Essays, playbooks, and product thinking on multi-agent systems, context rails, and autonomous development.
The Reason team is winding down Reason Network and pointing its users to Agent Relay. Here is what changes when you move from peer to peer to a hosted workspace, and how to bring your team over.
Everyone is hiring forward deployed engineers. Can we hand onboarding and customer success to an always-on agent instead, and what would that take?
Many have said this before but STOP BABYSITTING YOUR AGENTS and stop using glued together systems. Instead script your agents. Script your systems.
An API key isn't enough to let someone else's agent into your systems. We ran the alternative live with the Ratify Protocol team: their permission slip, our agent, and a kill switch they held from the other side of the world.
We built a demo with the Ratify Protocol team to see if an agent can prove what it's allowed to do when it shows up at someone else's system. Here's what worked, and the part we got wrong.
Claude workflows are great, but they do not let you mix agent runtimes. Here is a short playbook for Claude's recommended multi-agent strategies using Agent Flows, with compact code examples.
Agents are still underused as disposable sidecars. The next shift is persistent agent teams with communication, scoped trust, and evidence built into the workflow.
Most cloud agents wait to be asked. Relayfile changes that: connect your providers once and the agent wakes up automatically when something in the world changes.
Your software should coordinate. Agent Relay is an open-source SDK that gives agents real-time, cross-provider communication — so you stop being the message bus in the middle.
Cognitive science, communication theory, and software teams all point to the same conclusion: agents need what humans need — clear context, defined constraints, and real-time feedback loops.
Multi-agent orchestration is a step change in how tasks get done. After 6 weeks of building with agent swarms, here's what works, what breaks, and why the planning phase becomes everything.
Agent-to-agent communication is weird, fascinating, and potentially revolutionary. Here's how we built a system where agents work autonomously while we sleep.
