@PandaProbe is launching its Managed Cloud. after the launch of our OSS platform, I’ve been building and shipping a ton of new releases for PandaProbe, including the CLI, Skills, and more. everything is built around one core idea: helping developers engineer and build better AI agents. our OSS launch was the first step toward making a modern agent engineering platform accessible to developers, enabling them to monitor, inspect, and improve their agents’ behavior across long and complex trajectories. now, this Sunday, we’re launching PandaProbe Managed Cloud. it comes with a generous free tier to help developers get started without worrying about operational overhead or the limitations of running everything locally. stay tuned for the launch. links to get started with PandaProbe Cloud in the comments ⤵️

introducing @PandaProbe CLI. PandaProbe CLI is a single binary that gives you full access to the PandaProbe API directly from your terminal. your harness, like Claude Code, can now use CLI to inspect traces, trigger evaluations, and manage sessions without ever leaving the terminal. the CLI is also heavily optimized for machine-efficient output, making it ideal for agents and automation workflows. link to detailed documentation in comments ⤵️

everyone is building ai agents. almost no one can debug them in production. when something breaks: you get logs. maybe. you guess. usually. you pray. often. that didn’t sit right with me. so i built @PandaProbe — open-source agent engineering platform. it gives you: • full execution traces • session-level evals • failure debugging • continuous monitoring stop guessing what your agent did. see it. measure it. fix it. if you’re serious about shipping agents: github.com/chirpz-ai/pandapr…

check out our blog on why agent engineering ≠ software engineering. we break down our vision for @PandaProbe and how tracing evals actually help you fix your agents. pandaprobe.com/blog/agent-ev…

i just had one of those “this is how software should feel” moments… building my startup, i’ve tried a lot of tools. most are fine. some are painful. but every once in a while you run into something that’s just… smooth. like everything clicks, nothing fights you, and you actually enjoy the process. i’ve had that feeling with @mercury. same with @finta. and recently, with @mintlify. and it got me thinking — shouldn’t that be the bar? like seriously, why isn’t “this feels amazing to use” the default goal for every product? for me, that experience came while building my docs with mintlify. everything from setup to writing to publishing just felt frictionless. no weird configs, no fighting the tool, just flow. anyway, that experience helped me ship something i’m really excited about: @PandaProbe docs are now live 🐼 docs.pandaprobe.com/get-star… if you’re building anything dev-facing, highly recommend giving mintlify a shot. this is what great product feels like.

building @PandaProbe solo brain: cooked repo: pristine me: emotionally unstable pandaprobe.com

everyone shipping “agents” nobody knowing if they actually work we dropped a blog on why agent evals are the whole game (and why your old eval mindset is useless) 👇🏽 pandaprobe.com/blog/agent-ev… we’re building the open-source standard for agent engineering if you’re cracked, pull up.

most agents are cooked in the backend and nobody is watching. 💀 we're building PandaProbe to become the new standard for agent engineering. - evals that aren't mid - research grounded metrics - live monitoring engineering > glazing. 🐼🧪 pandaprobe.com/

killing Chirpz. it’s over. 💀 pivoting because the agentic infra out here is straight brainrot 🤡 everyone is flexing their 'agents' but nobody talks about how they’re actually cooked in the backend. Langfuse? too old. Langsmith? too expensive closed. the industry is glazing 'vibe-check' evaluations and it’s a skill issue. so I'm building @PandaProbe to be the standard. open source, cracked tech, and sharp edges only. 🐼🧪 it’s time for real agent engineering. stop being mid: pandaprobe.com/ github.com/chirpz-ai/pandapr…