Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Agentforce v2 is here: the ultimate upgrade. Agents that remember, collaborate, and deliver with short/long-term memory, seamless handoffs, and secure teamwork. It’s how powers 60M users, 1M+ articles, and 17 languages. From “helpful” to consultative—this is what AI was meant to be. ❤️🤖

44,478 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von Daniel Merja
Daniel Merjavor 1 Jahr

@Scobleizer @salesforce @agentforce We don’t even know what Salesforce does, let alone know what Agentforce does.

Profilbild von Rafael Ibañez
Rafael Ibañezvor 1 Jahr

Marc, we are very happy with your company's decision to invest in Argentina. We have been working closely with your team in the country in Argentina (entire LATAM), and we welcome this news with open arms. We look forward to seeing you! We will double our efforts to drive the entire strategy with @Salesforce and #AGENTFORCE 1st.

Profilbild von Doggy_Fi
Doggy_Fivor 1 Jahr

@Scobleizer @salesforce @agentforce Woulda been happier with sentient drunk clippy with a zoloft prescription

Profilbild von Jeff Cox
Jeff Coxvor 1 Jahr

@salesforce @agentforce My family loved the commercial on Netflix.

Profilbild von Lyle J. Dennis, MD
Lyle J. Dennis, MDvor 1 Jahr

@salesforce @agentforce So the AI agents have finally arrived?

Profilbild von Thomas Peters
Thomas Petersvor 1 Jahr

@salesforce @agentforce Turning AI from a tool into a partner. The future will s in making this tech more than efficient, and affordable

Profilbild von culture warrior
culture warriorvor 1 Jahr

@Scobleizer @salesforce @agentforce Add a follow button in slack

Profilbild von innerly
innerlyvor 1 Jahr

@salesforce @agentforce Memory and collaboration? Sounds like a recipe for delightful chaos! Tell me more.

Profilbild von Gary Kimmel
Gary Kimmelvor 1 Jahr

@salesforce @agentforce Brilliant - makes support so much faster and easier than fumbling and combing through articles trying to find the right answer.

Profilbild von Cda
Cdavor 1 Jahr

@salesforce @agentforce are they woke like you?

Ähnliche Videos

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

132,349 Aufrufe • vor 1 Jahr