SCSébastien Conejoinsebastienconejo.hashnode.dev·4d ago · 6 min readI stopped prompting my agent. Now I design the loop that prompts it. We’re moving past the era where working with an agent meant typing a prompt, waiting, reading the diff, typing again. You are the loop in that setup. Your attention is the constraint, not the model. T00
SCSébastien Conejoinsebastienconejo.hashnode.dev·4d ago · 3 min readThe reliability stack for LLM agents: tools and methodsA request can fail at three moments: before you send it, while it runs, or after it returns. Different tools and habits cover different moments. This is a directory grouped by what each one does. Meth00
SCSébastien Conejoinsebastienconejo.hashnode.dev·Mar 18 · 6 min readMy OpenClaw agent wouldn't stay autonomous. Here's what fixed it.If you’ve set up automations in OpenClaw and they worked for a few hours then stopped silently, this is for you. The agent forgets its instructions, cron jobs show up empty, and you end up babysitting00
SCSébastien Conejoinsebastienconejo.hashnode.dev·Feb 28 · 2 min readThe OpenClaw ecosystem is exploding. I mapped the key players actually gaining tractionI mapped the major players building the OpenClaw ecosystem, just 2 months after its release. What’s unfolding around OpenClaw is unlike anything I’ve witnessed in open-source AI. In 60 days:→ 230K+ Gi00
SCSébastien Conejoinsebastienconejo.hashnode.dev·Aug 25, 2025 · 4 min read🔥 5 Epic Tools To Launch Your MVP NowWhether you’re a solo founder, an indie hacker, or a CTO, one thing matters more than anything: shipping fast. Thanks to AI, a new wave of tools makes it possible to go from idea to product in record time. We’ve picked 5 that cut out the usual pain a...00