Skip to content
ceaksan

ai agents

QUERY = 'contents'; CATEGORY = 'ai-agents' // 22 rows

ai

Argus: Make Your AI Coding Assistant's Web Searches Visible

AI coding assistants run web searches during a conversation, but those searches stay invisible. Argus logs every WebSearch and WebFetch call to a local SQLite database, lets you query it from the CLI, and analyzes search patterns. I walk through what 68 days of real data revealed.

6/1/2026
ai

Compaction-Friendly Search Output: A Practical Playbook

There is a way to compress search output before the agent context window fills. file:line + 2 lines context format, file-cache, dedup, code examples for tool result wrappers, and measurement results.

5/22/2026
ai

Token Budget Arithmetic for Agent Search

An agent context window is a budget; search is a sub-budget. Where the ~15% search budget rule comes from, how it scales for different context window sizes, and how to catch overflow signals, with numerical examples.

5/20/2026
ai

Code Search for AI Agents: ripgrep, ast-grep, or Semantic?

ripgrep is fast, ast-grep is structural, semantic search is smart. But for an agent the right question is different: which backend in which order, under what token budget? Decision tree, academic evidence, and practical policy snippets.

5/19/2026
ai

ADR vs Spec-Driven Development: Why, What, and Using Both

Architecture Decision Records (ADR) and OpenSpec serve complementary roles: ADR answers 'why' a decision was made, spec defines 'what' gets built. How they work together in AI-assisted development.

1/7/2026 Updated
ai

From OpenSpec to Brainstorm + Court: Spec-Driven Workflow with Worktree

Evolution from OpenSpec CLI to a brainstorm + court pipeline, multi-AI evaluation, and parallel spec-driven development with git worktree.

4/19/2026
ai

Why KISS Is More Relevant Than Ever in the Age of AI Agents

According to Gartner, over 40% of agentic AI projects will be canceled. Why? Unnecessary complexity. Kelly Johnson's KISS principle, defined in the 1960s, plays a more critical role in AI agent architecture than in classical software.

7/17/2019 Updated
ai

Why SoC Is Critical in AI Agent Architecture

Separation of Concerns is not just a software principle but the fundamental design decision that determines whether an AI agent architecture collapses or stands. Context boundaries, defense layers, and protocol separation.

7/22/2019 Updated
ai

AI-Powered Codebase Audit: A Production-Grade Approach for Solo Entrepreneurs

Enterprise-quality codebase audit process using AI tools as a solo entrepreneur. Guardrail-driven AI-assisted coding, 6 audit tracks, and the Augmented CTO model.

3/11/2026
ai

Living Architecture Documentation for AI Coding Agents: Research, Approaches, and Tools

Codified Context, AGENTS.md ecosystem, C4 Model, Repomix, ADRs, Spec-Driven Development, Google Code Wiki. A comparative analysis of 11 different approaches to giving AI agents architectural context, backed by research.

3/6/2026
ai

Hybrid Search: Smart Search Architecture with FTS5 + Vector + RRF

Keyword search alone isn't enough. Neither is vector search. What happens when you combine them with Reciprocal Rank Fusion? Hybrid search architecture through the dnomia-knowledge implementation.

2/26/2026
ai

Decision Gate: The Missing Piece of Vibe Coding

AI generates code fast, but every accept is a decision. The 8-criteria Decision Gate framework, adapted from Stage-Gate, systematizes technical decisions in AI-assisted development.

2/22/2026
ai

Pre-injection vs MCP Tool Loop: Context Strategies for AI Coding Agents

GrapeRoot injects context before the model starts, CodeGraphContext uses MCP tool loops. Same repo, same model, same prompts. One comes out 31% cheaper. Where's the architectural difference? Benchmark data and comparison with my own system.

2/21/2026
ai

Which Files Do You Actually Read? Developer Interaction Tracking

Do you know which files you looked at most during a week of work? Which searches returned zero results? Using Claude Code hooks to collect interaction data and trace analytics to reveal patterns, I tracked my own workflow. The data was surprising.

2/17/2026
ai

Context Engineering for AI Coding Agents: From Static Documents to a Living Ecosystem

CLAUDE.md and architecture.md are not enough. A four-layer context engineering ecosystem combining semantic code search, knowledge base, decision governance, and learning loops. Based on real project experience.

2/15/2026