Loading video...

Video Failed to Load

Go Home

🚨We shipped a new context engineering primitive Mastra today, Agent Signals! (alpha) 🔓Unlocks: multiplayer steering, dynamic cacheable system prompts, agent notifications (gh/email/etc), and automatic behavior guidance 🧵

tylbar's profile picture

Tyler Barnes

1,870 subscribers

24,392 views • 1 month 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

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:
0:30

Starting today, agents can use Mastra Studio, not just humans We shipped CLI Actions so your Claude Code, Codex, or Cursor agent can run Mastra agents/workflows, search memory, query traces, and turn failures into datasets:

Sam Bhagwat

12,537 views • 15 days ago

An agent can sign up for WorkOS without an email. A human claims it later. Abhi Aiyer , CTO of Mastra , at HumanX on why agent-first onboarding is the new moat.
9:20

An agent can sign up for WorkOS without an email. A human claims it later. Abhi Aiyer , CTO of Mastra , at HumanX on why agent-first onboarding is the new moat.

WorkOS

15,058 views • 2 months ago

Insights Agent & Multi-turn Evals Agents run for a long period of time and have multiple interactions with users, tackling a wide variety of problems. Today we’re launching two new features in LangSmith, our agent engineering platform, so you can better understand your agent behavior: • Insights Agent is a new agent that automatically categorizes agent behavior patterns in LangSmith • Multi-turn Evals lets you evaluate agent trajectory across complete conversations, so you can see if the agent actually accomplished user goals Learn more:
0:40

Insights Agent & Multi-turn Evals Agents run for a long period of time and have multiple interactions with users, tackling a wide variety of problems. Today we’re launching two new features in LangSmith, our agent engineering platform, so you can better understand your agent behavior: • Insights Agent is a new agent that automatically categorizes agent behavior patterns in LangSmith • Multi-turn Evals lets you evaluate agent trajectory across complete conversations, so you can see if the agent actually accomplished user goals Learn more:

LangChain

13,322 views • 8 months ago

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.
7:51

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

Dami-Defi

10,107 views • 19 days ago

Private Terminal is live – your personal onchain agent, so you can touch more grass. Start with an email. Delegate your wallet. Let the agent handle the rest. Alpha is available today on Base 🧵
2:04

Private Terminal is live – your personal onchain agent, so you can touch more grass. Start with an email. Delegate your wallet. Let the agent handle the rest. Alpha is available today on Base 🧵

Terminal

17,691 views • 1 year ago

Today we're launching Mastra remote sandboxes Give your agent a secure, isolated environment to run untrusted user code... like a vibe coding agent...
2:28

Today we're launching Mastra remote sandboxes Give your agent a secure, isolated environment to run untrusted user code... like a vibe coding agent...

Alex Booker

22,196 views • 3 months ago

🚨 Announcing a new coding agent that rivals Claude Code but with no compaction needed 🚨 The feeling of using it: run your coding sessions forever, don't worry at all, and get shit done! We're calling it Mastra Code, it's powered by Mastra's new observational memory, and we've been using it internally Mastra to do all our work 1/4 🧵
4:34

🚨 Announcing a new coding agent that rivals Claude Code but with no compaction needed 🚨 The feeling of using it: run your coding sessions forever, don't worry at all, and get shit done! We're calling it Mastra Code, it's powered by Mastra's new observational memory, and we've been using it internally Mastra to do all our work 1/4 🧵

Tyler Barnes

66,557 views • 4 months ago

Introducing Inspector's context-aware screenshot tool! Screenshots as context for your coding agent is a pain. I decided I was tired of it and shipped something today to help with that.
1:33

Introducing Inspector's context-aware screenshot tool! Screenshots as context for your coding agent is a pain. I decided I was tired of it and shipped something today to help with that.

mikeBuildsMore

21,932 views • 8 months ago

Our first ship at Entire, Checkpoints is a new primitive that automatically captures agent context as first-class, versioned data in Git. Try today in Claude and Google Gemini CLI. Coming to all agents soon.
1:15

Our first ship at Entire, Checkpoints is a new primitive that automatically captures agent context as first-class, versioned data in Git. Try today in Claude and Google Gemini CLI. Coming to all agents soon.

Thomas Dohmke

56,934 views • 4 months ago

Introducing Launch Log 3 🚀 👉 MCP support 👉 Image as context 👉 Refine agent-generated content 👉 Suggested Prompts Details in the 🧵
2:17

Introducing Launch Log 3 🚀 👉 MCP support 👉 Image as context 👉 Refine agent-generated content 👉 Suggested Prompts Details in the 🧵

Warp

22,955 views • 1 year ago

Today we release our new platform, Access Intelligence 1⃣Monetize your content or data for agent consumption 2⃣Deploy a data powered agent in under 5 minutes — no code 3⃣Monetize useful agents 🧵
0:55

Today we release our new platform, Access Intelligence 1⃣Monetize your content or data for agent consumption 2⃣Deploy a data powered agent in under 5 minutes — no code 3⃣Monetize useful agents 🧵

Access Intelligence

39,162 views • 1 year ago

The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, context engineering, multi-agent systems, long-running agents,.. Go build!
9:09

The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, context engineering, multi-agent systems, long-running agents,.. Go build!

elvis

31,802 views • 1 month ago

We pivoted. Den is now a multiplayer AI agent builder. Thread below.
2:08

We pivoted. Den is now a multiplayer AI agent builder. Thread below.

Den

77,813 views • 11 months ago

Stagehand Agent just got way more powerful. We just added: • Agent Hybrid mode (DOM + vision) • Streaming output • Automatic web search (with Brave) Try the new agent with experimental flag.
0:24

Stagehand Agent just got way more powerful. We just added: • Agent Hybrid mode (DOM + vision) • Streaming output • Automatic web search (with Brave) Try the new agent with experimental flag.

Stagehand

16,720 views • 5 months ago

Today, we're announcing three Agent Skills: 🔸 email-best-practices 🔸 react-email 🔸 resend-skills Give your agent the power of email 👇
0:33

Today, we're announcing three Agent Skills: 🔸 email-best-practices 🔸 react-email 🔸 resend-skills Give your agent the power of email 👇

Resend

84,310 views • 5 months ago

New Tab model, 1M+ context windows, and a preview of our background agent
2:11

New Tab model, 1M+ context windows, and a preview of our background agent

Cursor

366,238 views • 1 year ago

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:
3:04

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: Learn more:

LangChain

24,885,978 views • 4 months ago

Agent-in-the-browser unlocks superpowers. The magic really shines when you bring your own model, system prompts, and MCP tools into the mix. Hence, AgentBoard 🪄. Your models, keys, and settings. Integration with remote MCP servers and — this is where it gets really fun — ability to register and allow the agent to call custom ~WebMCP tools that execute in context of the page. Chrome Web Store: Code:
3:51

Agent-in-the-browser unlocks superpowers. The magic really shines when you bring your own model, system prompts, and MCP tools into the mix. Hence, AgentBoard 🪄. Your models, keys, and settings. Integration with remote MCP servers and — this is where it gets really fun — ability to register and allow the agent to call custom ~WebMCP tools that execute in context of the page. Chrome Web Store: Code:

Ilya Grigorik

22,961 views • 8 months ago

We just shipped task lists for Mastra agents. Now the agent can break work into structured steps they can check off one by one, with tools for marking items as `in_progress` or `completed` .
0:24

We just shipped task lists for Mastra agents. Now the agent can break work into structured steps they can check off one by one, with tools for marking items as `in_progress` or `completed` .

Sam Bhagwat

11,250 views • 14 days ago