convez.ai
AgenteProdutividadeAvançado
bricevideau-ai

ALCF AI Agent Coding Talk

bricevideau-ai/alcf-ai-agent-coding-talk

Estudo de caso: 17 sessões, 2.650 prompts, 2 projetos, métricas reais

Ver no GitHub
InicialPluginScore · de 0 a 100

Retrospectiva de 15 semanas usando Claude Code em dois projetos reais de engenharia de performance (CCS e rust-gpu + claspr). Inclui deck de apresentação, métricas de sessão, análise de custos e ferramentas de reprodução. Recurso educacional completo documentando a experiência prática de codificação com agents de IA.

Instalação

$npx convez-ai bricevideau-ai/alcf-ai-agent-coding-talk

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Estudar padrões reais de uso de Claude Code em projetos grandes
  • Analisar custo-benefício de agentes IA para engenharia de performance
  • Entender fluxo de trabalho colaborativo entre múltiplos agentes

Veredito

Documentação técnica honesta e reproduzível de uso real de Claude Code. Mais valioso como estudo de caso para engenheiros sênior do que como ferramenta reutilizável — excelente para quem quer entender dinâmica prática de agentes IA em projetos complexos.

README

A tradução para o português deste README ainda está na fila.

From Directing to Dialogue

Fifteen Weeks of AI Agent Coding for Performance Engineering — a first-person retrospective from two ALCF-adjacent projects (CCS and rust-gpu + claspr).

Source materials for an ALCF talk evaluating my use of Claude Code on two real projects, one I owned and one I didn't.

Contents

FileWhat it is
ai-agent-coding-alcf.pptxThe deck (38 slides, ALCF template, ~30–35 min)
ai-agent-coding-alcf.pdfPDF render for quick viewing
build_deck.pypython-pptx generator — re-run to rebuild from edits
deck_outline.mdSlide-by-slide outline plus the numbers used
session_stats.jsonMined metrics from the surviving session JSONLs across both laptops
ccusage/ccusage@latest cost snapshots from both laptops + a README explaining the merge protocol
CLAUDE.mdOrientation for the next Claude agent picking up the deck
ALCF Presentation Template.pptxThe ALCF template — committed so the build is self-contained

Rebuild

pip install python-pptx
python3 build_deck.py
# Optional: render to PDF for QA
soffice --headless --convert-to pdf ai-agent-coding-alcf.pptx

No external paths: build_deck.py resolves the template relative to its own location.

Scope and provenance

  • Two projects covered:
    • CCS (argonne-lcf/CCS) — C99 autotuning configuration-space library; I wrote and maintain it. 4 sessions, ~600 user prompts, 96 PRs merged in 6 weeks.
    • rust-gpu + claspr — OpenCL Kernel execution model added to Rust-GPU/rust-gpu (PR #3 on the fork, +24,540 / −595 across 761 files) plus the new claspr single-source OpenCL host layer (~81K LOC). 13 sessions, ~2,059 user prompts.
  • 17 sessions total across both laptops, ~2,650 user prompts over 15 weeks (Feb 25 → Jun 8, 2026).
  • Token/cost metrics live in session_stats.json and ccusage/. Only 5 of the 17 session JSONLs survived Claude Code's 30-day eviction by the time mining was run (a910ecaa, 11e6e374 on the Arm Mac; 4862cd6d, 61dc0523, afa1ce4c on the native-Intel-Ubuntu laptop) — those are direct measurements; the other 12 sessions' prompts survive via history.jsonl but their per-call tokens are gone. Slide 30 in the deck projects the full-project bill from the 5-session sample.
  • The deck is built from the official ALCF PowerPoint template, which is committed to this repo so the build is self-contained.

Authoring notes

The talk itself was prepared with Claude Code (Opus 4.7) — first authored on the Arm Mac laptop (Ubuntu environment on macOS host), then reviewed and enriched on the native-Intel-Ubuntu laptop, with two agents collaborating via the GitHub repo. Mildly on-the-nose given the subject matter. The build script, outline, session-mining, and ccusage snapshots all sit in this repo so the whole thing is reproducible end-to-end.

Ver o original no GitHub

Bom para

Relacionados