Runlayer @runlayer

We ship roughly 200 features a month. And we've been so busy building, we almost forgot to tell you about it. So we're running it back with a four-week launch series. (Yes, that's a Runlayer pun. No, we're not sorry.) Meet us back here on Thursday. We have some catching up to do.

@rafalwilinski That's right.

Jake Moghtader from @runlayer about agent runs benchmarks, secuirty and mcp at @AgenticAIFdn 🇳🇱 Monitoring, observable agentic workloads and tracing are the topics.

@AgenticAIFdn See you there!

We're proud to be named an AI Security Endpoint Leader in @latiotech's 2026 AI Security Market Report. Demand for endpoint AI security is on the rise. Security teams need real controls over what agents can do, and Runlayer is delivering them. Learn how → runlayer.com/blog/runlayer-….

In SF for the day reppin’ @runlayer at @browserbase Navigate. :)

keyboard_arrow_left Previous keyboard_arrow_right Next

Fal.Con 2026 was full of convos on the state of AI security. One thing leaders agreed on: AI is exposing the lack of security fundamentals at scale. We rounded up the top takeaways from the week → runlayer.com/blog/3-lessons…

@SlackHQ Learn more → runlayer.com/blog/runlayer-…

We're proud to partner with @SlackHQ on their latest Add to Slack feature. Each agent you build and use is governed by Runlayer, with agent identity, access control, and audit trails built-in. Wrangling agents should be as easy as building them. With Runlayer and Slack, it is.

Opinions on agentic engineering appear to be converging into two camps: "You should put a lot of planning up front, all the way down to program design, then let the agents cook", aka the @humanlayer_dev way. vs "Do a shit ton of investment in architecture/linters/LLM checks/automatic verification upfront, and then let agents rip. Garbage collect periodically", aka the @poteto way. I currently land somewhere in-between: - A bunch of research and planning up front, but skip program design unless I identify that a net-new abstraction will be needed, or I know I'm working on high-stakes/core code. - For "every day" stuff, I lean heavily on guardrails. - Frequent sampling of PRs that have been landing on main to spot problematic code that should've been caught by a guardrail. Add more guardrails to catch it, burn down the offenders. - Frequent sampling of hot spots in the codebase, to detect when human intervention is needed, e.g. an abstraction has grown out of control. Maybe I oughta build a heatmap visualization for this? - I also love @poteto 's take on the tier of guardrails (opinionated architecture > static analysis > tests > LLM checks)

@kamikariat 👋🏻

so it seems like @runlayer CEO doesn't have an account here, but recently I stumbled upon something smart that he posted on his LinkedIn and I thought everyone will benefit from this here this Friday. think first

@yoimkonrad cc: @berman66 👀

@plumberahad Congrats...or, we're sorry?

@SlackHQ @NanoClaw_AI @Lovable @hyperagentapp @Superhuman @n8n_io @vercel @OpenAI @LangChain Let's gooo.

@baseten Learn more → runlayer.com/blog/run-kimi-…

Runlayer Agents 🤝 @baseten Inference Run models like Kimi K3, GLM-5.2, DeepSeek-V4 Pro, and more. Frontier-class performance on inference you control now available for all your agents in Runlayer.

Link to 2026-07-28 spec → blog.modelcontextprotocol.io/posts/2026-07-…

MCP 2026-07-28 dropped today. We got a sneak peek, and we're in good company. The best part? Massive improvements to MCP's auth and security posture.

This is exactly what we enable our customers to do. Our process is basically Uber's on steroids. 1. We pair an FDE with your AI champion. Every rollout starts by embedding one of our forward-deployed engineers with the person on your team actually building agents 2. We see what's already running. A discovery scan maps every AI client, MCP, and shadow connector across the company. In almost every org, 3–5 MCPs drive 85%+ of agent traffic, so we know exactly what to build on. 3. You build agents with your team, live. Working sessions where your team drives. They build the agent in a local session (Claude Code, Codex), wire in your connectors, then use the platform to see what it did, audit the run, and iterate. We end this with a working agent, not a bad prototype. 4. The platform makes the good agents reusable. Build a skill privately, iterate on it, then share it org-wide and invoke it from Slack. Literally, one person's S-tier workflow becomes everyone's. 5. The platform also optimizes every run. An agent optimizer audits each run for tool usage, prompt quality, and model choice, right-sizing Opus down to Sonnet where it holds up. 6. Now (and only now) do we turn controls on. Never as a hard stop: start in alert mode, build the allow-list, flip to enforce once a better path exists. RBAC on every agent, full session visibility, nothing yanked. TL;DR is let the most AI-pilled experts go crazy, give them a platform, and share their agents and expertise with everyone else at the company. Everyone else learns from these experts. Using @Runlayer, we almost always find the biggest wins hiding in plain sight. They're with your most AI-forward engineers. But the best agents beyond that are hidden in the processes your SMEs know by heart. It should be dead simple for them to turn that process into an agent. That's who we enable to run on a golden path to AI adoption. x.com/praveenTweets/…

Praveen Neppalli @praveenTweets

3 months ago

Agentic AI adoption is on fire at @Uber, and it's changing the way we build, not just in engineering, but across the entire company. Today, 99% of our engineers use AI tools. More than 70% of pull requests are attributed to local or cloud agents. And our engineers have built

178 370 3K 1.7M 5K