AnyDoc Architecture Review: Inside Firecrawl's Rust Document-to-Markdown Stack
A technical look at Firecrawl's AnyDoc and pdf-inspector, two open-source Rust libraries designed to turn heterogeneous documents into struc...
Aug 31, 2026
10 min
Pradeep Kumar
![First Post](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gFirst" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%238b5cf6" /><stop offset="100%" stop-color="%23ec4899" /></linearGradient><filter id="fFirst"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gFirst)" filter="url(%23fFirst)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.4)" stroke-width="2"/><path d="M60 30 C 50 30, 40 40, 35 55 L 30 70 L 45 65 C 60 60, 70 50, 70 40 C 70 35, 65 30, 60 30 Z" fill="%23ffffff" opacity="0.9"/><path d="M35 55 L 45 65" stroke="%23ec4899" stroke-width="2"/><circle cx="65" cy="25" r="3" fill="%23fef08a"/><path d="M65 15 L65 20 M65 30 L65 35 M55 25 L60 25 M70 25 L75 25" stroke="%23fef08a" stroke-width="2" stroke-linecap="round"/></svg>)
![Word Warrior](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gWord" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%23b91c1c" /><stop offset="100%" stop-color="%23f87171" /></linearGradient><filter id="fWord"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gWord)" filter="url(%23fWord)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.4)" stroke-width="2"/><path d="M25 60 L75 60 L70 75 L30 75 Z" fill="%23ffffff" opacity="0.9"/><path d="M50 20 L55 30 L55 70 L45 70 L45 30 Z" fill="%23ffffff" filter="url(%23fWord)"/><rect x="35" y="65" width="30" height="5" fill="%23b91c1c"/><rect x="45" y="70" width="10" height="15" fill="%237f1d1d"/></svg>)
![Weekend Warrior](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gWknd" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%231d4ed8" /><stop offset="100%" stop-color="%2360a5fa" /></linearGradient><filter id="fWknd"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gWknd)" filter="url(%23fWknd)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.4)" stroke-width="2"/><path d="M30 30 C 50 20, 50 20, 70 30 L 70 50 C 70 70, 50 80, 50 80 C 50 80, 30 70, 30 50 Z" fill="%23ffffff" opacity="0.9" filter="url(%23fWknd)"/><rect x="40" y="45" width="20" height="20" rx="2" fill="%231d4ed8"/><rect x="40" y="45" width="20" height="5" fill="%23bfdbfe"/><line x1="45" y1="42" x2="45" y2="48" stroke="%231e3a8a" stroke-width="2"/><line x1="55" y1="42" x2="55" y2="48" stroke="%231e3a8a" stroke-width="2"/></svg>)
![Night Owl](data:image/svg+xml;utf8,<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100"><defs><linearGradient id="gNight" x1="0%" y1="0%" x2="100%" y2="100%"><stop offset="0%" stop-color="%23312e81" /><stop offset="100%" stop-color="%23818cf8" /></linearGradient><filter id="fNight"><feDropShadow dx="0" dy="2" stdDeviation="3" flood-opacity="0.3"/></filter></defs><circle cx="50" cy="50" r="45" fill="url(%23gNight)" filter="url(%23fNight)"/><circle cx="50" cy="50" r="38" fill="none" stroke="rgba(255,255,255,0.2)" stroke-width="2"/><circle cx="65" cy="35" r="15" fill="%23fef08a" opacity="0.9"/><path d="M30 70 C 30 40, 70 40, 70 70 Z" fill="%23ffffff"/><circle cx="42" cy="55" r="5" fill="%23312e81"/><circle cx="58" cy="55" r="5" fill="%23312e81"/><polygon points="48,62 52,62 50,68" fill="%23fbbf24"/></svg>)
Joined Jun 2026
0Followers
5Week Streak
Subscribe to Pradeep Kumar's Newsletter
Get new engineering posts delivered straight to your inbox.
How an AI-Driven Copyright Takedown Got Luanti Pulled From Google Play, Again
Microsoft, acting through AI-driven brand protection vendor Tracer.AI, filed a DMCA notice that temporarily pulled Luanti from Google Play f...
Aug 29, 2026
6 min
Qwen3.8-Flash-Next: Inside Alibaba's Preview of the Qwen4 Architecture
Alibaba open-weighted a working preview of Qwen4's architecture: 125B parameters, only 6B active per token. It beats prior open Qwen models ...
Aug 27, 2026
6 min
Apple M6 and M5 Ultra: The Mac Is Becoming a Serious AI Workstation
Apple’s new M6 and M5 Ultra chips signal a major shift in Mac computing. From the 2nm M6 to the 512GB unified-memory M5 Ultra, Apple is buil...
Aug 26, 2026
7 min
How Git Actually Works: A Look Inside the .git Folder
Git isn't a diff tool with commands bolted on — it's a content-addressable database. This post walks through blobs, trees, and commits, veri...
Aug 25, 2026
5 min
Scraping LinkedIn with Python in 2026: Profiles, Companies, and Jobs
Practical Python code for scraping LinkedIn profiles, company pages, and jobs in 2026 — using curl_cffi for JA3 impersonation, the hidden jo...
Aug 24, 2026
9 min
The Best Open Source LLMs in August 2026: A Developer's Honest Guide
Open-weight models now match closed frontiers on independent benchmarks. The question is no longer 'are open-weight models good enough?' It'...
Aug 22, 2026
11 min
Caching Strategies Every Backend Developer Must Know
A practical, code-first guide to cache-aside, read-through, write-through, write-behind, and refresh-ahead patterns — with Redis examples, e...
Aug 19, 2026
12 min
Inside Claude's Brain: What Anthropic's Published System Prompts Reveal About the Future of AI Transparency
The Page That Changed Everything In August 2024, a quiet page appeared on Anthropic's documentation site. No press release. No keynote. Just...
Aug 17, 2026
11 min
Google Launches Gemini 3.7 Flash Three Weeks After 3.6 With 50% Introductory Pricing
Google DeepMind released Gemini 3.7 Flash on August 13, 2026. The model builds on Gemini 3.6 Flash with algorithmic improvements aimed at so...
Aug 15, 2026
8 min
The Rise of AI Trading Among Retail Investors
Robinhood just let customers connect Claude and ChatGPT straight to a trading account. Zerodha, Alpaca, and a wave of no-code platforms have...
Aug 4, 2026
5 min
AI Doesn't Ship Software. You Still Do.
AI can scaffold a working app in minutes. It can't tell you why the login breaks under two users, why a webhook fires twice, or why a query ...
Aug 1, 2026
4 min
How to Hide Your Backend VPS IP Behind Vercel Using Next.js Rewrites
Learn how to leverage Vercel's Edge network and Next.js Rewrites to route traffic securely to your VPS, effectively hiding its IP address fr...
Jul 30, 2026
3 min
Chinese Open-Weight Models Just Won OpenRouter's Token War. They Still Haven't Won the Dollar War.
Chinese open-weight models like DeepSeek, GLM, Kimi, and Qwen now account for 30-46% of US company traffic on OpenRouter, and up to 61% in n...
Jul 8, 2026
12 min