← back
The Future Is Domain-Specific Agents - Justin Schroeder, StandardAgents
Takeaway
Domain-specific agents need reusable operational structure and deep integration beyond distributing tools to a general-purpose model.
Summary
- Schroeder defines agents as deterministic software harnessing nondeterministic model outputs toward an objective.
- Businesses build custom agents primarily to integrate their own data, but production requires orchestration, durable execution, validation, and observability.
- Custom agents often lack portability and composability because they depend on local configurations, runtimes, and environments.
- MCP provides useful tool distribution into general-purpose agents, but tools and documentation-like skills alone do not fully solve domain integration.
domain-specific-agentsagent-integrationmcp
Original description
“Composition over inheritance” has always been a good engineering rule. It may also be the unlock for useful AI. A Gmail agent is fundamentally more powerful than a Gmail skill — and when composed with Sheets, Notion, and GitHub agents, the system gets more capable, more reliable, and cheaper to run. Suddenly, smaller models can do real work, and AI can move from internal copilots to customer-facing products. In this talk, we’ll unpack why this architecture hasn’t become the default yet, what’s been missing, and how to start building toward it today. Speakers: Justin Schroeder (StandardAgents): Co-founder of StandardAgents. Compulsive open source builder. Creator of dmux, ArrowJS, FormKit, AutoAnimate, Tempo, zodown X/Twitter: https://x.com/jpschroeder LinkedIn: / jpschroeder GitHub: https://github.com/justin-schroeder