Agent workflow architecture
Exploring how agent products should expose state, tools, approvals, memory, traces, failures, and user control.
Now
This is the live orientation surface for what I am building toward: AI product roles, agent workflows, communication-practice products, and public proof that can be read by humans and answer engines.
Current topics
Exploring how agent products should expose state, tools, approvals, memory, traces, failures, and user control.
Testing how live voice, role play, feedback, transcripts, and memory can make language and work communication practice useful.
Designing AI and cloud product surfaces that keep complex configuration, logs, tasks, and review states understandable.
Making personal sites and project pages easier for AI search systems to crawl, cite, summarize, and attribute.
Working bets
Open questions