https://blog.yusukeikoma.com/tags/agents/Recent content in agents on Ikoma's BlogHugoen-usThu, 06 Aug 2026 14:41:04 +0900https://blog.yusukeikoma.com/posts/search-before-write/Thu, 06 Aug 2026 14:41:04 +0900https://blog.yusukeikoma.com/posts/search-before-write/Designing AI agent memory with retrieved context, durable task records, and evidence-based create or update decisions that tolerate search index lag.https://blog.yusukeikoma.com/posts/transcript-is-not-a-task/Tue, 04 Aug 2026 22:38:09 +0900https://blog.yusukeikoma.com/posts/transcript-is-not-a-task/Designing a meeting AI pipeline with separate transcription, summarization, and task extraction, preserving evidence and resolving deadlines from meeting time.https://blog.yusukeikoma.com/posts/resident-agent-behind-nat/Mon, 03 Aug 2026 19:03:09 +0900https://blog.yusukeikoma.com/posts/resident-agent-behind-nat/Designing a resident agent behind NAT with outbound connections, separate liveness checks, and on-demand SSH sessions for interactive access.https://blog.yusukeikoma.com/posts/ai-agent-clean-architecture/Tue, 07 Apr 2026 12:00:00 +0900https://blog.yusukeikoma.com/posts/ai-agent-clean-architecture/Why I built an AI agent platform in Go instead of using LangChain, and how Clean Architecture made model, memory, tool, and streaming concerns independently replaceable.