{"slug": "i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report", "title": "⚚ I reverse-engineered my mobile operator's APK — then Hermes Agent wrote the executive report", "summary": "A developer in New Caledonia reverse-engineered the APK of OPT-NC's Helia mobile app, extracted its private HTTP calls, and built a Go CLI that snapshots voice, data, and SMS consumption every five minutes into a local DuckDB database. The developer then used Hermes Agent to generate a 17-page professional executive report—complete with brand-colored charts, a CEO-ready dashboard, and actionable network admin tickets—for a total cost of $19.57.", "body_md": "*This is a submission for the Hermes Agent Challenge: Write About Hermes Agent*\n\n// Detect dark theme var iframe = document.getElementById('tweet-2059698327235805258-252'); if (document.body.className.includes('dark-theme')) { iframe.src = \"https://platform.twitter.com/embed/Tweet.html?id=2059698327235805258&theme=dark\" }\n\nJust check how amazing these reports look like!\n\n\"Just generate a PDF\" — famous last words. What started as a simple request turned into something much bigger: a full monitoring stack for my mobile operator, built evenings and weekends, culminating in a 17-page professional report that would have taken a full week to build manually. Total cost with Hermes Agent: **$19.57**.\n\nI'm Adrien, a developer in New Caledonia. OPT-NC's Helia mobile service has an app — but no public API, no CLI, nothing on any marketplace. So I **reverse-engineered the APK**, extracted the private HTTP calls, and rebuilt them in a **Go CLI** that snapshots voice, data, and SMS consumption every 5 minutes into a local **DuckDB** database.\n\nThen I built **KDE Plasma widgets** in Python/PyQt that read from DuckDB and display live on my desktop — mirroring the official app's data, but with history, trends, burn rate, and alerts. Plus a **system tray icon** showing live API status at a glance.\n\nThe official app shows you *now*. My stack shows you *now, history, trends, and alerts.*\n\n**No other Helia customer has this.** That's the breakthrough.\n\nAll this data was sitting in DuckDB. The question was: *how do I present it to people who don't speak SQL?*\n\nThree completely different audiences: the **CEO** who needs a 30-second summary screenshot-ready for PowerPoint, the **CIO** who wants ROI in euros and SLA compliance, and the **Network Admin** who needs actionable tickets with specific hours and error patterns.\n\nBefore writing a single line of code, I asked Hermes Agent to do something unusual: **simulate a full team meeting** with 7 personas — CEO, CIO, network admin, developers, and marketing.\n\nIt produced a full transcript. Each persona argued their case:\n\nThat transcript became the design document. Every page of the report was written against a specific person's stated need. No guessing. No generic output.\n\n**It started with the data.** No assumptions — it queried the schema and immediately caught something: average latency was 2,534ms but the median was 204ms. Bimodal distribution. That single insight shaped every chart.\n\n**It extracted brand colors from the website** before writing a single line of LaTeX. Hermes Agent opened Helia's site, pulled the magenta/pink gradient from the SVG logo, and used it consistently across every chart, table, and tcolorbox. Small detail. Big difference.\n\n**Then it built everything:**\n\nOne message: *\"update with fresh data\"* — triggered 8+ tool calls automatically: DuckDB → diff → scripts → charts → LaTeX → 2× compile → verify.\n\nI asked for charts. I didn't ask for *this*:\n\n**Latency distribution** — median/mean/P95 lines labeled, shaded fast vs slow zones, annotated arrow pointing to the long tail: *\"Queue longue (timeout ~12s) (~40% des pings)\"*. Log-scale version revealing the true bimodal structure: two peaks at ~80ms and ~4s.\n\n**4-panel executive dashboard** — availability gauge (87.2% vs 99.5% SLA), latency (2534ms vs 500ms — *\"5.1x trop lent\"*), timeout rate (*\"1 requête sur 8 échoue\"*), composite SLA score per metric. **Score global: 65%. Verdict: RED.**\n\n**Timeout heatmap** — all 18 timeouts concentrated on Wednesday evening 19h–22h. The rest of the week: clean. Instant actionable insight for the network admin.\n\nAll in Helia brand colors. All annotated. None of it explicitly requested.\n\nPage 3 of the report is designed to be screenshotted directly into PowerPoint. Verdict box at the top (red), plain-language translation (*\"1 call in 8 fails\"*), business impact in euros, top 3 problems with responsible parties. The CEO gets it in 30 seconds.\n\n**Orchestration is the real superpower.** I asked for a PDF. It fetched brand colors, queried the DB, wrote Python scripts, compiled LaTeX — all unprompted.\n\n**Iteration is the default.** The first charts were basic. The final ones have annotated thresholds, color-coded data points, and statistical summaries. That's the loop.\n\n**Skills are the real ROI.** Everything got distilled into a reusable `~/.claude/skills/reporting-latex/`\n\nskill. Next similar project starts at 80%, not zero.\n\n** Qwen3.7-Max via OpenRouter.** Alibaba's flagship agentic model, built for long-horizon autonomous execution.\n\n**326 requests. 61.4M tokens. $19.57. ~1 hour. vs a full week manually.**\n\nThe next step: **run it all locally**. I'm currently eyeing an [Apple Mac Studio M4 Max](https://www.ldlc.com/fiche/PB00675416.html) — 16-core CPU, 40-core GPU, 64 Go unified memory. New Caledonia is 20,000km from everything; local inference just makes sense. Zero API costs, zero latency to the cloud, full control.\n\nWith 64GB unified memory, I'd be able to run:\n\nThe same class of model as Qwen3.7-Max on OpenRouter — locally, for free, forever. A fully local Hermes Agent stack.\n\n*From $19.57 on OpenRouter to owning the hardware. That's the roadmap. 🇳🇨*\n\nThe pattern: **monitor → query → visualize → compose → translate**. The *translate* step — turning a percentile into a story a CEO can act on — is where Hermes Agent earns its keep.\n\n*Have you used Hermes Agent for multi-tool orchestration? Curious how your experience compares.*", "url": "https://wpnews.pro/news/i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report", "canonical_source": "https://dev.to/adriens/i-reverse-engineered-my-mobile-operators-apk-then-hermes-agent-wrote-the-executive-report-2j3o", "published_at": "2026-05-28 23:01:45+00:00", "updated_at": "2026-05-28 23:42:13.474218+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-products"], "entities": ["Hermes Agent", "OPT-NC", "Helia", "Go", "DuckDB", "KDE Plasma", "Python", "PyQt"], "alternates": {"html": "https://wpnews.pro/news/i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report", "markdown": "https://wpnews.pro/news/i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report.md", "text": "https://wpnews.pro/news/i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report.txt", "jsonld": "https://wpnews.pro/news/i-reverse-engineered-my-mobile-operator-s-apk-then-hermes-agent-wrote-the-report.jsonld"}}