# Nibzard

> Complete collection of Nikola Balić's technical writings, thoughts, project updates, and ideas from nibzard.com. This file provides LLMs with structured access to all published content.

This collection includes in-depth technical articles on AI and development tools, personal reflections, project updates, and strategic ideas. All content is published by Nikola Balić and focuses on practical insights from building and shipping AI-powered products.

For the complete concatenated content of all articles, visit [https://nibzard.com/llms-full.txt](https://nibzard.com/llms-full.txt).

## Log Articles

- [Beside You, Not Between You](https://nibzard.com/beside-you): The best agent UX metaphor exists: the anonymous animal cursor in Google Docs. Agents as collaborators, not intermediaries.
- [A Software Factory Is No Substitute for Maturity](https://nibzard.com/dark-factory): The real barrier to the software dark factory isn't agent capability. It's the organizational capability to manage them.
- [A Deep Research Agent That Survives Its Own Failures](https://nibzard.com/durable-researcher): What we learned from making a research agent durable, routed, visible, and eval-driven.
- [An autopsy of Claude Code's deep research](https://nibzard.com/deep-research): Claude Code's deep-research workflow, pulled from its binary and dissected. Wide search, no second hop.
- [A Harness for Every Run](https://nibzard.com/harness): A reflection on Anthropic's dynamic workflows post, from someone building a browser agent on the same idea.
- [The Model Is the Smallest Decision You'll Make](https://nibzard.com/smallest-decision): Everyone building agents asks which model to use first. Wrong first question. The harness is where the agent lives or dies.
- [Serve Markdown to Agents, HTML to Humans](https://nibzard.com/agent-md): A copy-paste recipe for content negotiation that gives AI agents clean markdown while browsers keep getting HTML.
- [Agent-Native Extensibility](https://nibzard.com/agent-native): How extensibility shifts from packaged plugins to agent-readable recipes, and why the connector is the new extension point.
- [Trained Qwen to Write Clojure Better Than GPT-5.4 (Kinda)](https://nibzard.com/clojure-phone): I trained a Clojure LLM from my phone. It 'beat' GPT-5.4—kind of. Here's what actually happened.
- [The Hard Problems Nobody Has Solved](https://nibzard.com/hard-problems): Four unsolved problems blocking the agentic future: correctness, architecture drift, context scaling, and judgment.
- [Bash Owns the Loop](https://nibzard.com/wrappers): A durable wrapper pattern for autonomous agents: Bash owns state, validation, recovery, and completion.
- [What Pretext Reinforced About AI Loops](https://nibzard.com/oracles): Pretext reinforces what serious AI-assisted engineering looks like: hard constraints, real oracles, tiny repros, rejection.
- [Optimizing Skills](https://nibzard.com/optimizing-skills): Two weeks of agent benchmarks taught me that variance is a cost problem, and the real fix was better tooling.
- [AI-Native Dev Teams Start With Structure, Not Models](https://nibzard.com/ai-native-dev-teams): AI-native dev teams don't start with better models. They start with structure machines can actually read.
- [The Bubble and the Long Game](https://nibzard.com/bubble-long-game): What the printing press taught me about AI, FOMO, and the decades-long game of technological diffusion.
- [Claude Code with Multiple Accounts on One Machine](https://nibzard.com/claude-dual-provider): Use Claude Code with your normal login or z.ai via shell wrappers, without swapping config or leaking tokens.
- [The Post-Copyright Era of Software](https://nibzard.com/post-copyright-era-software): Software was already an awkward fit for copyright. AI turns that mismatch into a full-blown regime change.
- [Explore once, script forever: turning web runs into scripts](https://nibzard.com/cashout): Let an agent discover a messy web UI flow once, then export the exact tool commands as a deterministic bash script.
- [The Hidden Language of Search](https://nibzard.com/search-translator): AI answer engines rewrite your prompts into queries. Understanding this translation layer explains the weird keywords in your GSC.
- [What Makes a Great Coding Agent](https://nibzard.com/great-coding-agent): 10 principles that separate genuinely useful coding agents from flashy demos—and a north star spec for building them.
- [Designing CLI Tools for AI Agents](https://nibzard.com/ai-native): Most 'AI-native' tools are built with AI features. But what about tools designed FOR AI agents to use? Here's the playbook.
- [From Bash Script to AI-Native Go CLI in One Session](https://nibzard.com/bash-script-to-ai-native-go-cli): Turned a Bash script into a proper Go CLI with Whisper bootstrap and cross-platform releases—all in one AI coding session.
- [Eager Agents](https://nibzard.com/eager-agents): Agents over-deliver. They write tests, update docs, refactor nearby code—when all you wanted was a surgical fix.
- [40% of Signups This Week Came From AI Recommendations](https://nibzard.com/ai-discovery): Exactly 40% of new users this week found steel.dev through AI recommendations. Users told us this during onboarding.
- [Making CLIs Agent-Friendly with Loops and Schemas](https://nibzard.com/agent-ci): Building reliable agent tooling through loops, logs, and schemas.
- [Meat Moat: Why Cheap Code Doesn't Kill Defensibility](https://nibzard.com/meat-moat): When software is cheap to clone, the moat shifts to trust, liability, verifiability, and multi-party adoption.
- [The Instantiation Era](https://nibzard.com/instantiation-era): AI just rescued a failed Mistral.ai clone in one prompt. Web development is over.
- [Out of Weights](https://nibzard.com/out-of-weights): What happens when you use AI tools so new they weren't in the training data.
- [The Human Web Is Becoming Agent Web](https://nibzard.com/agent-web): I'm joining Steel as founding growth lead. The web is shifting from human clicks to agent-run workflows.
- [The Disequilibrium Advantage](https://nibzard.com/disequilibrium): In stable worlds, incumbents win. In disequilibrium, speed wins—because disequilibrium makes the world plastic.
- [Hacker News Hug: What Serverless Really Means](https://nibzard.com/hn-hug): 595K edge requests and 38GB of transfer in a day taught me that 'static' doesn't mean 'unmetered' on serverless platforms.
- [X's Grok-Powered Algorithm: The January 2026 Rewrite](https://nibzard.com/x-grok-algorithm): X's Grok algorithm analyzed with AI agents. Comparison with old algorithm and practical learnings.
- [Looper: The AI Junior That Never Forgets the Backlog](https://nibzard.com/looper-article): Why treating AI like a junior engineer—with a backlog, a schema, and a review gate—beats giving it free-form leeway.
- [One Skill to Rule Them All](https://nibzard.com/unified-skills): How I eliminated drift between AI code assistants using GNU Stow and a unified skills directory
- [The Agentic AI Handbook: Production-Ready Patterns](https://nibzard.com/agentic-handbook): A comprehensive guide to 113 production-informed patterns for building reliable AI agents.
- [The API is the Product](https://nibzard.com/api-first): In an AI-agentic future, if it's not in the API, it doesn't exist.
- [AI Agent Filed an Issue As Me](https://nibzard.com/agent-identity): When an autonomous agent escalated by filing a GitHub issue using my identity
- [AI Agents Are a Stress Test for Your Dev Stack](https://nibzard.com/agent-stress-test): Agent loops make code cheap. They also expose how brittle, non-standard, and half-tribal our development environments really are.
- [Two AI Agents Walk Into a Room](https://nibzard.com/demig): What emerged when two AI agents in a conversation loop revealed the eerie boundary between human and machine continuity.
- [2025: The Year AI Became a Teammate](https://nibzard.com/2025-year-in-review): AI became a teammate in 2025. From startups back to academia, advisory, and a summer of full-time AI experimentation.
- [Claude-Zhipu Parallel CLI Setup](https://nibzard.com/claude-zhipu): Complete setup guide for running Claude Code CLI with Zhipu API alongside your existing Anthropic installation
- [A 2026 Design Principles for AI-Native Products](https://nibzard.com/ai-design-principles): Software is no longer a noun, it's a verb. Here's how to design for AI-native products where users shape outcomes.
- [Growth Is Value Flow, Not Vanity Metrics](https://nibzard.com/growth-value-flow): Why chasing vanity metrics kills startups and how to think about growth as discovering and scaling value creation
- [Anthropic Bought Bun: Devtools Just Became AI Infrastructure](https://nibzard.com/bun-acquisition): The Bun acquisition isn't about M&A – it's about devtools becoming core AI infrastructure, not just SaaS above it.
- [Demos Run on Embeddings. Production Runs on Structure.](https://nibzard.com/structure): Why the gap between AI demos and shipping AI is a reliability gap, not a capability gap.
- [AI Agents Need Clearer Delegation](https://nibzard.com/orchestration-era): What hundreds of AI conversations taught me about effective agent workflows.
- [Agent Labs Are Eating the Software World](https://nibzard.com/agent-labs): Why product-first AI startups will dominate the next decade while model labs build the infrastructure they run on
- [Stop Using .md for AI Agent Instructions](https://nibzard.com/dotfiles): Files ending in .md trigger automatic processing that breaks agent instruction files. Use dotfiles instead.
- [Mention Engineering: The Content Side of Prompt Craft](https://nibzard.com/mention-engineering): Analysis of AI search behavior reveals why some brands get cited while others disappear in AI-generated responses
- [Serving Humans and AI Through Content Negotiation](https://nibzard.com/architecture): How I built a dual-format delivery system serving identical content to humans and AI agents with no hidden restrictions.
- [AI Agent Reasoning Failures: A Technical Autopsy](https://nibzard.com/autopsy): Five concrete reasoning breakdowns from a Claude Code session and what they reveal about AI agent cognitive limitations.
- [Developer Trust Over Conversion: The 10 Touchpoint Rule](https://nibzard.com/trust): Developers need 10+ touchpoints. Build trust through systematic signals, content, and community engagement.
- [The 20-Year Playbook: How to Build an AI Startup That Lasts](https://nibzard.com/startup-moat): Condensed wisdom from Marc Andreessen and Charlie Songhurst on winning the AI game over decades, not quarters
- [The Real Bottleneck in AI Development: Humans](https://nibzard.com/ai-bottleneck): Why the future belongs to agent orchestration, not faster typing.
- [From Twitter Analysis to Chrome Extension in Hours](https://nibzard.com/chrome-extension-ai): How AI coding agents democratized Chrome extension development, turning algorithm insights into shipped product overnight.
- [From Shower Ideas to Production: Autonomous AI Agents](https://nibzard.com/shower-to-production): Running 100% autonomous AI agents in VMs to go from idea to implementation without touching a keyboard
- [AI Ate Its Own Tail, and I Learned Something About Writing](https://nibzard.com/ai-ate-its-tail): AI analyzed its own git history. Meta-experiment revealed the urgent need for transparent proof-of-work in AI-human collaboration.
- [When AI Transformer Learns to Orchestrate AI](https://nibzard.com/transformer-orchestration): How we built a strategy controller that coordinates algorithmic approaches and learned to compete with the best
- [AI Coding Agents, Each With a Niche](https://nibzard.com/ai-coding-agents): Each AI coding agent has a niche. Knowing where each one shines is the difference between frustration and flow.
- [Vibe Coding Through the Berghain Challenge](https://nibzard.com/berghain): How my AI coding partner and I obsessed over a nightclub bouncer optimization problem for one intense day
- [Campfire Installation Guide for Oracle Cloud + Cloudflare](https://nibzard.com/campfire-oracle-cloud): Step-by-step installation of Basecamp's Once Campfire on Oracle Cloud Infrastructure with Cloudflare DNS
- [Outcome Liability: Why Agent Authorship Misses the Point](https://nibzard.com/outcome-liability): The future of code liability isn't about who wrote it, but who operates it. Provable assurance beats authorship tracking.
- [AI Agents Just Need Good --help](https://nibzard.com/agent-experience): Clear CLI documentation is your agent API. Vague help text costs 2x more in API calls and failed automations.
- [Implementing FRE in Production: Breaking the Sorting Barrier](https://nibzard.com/fre-production): Building Frontier Reduction Engine in Zig for real workloads, achieving O(m log^(2/3) n) complexity on large sparse graphs
- [The Orchestrated Mind: A Vision for Multi-Agent AI](https://nibzard.com/orchestrated-mind): A thousand AI agents working on one codebase, sharing continuous memory and orchestrated intelligence.
- [Why AI Code Still Needs Human Nudges](https://nibzard.com/nudges): AI excels at generating working code, but sustainable software requires strategic human intervention.
- [Why I Built a Tool to Test AI's Command Line AX](https://nibzard.com/agentprobe): Testing AI agents on CLI tools reveals chaos: 'vercel deploy' took 16-33 turns across runs with 40% success rate.
- [The Agent-Friendly Stack: 50+ AI Projects Taught Me This](https://nibzard.com/agent-stack): After shipping 50+ projects with AI agents, one pattern emerged: winners aren't the most powerful, they're the most agent-friendly
- [The Anti-Playbook: Why AI Dev Tools Need Different Growth](https://nibzard.com/anti-playbook-ai-dev-tools-growth-strategy): Traditional SaaS growth tactics fail with AI dev tools. Here's why you need to throw out the playbook.
- [Code with Claude AI from Your Phone: VM Setup Guide](https://nibzard.com/ssh-tunnel-cloudflare): Turn your phone into a powerful coding workstation with Claude Code running in your homelab VM
- [The 20-Year Technology Adoption Cycle and AI's Acceleration](https://nibzard.com/20yr-tech-cycle): How transformative technologies follow a 20-year adoption cycle, and why AI represents a fundamental departure from this pattern.
- [The Day the Skeptic Blinked](https://nibzard.com/converted): Journey from AI skeptic to convert--proving that the future belongs to experts who learned to work with machines.
- [The Agent is The Loop](https://nibzard.com/theloop): How the llm-loop-plugin transforms AI from a responsive tool into an autonomous agent that iterates until done.
- [When AI Does Research: An End-to-End Experiment](https://nibzard.com/ai-research): How AI transformed an entire research project from conception to arXiv publication in just 2 days of FTE.
- [The Amplification of Bottlenecks](https://nibzard.com/amplification): When AI solves one constraint, it reveals the next. What bottleneck will emerge when coding stops being the limitation?
- [How AI Agents Are Reshaping Creation](https://nibzard.com/silent-revolution): AI is dissolving the boundaries between roles, fundamentally changing who can create software and how quickly ideas become reality
- [What Sourcegraph learned building AI coding agents](https://nibzard.com/ampcode): Real-world insights from Sourcegraph's journey building AI coding agents that actually work.
- [Mastering Claude Code: Boris Cherny's Guide & Cheatsheet](https://nibzard.com/claude-code): Summary and cheatsheet from Boris Cherny's talk on Claude Code: setup, workflows, tools, and tips.
- [Why Senior Engineers Overlook Small AI Wins](https://nibzard.com/vacuum): How experienced devs might be missing the big impact of tiny AI improvements on user experience.
- [AI Coding Agent Pricing](https://nibzard.com/agent-pricing): AI coding agents burn through credits fast while users pay for inefficiencies. Explore fair pricing models and market solutions.
- [Blink, and the entire AI landscape could shift](https://nibzard.com/blink): AI dev tooling is consolidating--acquisitions, coding agents, and fierce competition reshape interfaces, pricing, and memory.

## Ideas
- [AI Agents Dashboard](https://nibzard.com/idea/agent-dash): A web UI for deploying and managing AI agents in containers - A web UI for deploying and managing AI agents in containers

## Thoughts
- [Thought from 2026-02-06](https://nibzard.com/thoughts/260206): Personal reflection
- [Thought from 2026-01-21](https://nibzard.com/thoughts/260121): Personal reflection
- [Thought from 2026-01-15](https://nibzard.com/thoughts/260115): Personal reflection
- [Thought from 2025-07-28](https://nibzard.com/thoughts/250728): Personal reflection
- [Thought from 2025-06-07](https://nibzard.com/thoughts/250607): Personal reflection
- [Thought from 2025-05-26](https://nibzard.com/thoughts/250526): Personal reflection
- [Thought from 2025-05-25](https://nibzard.com/thoughts/250525): Personal reflection
- [Thought from 2025-05-23](https://nibzard.com/thoughts/250523): Personal reflection

## Now Updates
- [Now Update - 2026-02-06](https://nibzard.com/now/260206): Current activities and projects
- [Now Update - 2026-01-14](https://nibzard.com/now/260114): Current activities and projects
- [Now Update - 2025-10-30](https://nibzard.com/now/251030): Current activities and projects
- [Now Update - 2025-08-12](https://nibzard.com/now/250812): Current activities and projects
- [Now Update - 2025-07-29](https://nibzard.com/now/250728): Current activities and projects
- [Now Update - 2025-05-31](https://nibzard.com/now/250531): Current activities and projects
- [Now Update - 2025-05-20](https://nibzard.com/now/250520): Current activities and projects

## Images
- [Image from 2025-05-26](https://nibzard.com/images/250526): Visual content - https://nibzard.com/images/apnea-comprehensive_dashboard.png
- [Image from 2025-05-25](https://nibzard.com/images/250525): Visual content - https://nibzard.com/images/250526_will-agents-replace-us.jpg
- [Image from 2025-05-23](https://nibzard.com/images/250523): Visual content - https://nibzard.com/images/250523_claude4imagecritic.jpeg
- [Image from 2025-05-19](https://nibzard.com/images/250519): Visual content - https://nibzard.com/images/250523_oreillyandkentbeck.jpeg

## Optional

- [Complete Content Collection](https://nibzard.com/llms-full.txt): Full markdown content of all articles in a single file

---

*This file follows the [llms.txt specification](https://llmstxt.org/) for providing LLM-friendly content access.*