hackage.haskell.org with an AI agent
The short answer: hackage.haskell.org is the Haskell community's package archive. We gave Claude Code a real task there, each in a brand-new session. With Playwright MCP a task used 331K tokens on average. With Dejo it used 331K the first time and 79K on every run after, 76% fewer, because Dejo replays a learned task without the model reading the pages again.
The task
- “browse Hackage's packages by category, open the Chess Engine category, open the package listed there and tell me its author”
What each tool used
| task | Dejo, first run | Dejo, every run after | Playwright MCP | Playwright CLI |
|---|---|---|---|---|
| 1 | 331K tokens, 93 s | 79K tokens, 1 call, 15 s, right | 331K tokens, 6 calls, 35 s, right | 958K tokens, 14 calls, right |
Calls are browser tool calls the agent made. Right or wrong is checked against the answer read off the live site before any tool ran.
Learned and replayed with Dejo on 13 November 2026
We ran the task again with Dejo on 13 November 2026, so you can see what it saves today. These are the steps Dejo kept, exactly as it reported them. Each one carries a check that it landed, and a replay walks them in plain code.
1. go https://hackage.haskell.org/
2. click link "Packages by category" (by name)
3. click link "Chess Engine" (by name)
4. click link "turncoat" (by name)
5. answer (by position)Replay: 5 steps in 3.5 s, with no page reading. Answer: “Alberto Perez” (right).
How we measured
Claude Sonnet 5 at medium effort, a brand-new Claude Code session per task and tool, @playwright/mcp 0.0.80, October 2026. The full method, and the sites that blocked every tool, are on the benchmark page. Raw data: benchmark-real-2026-10-21.json, benchmark-real-2026-10-23.json, benchmark-real-2026-10-23-fixes.json, benchmark-site-memory-2026-11-10.json.
Other websites we measured
- scrapethissite.com: a sandbox site for practising web scraping, with tables, forms and paging
- packages.debian.org: Debian's package directory, searched by name and release
- rfc-editor.org: the official home of the RFC series of internet standards
- catalog.ccv.edu: the course catalog of the Community College of Vermont
- ctan.org: the Comprehensive TeX Archive Network, where LaTeX packages live
- practicesoftwaretesting.com: a demo tool shop built for practising test automation
- demowebshop.tricentis.com: Tricentis's demo web shop for test automation
- collection.internationalfolkart.org: the online collection of the Museum of International Folk Art in Santa Fe
- gutenberg.org: Project Gutenberg, a library of free ebooks
- pub.dev: the package site for Dart and Flutter
FAQ
How many tokens does an AI agent use on hackage.haskell.org?
In our test, Claude Code with Playwright MCP used 331K tokens per task on hackage.haskell.org on average. Dejo used 331K the first time and 79K on every run after, 76% fewer than Playwright MCP once the task was learned.
Can Claude Code automate hackage.haskell.org?
Yes. In fresh Claude Code sessions on one task there, Dejo answered 1 of 1 right, Playwright MCP 1 and Playwright CLI 1. With Dejo, a task done once is replayed later without the model reading the pages again.