Focus area
Browser infrastructure and automation
Doccraft measures when a headless browser is the right choice, how lighter browser engines compare with Chrome, what browser tools cost an agent in tokens, and how teams run browsers at scale. It writes for the companies that build cloud browsers and browser infrastructure for AI agents.
Research and guides
- Best headless browser for AI agents: Chrome, Lightpanda and Obscura tested on 50 real pages
I ran Chrome 156, Lightpanda 1.0.2 and Obscura 0.2.5 through agent-browser on 50 real pages, twice. Lightpanda matched Chrome's text on 33 of 41 pages with a median of 120 MB against Chrome's 1,636 MB. Obscura matched 26 and returned an empty page on 11. On 10 agent tasks, Claude got all 20 answers right on every engine.
- Chrome DevTools MCP's --no-javascript-evaluation flag, tested: 39% more input tokens, 18 of 20 answers right
Chrome DevTools MCP has a --no-javascript-evaluation flag that removes the agent's evaluate_script tool. I ran Claude on 10 real tasks with and without it, twice. With the flag, it got 18 of 20 right, compared with 20 of 20 without it. It also used 39% more input tokens and cost 2.3 times as much.
- Playwright MCP vs Chrome DevTools MCP vs agent-browser: same accuracy, but tokens per task ranged from 4.1K to 95K
I ran the same Claude agent on 19 real browser tasks, twice, through Playwright MCP, Chrome DevTools MCP and 5 agent-browser setups. All 7 got every answer right. The median task read 31K tokens with Playwright MCP, 46K with Chrome DevTools MCP, and 4.1K to 95K with agent-browser, depending on how it was loaded. In dollars, the typical task cost under 4 cents in every setup.
- Browser Use found the right price on 29 of 34 stores, and duplicate product names caused most misses
I gave the Browser Use agent a store homepage and a product name on 34 real stores, twice. It returned the right product and price for 29 and 28. Most misses were other listings with the same name. Each product took about a minute and about a cent.
- Lightpanda 1.0 built 21 of 28 real JavaScript sites, but only with the right wait setting
I tested Lightpanda 1.0.1 and headless Chromium on 28 real sites that need JavaScript, twice. One wait setting changed the result from 12 sites to 21. Lightpanda was about 2 times faster than Chromium and used about 3 times less memory.
- Do you need a browser for web scraping? A 1,000-site test
I tested the top 1,000 websites with a plain HTTP request and a headless browser. 5% needed JavaScript, and on 14% the browser loaded pages that blocked the plain request.
- Scraping JavaScript pages without a full browser, retested
ScrapingBee's OxyCon 2026 talk says jsdom runs a page's JavaScript with less than half a browser's memory. The saving held, but on 29 real JavaScript sites, the full browser built far more pages.
- MCP's context problem, measured: tool definitions vs tool results
Apify's CEO argued at Prague Crawl 2026 that MCP isn't the problem, the agents are. I measured 6 MCP servers. 95 tool definitions took 15,950 tokens, and one page snapshot took 31,565.
Published for clients
- Cloudflare Browser Rendering: Benchmark, Limits & Cloud Alternatives (opens in a new tab)gologin.com
- Lightpanda vs Playwright and Headless Chrome: When a Lightweight Browser Is Enough (opens in a new tab)brightdata.com
- Bots Block Bots: Why Anti-Bot Systems Flag LLM Browsers (opens in a new tab)scrapingbee.com
- Running Amazon Nova Act agents in production with Bright Data (opens in a new tab)brightdata.com
- Kernel.sh Review 2026: Speed, Concurrency and Real Pricing (opens in a new tab)gologin.com
- Playwright & Puppeteer on AWS Lambda: Serverless Scraping Guide (opens in a new tab)scrapingbee.com
- Browser as a Service (BaaS): Architecture, Use Cases & 2026 Guide (opens in a new tab)gologin.com
Working with Satyam has been a great experience. He brings a deep engineering mindset to technical writing, whether he is analyzing Browser as a Service (BaaS) infrastructure, Cloudflare Browser Rendering, or complex website automation and fingerprinting. His hands-on benchmarks and ability to explain complex technical concepts make his work stand out. Highly recommended!