Christian Pojoni
Tagged

Agents

5 posts

12 Apr 2026 · 8 min read

Streaming UI from AI Agents: 4 Approaches Ranked

AG-UI, A2UI, Vercel AI SDK streamUI, and Kombai take four different bets on how agents should build interfaces. One question decides which wins.

aiagentsfrontendarchitecture
Open post
10 Apr 2026 · 7 min read

Your MCP Setup Is Burning 90% of Its Context Window. Here's the Fix.

Every MCP tool you connect loads its full schema upfront, before you type a word. Anthropic's deferred loading fixes this.

mcpclaudeaiagents
Open post
6 Apr 2026 · 6 min read

Svapna or Sushupti: What Three Traditions Say About Offline Memory Consolidation

Neuroscience, recent AI papers, and an ancient Sanskrit text converge on the same insight about offline consolidation, yet disagree on which phase of sleep matters most.

aiagentsmemorymuninndb
Open post
6 Apr 2026 · 5 min read

Sleep-Inspired Memory for LLM Agents: 6 Papers Ranked by What You Can Ship This Week

I read 6 papers on biologically-inspired memory replay for LLM agents. Only 2 are worth your time if you're building, not publishing.

memoryllmagentsmuninndb
Open post
4 Apr 2026 · 7 min read

Stop Designing Your AI System. Design Its Environment.

Self-evolving AI harnesses fail when they optimize a fixed evaluator. The biological model is right: what needs to evolve is the selection pressure, not just the genome.

aiagentsarchitectureinterpretability
Open post