Skip to content
Nikola Balićnibzard
OverviewWritingProjectsNowAbout
Search ↗ GitHub ↗ RSS feed ↗

Entries tagged with: ARCHITECTURE

  • Jun 12, 2026

    A Deep Research Agent That Survives Its Own Failures

    What we learned from making a research agent durable, routed, visible, and eval-driven.

    ↗
  • Jun 10, 2026 · Updated

    An autopsy of Claude Code's deep research

    Claude Code's deep-research workflow, pulled from its binary and dissected. Wide search, no second hop.

    ↗
  • May 07, 2026

    Agent-Native Extensibility

    How extensibility shifts from packaged plugins to agent-readable recipes, and why the connector is the new extension point.

    ↗
  • Nov 16, 2025

    Demos Run on Embeddings. Production Runs on Structure.

    Why the gap between AI demos and shipping AI is a reliability gap, not a capability gap.

    ↗
  • Oct 26, 2025

    Stop Using .md for AI Agent Instructions

    Files ending in .md trigger automatic processing that breaks agent instruction files. Use dotfiles instead.

    ↗
  • Oct 25, 2025

    Serving Humans and AI Through Content Negotiation

    How I built a dual-format delivery system serving identical content to humans and AI agents with no hidden restrictions.

    ↗
← All Tags
Tools and notes by Nikola Balić.
All activityThoughtsTopics RSSCVX LinkedIn