Turning some long-shelved ideas into systems that actually run.

This is a record of how I've been working with AI lately: some of it is websites, some knowledge systems, some data wrangling and automation. They aren't necessarily complete, but each has gone from an idea to something usable and maintainable.
Paul Kuo（paulkuo.tw）
Tool Which AI model is strongest, and best value, right now? A weekly-refreshed frontier snapshot: general intelligence, coding, long-horizon agentic, and the price-performance frontier, all on one page. See the model frontier →

Projects I've worked on

A few examples that are live or were once running.
paulkuo.tw multilingual content site
My content site, with versions in several languages, tying together caching, the Dedao brain API, a Worker API, dynamic share images, and login. It mainly hosts articles, knowledge notes, and project records.
paulkuo.tw ↗
LLM Wiki personal knowledge system
Turning notes and material from different sources into a knowledge system you can search, ask, and visualize. The point isn't to show off a graph, but to let the material be re-linked, found, and extended.
paulkuo.tw/wiki ↗
Baishatun Mazu ESG pilgrimage record platform
An activity-record platform set around the Baishatun pilgrimage, combining multilingual content, LINE check-ins, route data, and carbon- and kindness-footprint records. The project wrapped up in 2026; the site stays online as a record of the experiment.
mazu.today ↗

Decision records

One decision left behind during the work.
Avoiding dependence on a single git host
ContextThe main git-host account was once suspended, which made me realize that if version history, deploys, and issue records all depend on one platform, that's a single point of risk.
ConsiderationsAt the time I weighed three options: keep using one platform, move everything to another, or set up several mirrors so different platforms back each other up.
ApproachI chose to set up mirrors across platforms. If any one platform has a problem, the others still keep the version history and the ability to update; deploys moved to wrangler, not tied to any specific git host.
ResultAfter the account was restored, I brought it back as a third mirror. Since then, no single git host is the only dependency, and issues are just one part of the work record rather than the whole truth.

AI collaboration — raw records

Some of the raw records behind the projects and workflow above. Last updated: 2026-07-15 10:31 Records since 2026-02-10 · 120-day commit streak

Overview

Sources include git history and Claude Code usage records
Commits
3,721
Deploys
382+
plus 14 PR merges
Code & content changes
+784K / −172K
lines (added / deleted)
Days with records
120 / 120
days · every day in range
Consecutive days
120d
Unbroken so far
AI sessions & messages (last 30 days)
256 sessions
82,301 messages
Token usage (last 30 days)
260.6M
Peak collaboration hour
23:00
claude-opus-4-8
Codebase Growth 612K lines · from zero
0K 100K 200K 300K 400K 500K 600K 0304050607
Commit calendar Less More Platform activity
Sep 2025OctNovDecJan 2026FebMarAprMayJunJul
There's a commit on record for every day in this stretch.

Workflow records

Cross-window AI agent collaboration, organized into records that can continue, hand off, and be tracked
Worklogs: work journal (total)
117
Handoffs: cross-session briefs (total)
173
Governance docs (incl. ADRs · total)
149
39 of which are ADR decision records

Verifiable Quality Signals

Raw evidence layer; not-yet-accumulated is shown as “not measured”, never 0
Test coverage (Python / Node)
81 / 64.4%
Deploy smoke-test compliance
87%
Cross-project impact-tag compliance
100%
Contract-test SLA adherence
91%
Reverts / rollbacks
21
Test files
14
Change failure rate
8%
Incidents / MTTR
3

Delivery Signals (DORA, directional)

Solo personal site, manual deploy: directional only, no Elite badge
Deploy frequency
3.18
daily~on-demand
Change failure rate
not measured
Incident recovery (MTTR)
not measured
Change lead time
not measured

DORA is a team software-delivery scale; solo direct-to-main inflates frequency/lead-time semantics, and tiering needs all four metrics together. Treated here as a directional reference only: no tier, no personal badge.

Five-Dimension Capability Evidence

Qualitative read + evidence level; no composite score, no grading
Command | steering the AI collaboration system (direction / governance / orchestration) Artifact-evidenced
Ample governance / orchestration artifacts; command quality is self-reported.
Delivery | speed and stability of shipping Partial
Strong deploy-frequency signal; CFR / MTTR / lead-time not yet accumulated.
Leverage | amplifying output with AI Artifact-evidenced
High output + high AI usage; a multiplier would need a no-AI same-person baseline, which is unmeasurable.
Quality | reliability of output Auto-fetched
The hardest dimension, but mostly process signals (high coverage != good tests).
Influence | outward reach Self-reported
No external-reach signal; left honestly blank.

Data observations

Consistency

An unbroken 120-day commit trail (weekends and holidays included), overlaid with the time distribution of 256 Claude Code sessions; cross-checked against two independent sources — the git mainline and the session records.

Collaboration records

AI conversations break easily, so I keep handoffs, ADRs, and work journals on the side. These records let separate sessions pick up where the last one left off, and let a later me see why something was done the way it was.

Data limits

This only covers Claude Code records; usage from other AI tools isn't included. Deploy counts and lines of code are rough references too, and don't fully represent all the work.

How the data is compiled

  • Sources include the git mainline records and raw Claude Code session records.
  • Commit counts come from a single git mainline. GitHub, GitLab, and Codeberg are mirrors of the same history and aren't counted twice.
  • Scheduled auto-commits are excluded; active days are deduplicated by commit date (UTC+8).
  • AI session figures are recomputed from local Claude Code raw records and have been cross-checked against the official usage panel.
  • Claude Code only keeps session records for a recent window, so sessions from 2026-02-10 to 2026-05-05 aren't included.
  • Repo platform activity is traceable from 2026-02-20 via PR and issue records; because the git mainline history was reset in mid-March, commit details before 3/18 aren't included in the current counts.
  • This page makes no scores or estimates; it only shows data that can be checked against the raw records.
  • "Governance and decision docs" refers to the Markdown files under docs/governance/. ADRs are part of that, already included in the total, not counted separately.