Seevali Rathnayake
Feed Writing Builds Constellations About
ESC

Type to search across all signals

WRITE THOUGHT BUILD DECISION ARC

    No signals found

    ↑↓ navigate ↵ open esc close
    ← Back to feed
    Lens

    AI Agents & Tooling

    21 signals

    WRITE Aug 5, 2026
    ai-agentsclaude-codemulti-agentorchestrationcost-optimizationmission-command
    The Orchestration Dividend: What a Month of Mission-Command Cost, to the Cent

    Claude Fable 5 parsed every Claude Code transcript on the two machines I used in July 2026 and repriced 77,592 assistant turns at API list rates. The fleet ran the month for $6,648 in API-equivalent spend. The same tokens on the frontier model alone would have billed $15,482.

    BUILD May 25, 2026
    Watching the Loop Forge Itself: A Demo Repo That Refactored Its Own Loop

    I pointed my Ralph Loop at its own script to ship a public demo. The useful part was not the recursion — it was every decision I made while the loop made the git log lie, burned $4 on an impossible spec, and taught me which corner I should have cut instead.

    shipped
    BUILD May 23, 2026
    Hardening the Ralph Loop: The 68K-Token Tax in My Overnight Coding Agent

    My first overnight Claude Code loop produced real commits and still failed: it burned quota faster than doing the work by hand. The real leak was the 68K-token runtime tax hiding before my prompt.

    shipped
    BUILD Mar 30, 2026
    The Voice Layer

    How Metis learned to speak — and why a human had to listen four times before it got the main word right.

    shipped
    BUILD Mar 28, 2026
    The Output Layer

    Where the vault speaks back. The pipeline from captured knowledge to published content — and why the blank page problem is gone.

    shipped
    BUILD Mar 28, 2026
    Lyra — The AI Pipe

    What the AI in this system actually does — and what it doesn't. Obsidian holds the knowledge. Lyra moves it.

    shipped
    DECISION Mar 28, 2026
    Context: Sixteen years of professional knowledge with no expression layer. Five tools tried — EverNote, OneNote, Notion, Twos, and two years of unstructured Obsidian experiments — none solved the fundamental problem. The knowledge accumulated. The words never came out right.
    Why PARA. Why Obsidian.
    → PARA applied to Obsidian on January 6, 2026, for structure. NanoClaw connected on March 9, 2026, for access. Plain Markdown files as the substrate — readable by AI agents without any API, authentication, or rate limits.

    Consequence: Capture became zero-friction via WhatsApp. The knowledge base became programmatically readable. The expression problem dissolved: instead of sitting down to write, I describe what happened. The vault routes it. The structure holds it. The AI layer expresses it.

    BUILD Mar 28, 2026
    The Capture Layer

    How a WhatsApp message at 11pm becomes a structured knowledge base entry by morning — the raw input layer of the second brain.

    shipped
    WRITE Mar 28, 2026
    ai-agentscareerwritingknowledge-management
    The Breed

    The AI era didn't create new knowledge. It created an expression layer for people who already had it. This is for that breed.

    WRITE Mar 28, 2026
    knowledge-managementmetricsworkflow-automation
    Three Months of Capture

    What the vault actually looks like after three months of PARA and three weeks of automated routing. Real numbers from a real system.

    WRITE Mar 28, 2026
    ai-agentsknowledge-managementwriting
    The LLM Smell Problem

    Someone said my blog has LLM smell. They were right about the writing. They were wrong about where the knowledge came from.

    WRITE Mar 26, 2026
    ai-workflowimage-generationgeminicloudflare-r2
    An AI Pipeline That Reads Your Post Before It Draws the Picture

    How to generate blog cover images that actually reflect your content — using a three-tool pipeline built around visual metaphor, not stock photo logic.

    WRITE Mar 26, 2026
    ai-toolsdesignclaude-skillsux
    Five World-Class Designers in Your IDE

    Design Council is a Claude Skill that activates five distinct philosophical lenses on demand — Ive, Rams, Hadid, Ingels, Norman — each asking a different question about the same design.

    WRITE Mar 26, 2026
    ai-workflowdev-toolsclaude-codebmad
    The Dev Workflow That Follows You Everywhere

    How NanoClaw, the BMAD Method, and Claude Code Remote Control combine into a single workflow that goes from late-night insight to shipped code — regardless of what device you are on.

    BUILD Mar 25, 2026
    Claude Skills

    Open-source Claude Skills for design, architecture, and developer workflows.

    shipped
    WRITE Mar 16, 2026
    aiengineering
    Giving AI Context in Large Brownfield Codebases

    AI generates plausible but wrong code in large legacy codebases — not randomly wrong, but wrong in ways that quietly erode conventions. Here's how to prevent it.

    BUILD Mar 5, 2026
    Nyx

    GPU-accelerated Rust terminal with local AI. Privacy-first, no cloud dependency.

    active
    WRITE Mar 3, 2026
    aiarchitecturenanoclawkleosnyx
    One Brain, Three Interfaces

    NanoClaw, Kleos, and Nyx are three different ways to talk to the same AI. Here is why that architecture exists and how it came together.

    BUILD Feb 20, 2026
    Kleos

    Voice-first PWA and web dashboard for NanoClaw. React 19 + Vite 7.

    active
    THOUGHT Feb 15, 2026

    AI doesn't replace engineers — it raises the floor. Stop trying to make humans consistent; make your tooling consistent instead.

    BUILD Feb 1, 2026
    NanoClaw

    Personal AI assistant running Claude in containers with isolated memory per context.

    shipped
    Get new posts by email
    Software Architect. The work speaks.
    LinkedIn ↗ GitHub ↗ RSS
    Editorial policy AI disclosure