Claude-Code on Daffa Abhipraya

PPL: AI at Different Cognitive Distances [Sprint 2, Week 3]

Wed, 15 Apr 2026 00:00:00 +0700

What I Worked On

Two weeks where AI was the primary productivity multiplier across very different task shapes. Week 1 leaned on iterative CI debugging (ten MRs of “run pipeline, read failure, ask AI, apply fix”) and integration-test infrastructure design. Week 2 leaned on bulk test generation (400+ mutation-killing assertions), bash-with-tricky-primitives design (a flock-based slot allocator), and cross-agent documentation research. The common thread across all six patterns: AI is best when the task is a known pattern applied to new context, and weakest when the task is about how primitives interact in a specific environment.

PPL: AI Literacy [Sprint 2, Week 2]

Mon, 30 Mar 2026 00:00:00 +0700

What I Worked On

With 19 MRs landing this week across CI scripting, application features, and infra fixes, AI assistance was involved throughout. The most interesting usage this week was not code generation but rather iterative verification: describe what the output should look like, generate, run against real CI output, observe differences, fix, repeat.

AI for Complex Bash Scripting

The CI report scripts (scripts/ci-report.sh) grew from 0 to 356 lines in MR !126 alone, and another 111 lines across !129, !132, and !140. Writing bash that parses CI job output, formats it as GitLab-flavored markdown, and posts it via the GitLab API is exactly the kind of code that AI handles well — repetitive structure, lots of string manipulation, easy to verify.

PPL: AI-Assisted Sprint Planning [Sprint 2, Week 1]

Mon, 23 Mar 2026 00:00:00 +0700

What I Worked On

This week I used Claude Code (Anthropic’s CLI agent) as my primary development partner for Sprint 2 planning, feature brainstorming, code implementation, and CI debugging. The session produced 20 PBIs, 64 subtasks, 3 service file changes, and a merged MR, all in one sitting.

AI for Sprint Planning

Feature Gap Analysis

I asked Claude to explore the entire codebase (frontend + backend + infra) and catalog what’s implemented vs missing. It launched parallel exploration agents that traced through routes, services, workers, and the database schema, producing a comprehensive feature inventory.

How I Actually Use Claude Code

Fri, 13 Mar 2026 00:00:00 +0700

People keep asking me how I work with Claude Code. Friends, classmates, engineers I meet - the question always comes up: “Can you walk me through your dev workflow with it?”

I use Claude Code for pretty much everything: personal projects, internship work at a startup, managing my VPS, even continuing sessions from my phone with Remote Control. If you’re already using something like GitHub Copilot or Cursor and wondering what a CLI-first AI workflow looks like when you go deeper, this is for you.

PPL: AI Literacy [Sprint 1, Week 3]

Fri, 13 Mar 2026 00:00:00 +0700

What I Worked On

This week tested whether the AI development infrastructure built in Sprint 1 Weeks 1-2 actually pays off under heavy workload. With 14 MRs and 10 code reviews in one week, every tool in the AI stack was used extensively. I also updated the CLAUDE.md documentation based on new patterns discovered during development.

CLAUDE.md as Living Documentation

The project’s AI instruction document (CLAUDE.md) was updated this week to reflect new patterns encountered during development. Commit 80b127b added fullName to the documented auth context values in apps/web/CLAUDE.md:

PPL: AI-Augmented Development with Claude Code [Sprint 1, Week 2]

Thu, 05 Mar 2026 00:00:00 +0700

Overview

The SIRA project has a comprehensive AI development setup built around Claude Code. Rather than using AI as a one-off assistant, the project treats AI tooling as infrastructure - versioned, tested, and evolved alongside the codebase.

graph TB
 subgraph claude [Claude Code]
 CM["CLAUDE.md
3 files, 19 commits"]
 MCP["MCP Servers
4 integrations"]
 CMD["Commands
3 slash commands"]
 SK["Skills
3 project skills"]
 PL["Plugins
3 enabled"]
 end

 subgraph ext [External Services]
 LN[Linear]
 SB[Supabase]
 SQ[SonarQube]
 GL[GitLab]
 end

 MCP --> LN
 MCP --> SB
 MCP --> SQ
 CMD --> GL

Component	Count	What
CLAUDE.md files	3	Root + `apps/web/` + `apps/api/`
AGENTS.md symlinks	3	Multi-tool compatibility (Cursor, Copilot, Codex)
MCP servers	4	Linear, Supabase, Context7, SonarQube
Slash commands	3	`/commit`, `/commit-and-push`, `/create-pr`
Project skills	3	frontend-design, vercel-react-best-practices, web-design-guidelines
Plugins	3	GitLab, PR review toolkit, CLAUDE.md management

CLAUDE.md - Three Files, 19 Commits

CLAUDE.md is the AI instruction document for the SIRA project. It was not written once and left static. It evolved through 19 commits, each one a direct response to a real friction point encountered during development.

Claude-Code on Daffa Abhipraya

PPL: AI at Different Cognitive Distances [Sprint 2, Week 3]

# What I Worked On

PPL: AI Literacy [Sprint 2, Week 2]

# What I Worked On

# AI for Complex Bash Scripting

PPL: AI-Assisted Sprint Planning [Sprint 2, Week 1]

# What I Worked On

# AI for Sprint Planning

# Feature Gap Analysis

How I Actually Use Claude Code

PPL: AI Literacy [Sprint 1, Week 3]

# What I Worked On

# CLAUDE.md as Living Documentation

PPL: AI-Augmented Development with Claude Code [Sprint 1, Week 2]

# Overview

# CLAUDE.md - Three Files, 19 Commits

What I Worked On

What I Worked On

AI for Complex Bash Scripting

What I Worked On

AI for Sprint Planning

Feature Gap Analysis

What I Worked On

CLAUDE.md as Living Documentation

Overview

CLAUDE.md - Three Files, 19 Commits