фото профиля Gabriel Rymberg
Gabriel Rymberg1 год назад

@threadreaderapp unroll

Фото профиля Attila-IBS
Attila-IBS1 год назад

How about using entity types? Would have real advantages.

Похожие видео

Lindy AI just announced the first AI employee. You can now create custom AI agents with just a prompt and get them to work natively in your browser for limitless use cases. Sales outreach, personalized emails, automated research…anything! Here’s how to set up your AI agent:
0:24

Lindy AI just announced the first AI employee. You can now create custom AI agents with just a prompt and get them to work natively in your browser for limitless use cases. Sales outreach, personalized emails, automated research…anything! Here’s how to set up your AI agent:

Alvaro Cintas

26,763 просмотров • 10 месяцев назад

The future of ecommerce intelligence is here. Meet Moby Agents 🤝 AI agents will redefine how teams operate, and we’re leading the charge with the first AI agents built for ecommerce intelligence. Imagine AI agents supporting your entire business with… 🧠 Deep ecommerce expertise 💻 Full access + context to all your business data 👀 Real-time insights, recommendations, and anomaly detection on autopilot Deploy 24/7 AI agents that unlock insights you couldn’t access before—making your business smarter, faster, and more efficient. Want in? We’re opening 100 exclusive spots for Triple Whale customers. Check out the comments to request a demo now.
0:52

The future of ecommerce intelligence is here. Meet Moby Agents 🤝 AI agents will redefine how teams operate, and we’re leading the charge with the first AI agents built for ecommerce intelligence. Imagine AI agents supporting your entire business with… 🧠 Deep ecommerce expertise 💻 Full access + context to all your business data 👀 Real-time insights, recommendations, and anomaly detection on autopilot Deploy 24/7 AI agents that unlock insights you couldn’t access before—making your business smarter, faster, and more efficient. Want in? We’re opening 100 exclusive spots for Triple Whale customers. Check out the comments to request a demo now.

Triple Whale 🐳

20,658 просмотров • 1 год назад

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:
1:46

Specialized AI agents help enterprises turn AI into systems built for their own workflows. NVIDIA Agent Toolkit brings together open Nemotron models, tools, skills and secure runtime support to help teams build agents tuned for domain-specific work. Learn more:

NVIDIA

77,436 просмотров • 3 дней назад

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:
2:06

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,640 просмотров • 1 год назад

Say hello to Glean Apps – no-code custom generative AI agents, assistants, copilots, and chatbots to help you unlock the full potential of AI at work. ✨ Check out how you can use the Glean Platform to securely build and deploy custom AI apps 👉
0:57

Say hello to Glean Apps – no-code custom generative AI agents, assistants, copilots, and chatbots to help you unlock the full potential of AI at work. ✨ Check out how you can use the Glean Platform to securely build and deploy custom AI apps 👉

Glean

11,628 просмотров • 2 лет назад

My TRAE Agent is cuter and smarter than yours… 😎 With TRAE 2.0, you can now: 🛠 Define custom roles, tasks, and tools for each agent 🤝 Combine agents to co-build in the same project 🎨 (NEW) Pick from 100+ pixel-style avatars to match their vibe 🧵Thread below for example agents to start building your dream AI team
0:47

My TRAE Agent is cuter and smarter than yours… 😎 With TRAE 2.0, you can now: 🛠 Define custom roles, tasks, and tools for each agent 🤝 Combine agents to co-build in the same project 🎨 (NEW) Pick from 100+ pixel-style avatars to match their vibe 🧵Thread below for example agents to start building your dream AI team

TRAE

21,863 просмотров • 11 месяцев назад

🚀 Just shipped `.narrow()` in TS-Pattern for deep narrowing! Need to exclude matched cases from deeply nested types? Now you can! Perfect for: 👉 Excluding nested union types 👉 Getting precise types in `.otherwise()` 👉 Avoiding impossible branches More in 🧵👇
0:22

🚀 Just shipped `.narrow()` in TS-Pattern for deep narrowing! Need to exclude matched cases from deeply nested types? Now you can! Perfect for: 👉 Excluding nested union types 👉 Getting precise types in `.otherwise()` 👉 Avoiding impossible branches More in 🧵👇

Gabriel Vergnaud

12,876 просмотров • 11 месяцев назад

Custom instructions provide more context about your specific coding preferences and tech stack. Better context = better results from the LLM. And custom instructions are extra helpful for remote development, where you can provide more info about the type of remote environment you're connected to.
1:15

Custom instructions provide more context about your specific coding preferences and tech stack. Better context = better results from the LLM. And custom instructions are extra helpful for remote development, where you can provide more info about the type of remote environment you're connected to.

Visual Studio Code

44,868 просмотров • 1 год назад

Today, we’re excited to announce the general availability of the Contextual AI Platform. This is the first enterprise platform designed for building specialized RAG agents to support expert knowledge work. What is a specialized RAG agent? First, a general-purpose AI agent is one designed to automate simple daily tasks like scheduling a meeting or responding to an email. On the other hand, a specialized RAG agent is one designed to augment subject-matter experts performing complex domain-specific work. The Contextual AI Platform allows you to create these agents easily and achieve SOTA accuracy right out of the box. Check out what the Contextual AI Platform can do.
2:11

Today, we’re excited to announce the general availability of the Contextual AI Platform. This is the first enterprise platform designed for building specialized RAG agents to support expert knowledge work. What is a specialized RAG agent? First, a general-purpose AI agent is one designed to automate simple daily tasks like scheduling a meeting or responding to an email. On the other hand, a specialized RAG agent is one designed to augment subject-matter experts performing complex domain-specific work. The Contextual AI Platform allows you to create these agents easily and achieve SOTA accuracy right out of the box. Check out what the Contextual AI Platform can do.

Contextual AI

879,586 просмотров • 1 год назад

If you haven’t tried Nimble Network AI Agent Platform or AI Creator yet, here’s a step-by-step guide on how to use it！ Link: 1. Create an Image-Generation Agent • Users can create their own image-generation agents using two methods: • Pick: Select from pre-configured templates to quickly set up your agent. • Input: Customize your agent by manually entering specific parameters and preferences. 2. Deploy and Run the Agent • Navigate to the agent_run section of the platform. • Deploy your custom agent and execute its functions based on your configuration. 3. Generate Tweets and Images • Use the deployed agent to generate tweets tailored to your content. • Pair these tweets with AI-generated images to boost engagement and storytelling.
2:05

If you haven’t tried Nimble Network AI Agent Platform or AI Creator yet, here’s a step-by-step guide on how to use it！ Link: 1. Create an Image-Generation Agent • Users can create their own image-generation agents using two methods: • Pick: Select from pre-configured templates to quickly set up your agent. • Input: Customize your agent by manually entering specific parameters and preferences. 2. Deploy and Run the Agent • Navigate to the agent_run section of the platform. • Deploy your custom agent and execute its functions based on your configuration. 3. Generate Tweets and Images • Use the deployed agent to generate tweets tailored to your content. • Pair these tweets with AI-generated images to boost engagement and storytelling.

Nimble Network

15,622 просмотров • 1 год назад

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.
0:24

Announcing Agent Bricks: auto-optimize agents for your domain tasks. Provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks builds out an agent system that automatically optimizes against your goals and generates domain-specific synthetic datasets, accelerating agent development without relying on manual labeling or external sources.

Databricks

47,044 просмотров • 1 год назад

🚀 Micro Agent is now live on the PAAL AI 🧠🤖 Agents Marketplace! 🎉 Developers can now interact with Micro Agent via API to build powerful apps and integrate with other agents seamlessly. Unleash the full potential of AI! 👉 Explore:
0:29

🚀 Micro Agent is now live on the PAAL AI 🧠🤖 Agents Marketplace! 🎉 Developers can now interact with Micro Agent via API to build powerful apps and integrate with other agents seamlessly. Unleash the full potential of AI! 👉 Explore:

MicroGPT

168,414 просмотров • 1 год назад

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!
1:37

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

158,701 просмотров • 3 месяцев назад

Ever wanted to make your own Minecraft NPC? Now you can, with the Blockbench Entity Wizard and the NPC Dialogue Designer! Learn how here:
2:08

Ever wanted to make your own Minecraft NPC? Now you can, with the Blockbench Entity Wizard and the NPC Dialogue Designer! Learn how here:

Minecraft

136,822 просмотров • 1 год назад

💡 Managing your digital presence doesn’t have to take hours. With OptimAI, every post, reply, and DM feels personalized, authentic, and human — just like you. ✨ Try it now: We help you cut down the grind of managing social presence, so you can focus on creating real impact. Even more exciting features are on the way: smarter agents, deeper personalization, and mind-blowing new ways to grow your presence. Together, we make impact!🔥
0:37

💡 Managing your digital presence doesn’t have to take hours. With OptimAI, every post, reply, and DM feels personalized, authentic, and human — just like you. ✨ Try it now: We help you cut down the grind of managing social presence, so you can focus on creating real impact. Even more exciting features are on the way: smarter agents, deeper personalization, and mind-blowing new ways to grow your presence. Together, we make impact!🔥

OptimAI

52,891 просмотров • 9 месяцев назад

Perplexity now remembers your threads and interests to provide smarter, faster, and more personalized answers. Memory recall works across all models and search modes, even allowing you to continue conversations with full context weeks later.
0:30

Perplexity now remembers your threads and interests to provide smarter, faster, and more personalized answers. Memory recall works across all models and search modes, even allowing you to continue conversations with full context weeks later.

Perplexity

139,566 просмотров • 7 месяцев назад

SDG V2 Model Live on SecureGPT SDG V1 allowed users to create customized filters for specific data types to be exposed or passed through. With SDG V2, we are taking privacy to the next level by enabling real-time decision-making and data exposure within the filtered data types. SDG V2 introduces character-based runtime filtration, allowing you to define specific characters and control which words are exposed in your queries, while filtering out others within the same data type. This gives you the ability to fine-tune your AI filters in real time, enhancing your privacy and control during every interaction. Enjoy customizable privacy power now in SecureGPT!
0:39

SDG V2 Model Live on SecureGPT SDG V1 allowed users to create customized filters for specific data types to be exposed or passed through. With SDG V2, we are taking privacy to the next level by enabling real-time decision-making and data exposure within the filtered data types. SDG V2 introduces character-based runtime filtration, allowing you to define specific characters and control which words are exposed in your queries, while filtering out others within the same data type. This gives you the ability to fine-tune your AI filters in real time, enhancing your privacy and control during every interaction. Enjoy customizable privacy power now in SecureGPT!

ZKCrypt AI

26,211 просмотров • 1 год назад

🌟 Introducing Mansa AI — the enterprise-grade AI platform built to empower Web3 creators, developers, and businesses! 🚀 🧠 Seamless Agent Creation: Use the intuitive low-code AgentCraft framework to build autonomous AI agents that handle real‑time automation, complex workflows, and intelligent decision‑making. 🛠 Fully Customizable Logic: Configure every aspect of your AI agents — from behavior and triggers to cross‑chain integration and modular logic blocks — so they act according to your unique strategy. 🔗 Web3‑Ready Deployment: Deploy your AI agents across multiple blockchain ecosystems with full interoperability, giving you powerful automation that scales with your business. 📈 Scalable Workflow Infrastructure: Launch once and automate everywhere — Mansa AI ensures your systems perform seamlessly across chains, supporting enterprise growth without complexity. Welcome to the next evolution of automation, where intelligence is not just built, it’s deployed, scaled, and owned. Step into the future with Mansa AI. 🌐
2:00

🌟 Introducing Mansa AI — the enterprise-grade AI platform built to empower Web3 creators, developers, and businesses! 🚀 🧠 Seamless Agent Creation: Use the intuitive low-code AgentCraft framework to build autonomous AI agents that handle real‑time automation, complex workflows, and intelligent decision‑making. 🛠 Fully Customizable Logic: Configure every aspect of your AI agents — from behavior and triggers to cross‑chain integration and modular logic blocks — so they act according to your unique strategy. 🔗 Web3‑Ready Deployment: Deploy your AI agents across multiple blockchain ecosystems with full interoperability, giving you powerful automation that scales with your business. 📈 Scalable Workflow Infrastructure: Launch once and automate everywhere — Mansa AI ensures your systems perform seamlessly across chains, supporting enterprise growth without complexity. Welcome to the next evolution of automation, where intelligence is not just built, it’s deployed, scaled, and owned. Step into the future with Mansa AI. 🌐

Mansa AgentCraft

586,470 просмотров • 8 месяцев назад

Introducing the new @aomniapp - an AI agent that builds other agents for you. Now you can go from idea -> fully working agent with 1 prompt. We provide all the tools and contact datasets to build agents that excel at revenue gen activities. Here are some cool use cases 🧵
7:48

Introducing the new @aomniapp - an AI agent that builds other agents for you. Now you can go from idea -> fully working agent with 1 prompt. We provide all the tools and contact datasets to build agents that excel at revenue gen activities. Here are some cool use cases 🧵

David

71,692 просмотров • 1 год назад

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:
0:43

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

LangChain OSS

65,840 просмотров • 3 месяцев назад