← back
Your agent architecture has a half-life of 6 months — Dan Farrelly, CTO, Inngest
Takeaway
Decouple durable execution from fast-changing models and ephemeral compute to reduce architecture rewrites.
Summary
- Farrelly separates agent systems into execution, context, and compute layers with different rates of change.
- Execution owns flow, state, retries, and durability; context contains models, prompts, tools, and memory; compute supplies sandboxes and browsers.
- External durable state enables failed long-running work to resume without replaying the entire task.
- A stable execution layer supports events, schedules, APIs, human input, and full-session observability while allowing other components to change.
durable-executionarchitectureinngest
Original description
A short history of the right way to build an agent: RAG, ReAct, prompt chaining, orchestrator-workers, MCP, CLI, MCP again... CLI again?? Every time you adopt a trend you rebuild your architecture. In this talk, Dan Farrelly, Inngest cofounder and CTO, is not going to tell you what comes next. He's going to show you how to build so it doesn't matter. He'll cover the core primitives that show up in every production agent, how bringing decisions closer to code provides more stack flexibility, and why the right execution layer unlocks faster iteration. Dan Farrelly CTO and Co-founder · Inngest [LinkedIn]( / djfarrelly ) Dan Farrelly is CTO and co-founder of Inngest, a platform for durable serverless functions, workflows and agent orchestration. He was previously CTO at Buffer and created developer tools including Timezone.io and MailDev.