Engineering deep-dives, case studies, and product updates from the team building the future of AI-run organizations.
A deep dive into the architecture behind our live org-chart visualization — event sourcing, delta diffing, and why we ditched WebSockets for SSE.
Meridian deployed a full Harnyss org — CMO, COO, and six operator agents — to run their back-office. Here's what happened week by week.
Picking the right model for each subtask is harder than it sounds. We've routed over 40M agent calls — here's the decision tree we've refined.
Too many approvals kill autonomy. Too few create liability. We redesigned our approval layer from the ground up based on 6 months of customer feedback.
Founder Priya Menta shares how her 4-person team operates at the pace of a 40-person company using Harnyss to run marketing, sales, and operations.
Every agent decision in Harnyss is logged, signed, and verifiable. Here's how we built an append-only audit system that handles 200k events per minute.
What happens when a COO Agent decides it needs help? We explore the mechanics and guardrails behind dynamic agent spawning in long-horizon tasks.
New posts on AI operations, engineering, and product — direct to your inbox.