LangSmith Traces 🤝 Server Logs View all user and... system logs for a particular trace in a single window. Agentic observability just got even easier! ➡️ Docs:show more

🚀 LangSmith for Startups Spotlight: Cogent Security Cogent is... building AI agents that protect the world's largest organizations from cyberattacks. One of the hardest problems in cybersecurity is going from finding a vulnerability to actually fixing it. Cogent is automating that entire process from end-to-end. Cogent is already working with dozens of Fortune 1000 and Global 2000 enterprise customers such as major universities, hospitality brands, and consumer retailers. Cogent uses LangSmith for production tracing and monitoring of our agents. Their team leverages execution traces for usage insight and use-case categorization, self-refinement loops to diagnose eval failures, and online evaluators to flag undesired behavior. Join their team if you want to build frontier AI for mission critical problems 🤝show more

I replaced our Datadog bill with a single binary... and cut infrastructure costs by 98% overnight. It’s called OpenObserve. Logs, metrics, traces, and frontend monitoring in one tool, self-hosted, and it’s built specifically to stop the bill that grows every time you add a host, a user, or a custom metric. → One binary, running in under 2 minutes. No cluster, no separate components for logs vs metrics vs traces → Built in Rust on the DataFusion query engine, so it stays fast even at petabyte scale → Uses Parquet columnar storage on S3-compatible object storage instead of a proprietary format, which is where the real cost savings come from → Query with SQL or PromQL instead of a vendor’s proprietary syntax, so your team isn’t learning a new query language just to read a dashboard → Full OpenTelemetry compatibility, no proprietary agents required to get your existing instrumentation talking to it → Community dashboard library on GitHub for Kubernetes, Docker, Postgres, AWS, and LLM observability, ready to drop in instead of building from scratch In OpenObserve’s own published benchmark, the same 16-service workload cost $174/day on Datadog and $3/day self-hosted, a 98% cut, before even touching per-host or per-seat fees. 18,000+ GitHub stars. Single binary. Self-hosted, no per-host or per-user tax.show more

Introducing Video → UI in Magic Patterns, now available... to everyone. Animate interactions, generate full user flows, debug issues, all from just uploading a single file. Here are some insane examples of how prompting just got 10x easier:show more

✨ Klarna's AI Assistant, powered by LangGraph and LangSmith,... handles customer support tasks for 85 million active users — reducing customer resolution time by 80% ✨ 🛍️ Klarna’s flagship AI Assistant is revolutionizing the shopping and payments experience. Built on LangGraph and powered by LangSmith, the AI Assistant handles tasks ranging from customer payments, to refunds, to other payment escalations. ‼️ In the past 9 months, they’ve reduced average customer query resolution time by 80%, enabling faster responses to user queries and saving analysts and engineers hours a week of investigation time. 🔄 They’ve also automated ~70% of repetitive support tasks, freeing up customer service agents to handle complex, high-value interactionsshow more

At Uber, our testing agent hit an outage in... Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.show more

🧬🧬 LLM Generated UIs We've added a series of... templates and documentation showing off how to build generative UI applications using LangChain JS/TS & Next.js. These templates include: - 🌆 generative UI in Next.js - 🤖 streaming agent events - 🛠️ streaming tool calls and more! Checkout our Next.js template repo for these examples and extensive docs:show more

And it's live, the frontend still throttle to 250ms... updates for now, just monitoring things. Will push the full speed later on after a few performance improvements in the code computing the full order books from Hyperliquid logs files. Was a good day of coding 🦈show more

How I got out of bot jail!! I was... stuck there for a year, all because I didn’t change some settings. This isn’t a growth video, even though I GREW, this is just how I got out of 20-200 view jailshow more

“We argued for change: We got that mandate and... we got it in all four nations. That is really important for us as well.” Fact check: Labour didn’t stand in Northern Ireland - and therefor didn’t win a single vote in NI. Keir Starmer didn’t even visit NI during campaignshow more

Biggest Virtuals Protocol bug bounty of all time is... LIVE. 🚨 $15,000 for anyone who can decrypt a Morse AI signal containing a private wallet key holding all the funds. $5,000 extra if you DM me on X explaining exactly how you did it. Yeah. That’s how confident we are in the tech. To make it even better, the MORSE user-to-user platform is FREE to use until launch. We want real stress testing. No funds needed. Just create a fresh empty wallet and play with it. Early users will also get special rewards in the coming days 👀 Quick $MORSE TL;DR MORSE is a native privacy layer. Not just for payments, but for communication and assets too. It doesn’t replace ACP, it completes it. Some real examples: User → User Send a private message, file, prompt, or even a wallet key through a one-time encrypted URL. Only the target wallet can open it. Once opened, it’s burned forever. Agent → Agent Agents exchange sensitive data, strategies, keys, or instructions privately through the SDK. No logs. No persistence. No leaks. Agent → User Agents can send private signals, reports, assets, or credentials to a specific wallet, fully encrypted so only that user can read it. Nothing public. Nothing stored. Everything ephemeral by design. Have fun breaking it.show more

.Jay Bhattacharya, MD, PhD: “There is a loss in... public trust in public health that happened in part because — frankly, even on this network and on other networks — there was a particular single point of view put across during the COVID pandemic that led to things that really did cause harm to people.”show more

🚨 BREAKING 🇺🇸 TRUMP INSIDER WITH A 100% WIN... RATE JUST GOT FULLY LIQUIDATED ON HIS LONGS FOR $75 MILLION! AFTER 15 SUCCESSFUL TRADES IN A ROW AND $115 MILLION IN PROFIT, HE WENT ALL-IN AND LOST EVERYTHING IN A SINGLE TRADE. CRYPTO IS A WILD SPACE 🤯show more

Medicare For All strengthens care, lowers costs, and improves... choice. I’ve proudly supported a single-payer system since I got to Congress, because it delivers the best health care for Americans. This week, my colleagues and I reintroduced #M4A.show more

Agentic traces contain perfect information about an agent’s behavior... with every plan, action, and retry. But that information gets lost in a sea of JSON. So we built AgentPrism: open source React components that turn traces into visual diagrams for debugging AI agents. You can plug in your OpenTelemetry data and see your agent’s process unfold: messages, tool calls, retries. Quotient AI automatically monitors, analyzes, and improves AI agents. Being able to review traces quickly is paramount for their research, and for their customers. “Dealing with agent traces was one of the biggest frustrations for our researchers and a huge time sink. All of that has gone away since adding AgentPrism, and we’re excited to bring that functionality to our users.” — Julia Neagushow more

Do you know what your OpenClaw agents are actually... doing? If not, bookmark this. Here is a complete 3D neural command center for monitoring agents, nodes, logs, and live activity in real time you can build yourself with this prompt. FULL PROMPT: I’ll upload a GitHub soon with the working files for all the projects I’ve shared so far. Notis on.show more

🚨 Introducing Nomis Pass: All the Scores in a... Single Subscription. Easy to Get. Even Easier to Get Airdrops! You asked for less chaos. We built it. Start Here -> 1/ The price — $5. Potential rewards = $15K. Learn more 👇🧵show more

rewatching that lewis and franco moment i can’t, the... way the front wing just folded under lewis’ car 😭😭😭😭😭😭 and franco didn’t even feel a single thing yet lewis got a penalty for thatshow more

I just put together all my AI Agents posts... in a single PDF. It covers: - Agent fundamentals - LLM vs RAG vs Agents - Agentic design patterns - Building Blocks of Agents - Building custom tools via MCP - 12 hands-on projects for AI Engineers Download link in next tweet.show more