// QA & monitoring
Monitor SaaS pricing pages
Normalize the plans from four SaaS pricing pages into one comparable table, ready to run on a schedule.
10 agent tool calls, click to jump
Why it’s hard
Pricing pages are marketing pages: toggles, footnotes and plans that are priced per seat, per project or not at all.
- Some pages default to annual billing behind a toggle
- Plans are priced per user, per month, or 'Contact us'
- A monitor re-runs daily, so cost per run matters
Stagehand vs. Playwright MCP
Given the same goal and model, the Stagehand code-mode agent finished for 39% less than an agent driving Playwright MCP.
- stagehand code mode agent3/3 runs succeeded
- $0.338
- playwright mcp agent3/3 runs succeeded
- $0.551
medians over successful runs, or over all runs when none succeeded; lower is better
Then run it as a script
Once the flow works, the cookbook runs it as plain Stagehand calls. With caching on, a re-run cost 17% less, because Stagehand served unchanged steps from its cache.
- cookbook, first run3/3 runs succeeded
- $0.364
- cookbook, cached re-run3/3 runs succeeded
- $0.301
medians over successful runs, or over all runs when none succeeded; lower is better
anthropic/claude-sonnet-5 at $2 input · $0.2 cached · $2.5 cache write · $10 output per 1m tokens · stagehand 4.1.0 · playwright mcp 0.0.82 · agents stop after 60 llm calls · run on 2026-09-27 · methodology
Run it yourself
Give the same goal to Claude Code with Stagehand’s code-mode MCP server, which exposes three tools: run, snapshot and screenshot. Once the flow works, the cookbook runs it as a plain Stagehand script.
Visit the pricing pages of Linear (https://linear.app/pricing), Supabase (https://supabase.com/pricing), Vercel (https://vercel.com/pricing) and Render (https://render.com/pricing). Switch to monthly billing where there is a toggle. For each vendor list every plan with its name, monthly price in USD when billed monthly (null for custom pricing) and what the price is per.