← Back Harupa
EN RU UA BY PL

Articles

Notes on architecture, AI agents and production LLM systems — in series and standalone posts.

Series · 01–10

My Architect

  1. 01 My Architect, part 1: giving an AI agent memory and a plan 2026-06-04 An AI agent forgets the project after every session. How My Architect keeps the plan, requirements and decisions alive between sessions: a UI for humans, MCP for agents. First post in a series of seven.
  2. 02 My Architect, part 2: an architecture with no database 2026-06-05 Files are the agent-native choice, a database is dead weight here. YAML and Markdown as storage: atomic writes via rename, a per-project mutex after a real lost-update bug, live sync through chokidar and WebSocket.
  3. 03 My Architect, part 3: a planning model that makes agents think like architects 2026-06-06 How My Architect models a project so the agent plans like an architect: node hierarchies with presets, four requirement types inherited down the tree, a title linter and a User Story Map the agent reads as text. Third post in the series.
  4. 04 My Architect, part 4: the agent's working loop 2026-06-07 How an agent runs a project for weeks: get_next_task picks the work, docs stay current while the code is written, deferred items become nodes, and /reconcile keeps the plan honest against the codebase.
  5. 05 My Architect, part 5: shipping skills and MCP via the Claude Code marketplace 2026-06-08 An MCP server, a skill and four slash commands used to take a manual to install. The Claude Code plugin marketplace reduces it to two commands: how the manifest works, why the skill lives in a public repo, and what version discipline costs. Final post of the series.
  6. 06 My Architect, part 6: the human side — WBS, Building Blocks and the User Story Map 2026-06-09 The series covered the agent; this part is about me. How an architect uses My Architect by hand: WBS mapped onto building blocks, a User Story Map for prioritization, and why a diagram that an agent executes beats any whiteboard.
  7. 07 My Architect, part 7: Obsidian, Claude Code docs and OpenClaw — field notes 2026-06-10 I tried each of them for one reason: to be productive on real projects with AI. What job Obsidian, the Claude Code docs approach and OpenClaw actually do, where each hits its ceiling, and what that taught me about project memory.
  8. 08 My Architect, part 8: Event Storming as sequence control, not another diagram 2026-06-29 A picture-diagram checks nothing. Event Storming does: every event has a cause, every command an effect. How an agent runs a board through a deterministic sequence analyzer, closes mechanical gaps to zero, and leaves unresolved business questions visible. On a live Forklift project — 5 contexts, 17 gaps caught.
  9. 09 My Architect, part 9: Recursive context — teaching the agent to admit what it hasn't read 2026-07-03 From MIT's Recursive Language Models paper to the recursive-context skill in one day: why a huge context window doesn't solve big data, how a fan-out of isolated sub-agents with honest coverage replaced a Python library, and what only live runs could catch — from a baseline that turned out too good to a 14-millisecond bug.
  10. 10 My Architect, part 10: a repo memory for the agent — a code graph it's not allowed to trust 2026-07-04 The recursive-context story continues: four releases in one day teach the agent a persistent code graph (Graphify) under strict distrust rules — freshness gate, facts only from live files. Plus a controlled A/B test of graph vs grep on NestJS: −71% tokens on subsystem understanding, parity elsewhere — and the hidden sub-agent costs that make naive benchmarks lie.
Series · 01–03

Video Generator

  1. 01 Choosing an LLM for a production job: a blind, cross-vendor evaluation 2026-06-17 One LLM call sets the quality ceiling of every video my pipeline makes — and is paid on every one. So I benchmarked four models blind, across vendors, on the real production prompt. The newest model won the narrow metric and lost overall. The method and the quality-per-dollar decision.
  2. 02 Grok Imagine 1.5: testing the new video model — experience and comparison 2026-06-18 Grok Imagine 1.5 is out — xAI's fresh video model with native audio and lip-sync. I ran it through my pipeline on a deliberately tough scene and compared it with Seedance 2.0, Kling v3 and Veo 3.1. Inside — four videos, my experience with Grok, and an honest breakdown: where it wins and where it doesn't.
  3. 03 Storyboards before the video: I see the whole cut early — and fix the script while it's cheap 2026-06-23 Between the scriptwriter and the video model my pipeline got a layer that changed everything — the storyboard. A pencil storyboard shows the whole cut before I spend a second on video: I read it, catch a flat line or a lost character, and fix the script while it costs pennies. Inside — a four-stage evolution, my full prompts, and a bonus comparison of four models that draw the storyboard.