{"slug": "how-forestrydiary-com-was-built-with-ai-prompts", "title": "How forestrydiary.com was built, with AI prompts", "summary": "Lance Orner, lead developer of the OCCA Database Sizing Project, built forestrydiary.com by feeding four prompts to Codex, turning 18 years of U.S. Forest Service ranger Reuben P. Box's pocket diaries from 1927 to 1945 into 7,488 pages covering 217 months and 4,656 days. Codex wrote Python to scan and crop each page into a local SQLite database, Mistral transcribed the 1930s handwriting and a later pass extracted 413 people, 70 places and 50 events, and Flask templates plus flask freeze generated about 8,000 static pages and 15,000 images (840 MB) served by nginx on one small OCI compute instance. The agent configured the server over SSH, and the fully static setup kept CPU load at 0.05 under peak loads of thousands of requests a minute.", "body_md": "forestrydiary.com\n\n# How this site was built\n\nWith AI prompts\n\n**Lance Orner** · OCCA Database Sizing Project, Lead Developer[occa.us.oracle.com](http://occa.us.oracle.com/)\n\nEighteen years of a Forest Service ranger’s pocket diaries, 1927 to 1945, and the four prompts that put them online.\n\n**217** months\n\n**4,656** days\n\n**7,488** pages\n\nStep one\n\n## Scan the paper\n\nPrompt to Codex\n\nCreate a Python program to capture an image from my document scanner, trim and crop, then add to a local sqlite database.\n\n- **Eighteen years** of monthly pocket diaries, one notebook per month, kept by\nRanger Reuben P. Box of the Lassen National Forest.\n- **Every page becomes a row** : a front and back image, trimmed to the page edge,\nkeyed by a catalogue number so it can always be traced back to its notebook.\n\nStep two\n\n## Teach a machine to read 1930s handwriting\n\nPrompt to Codex\n\nFor each entry in table, use Mistral to transcribe image and put results into new column in database\n\n- **Mistral reads each page** and types out the entry, including the\nhours table at the bottom of each day.\n- **A later pass pulls out the names** : 413 people, 70 places and 50 events,\nwith coordinates for the places.\n\nTranscription, January 28, 1931With Asst. Hufford we drive as far as we can go down. Walk over old road to Old S.C. and thence up Big Chico Ck. to Little Smoky and back up 9 mile Ck to Rd. and then to East.\nGot to camp at 9 P.M. We are looking out and possibilities and burn snags along roads.\nFire Prevention 10 hrs. Burn about 50 snags.\n\nStep three\n\n## Generate the pages\n\nPrompt to Codex\n\nCreate Python app using Flask that resizes all images to 800px width, and create People, Places, and Events pages from database entries that have been computed. Deploy using rsync to copy static pages to compute instance.\n\nDatabase\n\n*→*Flask templates*→*8,000 static pages*→*rsync*→*OCI compute\n- **One page per month, day, person, place and event** , rendered from the database.\nAbout 8,000 pages and 15,000 images, 840 MB in all.\n- **This renders as a set of static HTML/CSS pages** , which is very lightweight to serve,\nusing`flask freeze` to generate the files.`Hugo` also works, and does for my other sites.\n- **Nothing runs online but a file server.** A corrected transcription means a\none-minute rebuild and an rsync that carries only what changed.\n\nStep four\n\n## Stand up the server\n\nPrompt to Codex\n\nUse `ssh ociserver` to configure compute instance with nginx and log all traffic and referrals.\n\n- **One small OCI compute instance** running nginx, serving the static files with\nlong cache headers on the scans and a Let’s Encrypt certificate.\n- **Access logs with referrers** are what tell us who reads the diaries: search\nengines, genealogy forums, local history groups, and which bots to turn away.\n- **Static sites are easy to serve.** Peak loads of thousands of requests a minute\nonly push the CPU load to 0.05.\n- **The agent did the setup over SSH** : packages, vhost, certificate, log rotation.\nNothing was typed on the server by hand.", "url": "https://wpnews.pro/news/how-forestrydiary-com-was-built-with-ai-prompts", "canonical_source": "https://orner.com/talks/howtobuild/", "published_at": "2026-11-18 00:00:00+00:00", "updated_at": "2026-11-18 20:44:30.042578+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "generative-ai", "ai-agents"], "entities": ["Lance Orner", "Codex", "Mistral", "Flask", "nginx", "Oracle Cloud Infrastructure", "Reuben P. Box", "forestrydiary.com"], "also_reported_by": [], "takeaway": "Using Codex to generate a Python/SQLite scanning pipeline, Mistral for handwriting transcription, and flask freeze to emit roughly 8,000 static pages served by nginx on one OCI instance kept CPU load at 0.05 under peak traffic of thousands of requests a minute.", "recommendation": {"advice": "Pre-render database-driven content to static HTML with flask freeze and rsync only changed files to a single nginx instance; the source saw peak loads of thousands of requests a minute at 0.05 CPU load.", "playbook": "production-ops", "playbook_url": "https://wpnews.pro/playbooks/production-ops"}, "alternates": {"html": "https://wpnews.pro/news/how-forestrydiary-com-was-built-with-ai-prompts", "markdown": "https://wpnews.pro/news/how-forestrydiary-com-was-built-with-ai-prompts.md", "text": "https://wpnews.pro/news/how-forestrydiary-com-was-built-with-ai-prompts.txt", "jsonld": "https://wpnews.pro/news/how-forestrydiary-com-was-built-with-ai-prompts.jsonld"}}