Job 06 · Not yet tested
Which AI can use a website for me?
Agents that drive a browser. Three fixed tasks on public pages that do not need a personal account.
People who want an agent to click through a site, not only fetch a URL.
The standard test
Pack 0.1.0 · specified · Three public tasks
3 fixed tasks on stable public sites
Setup
Three tasks written in advance: one navigation, one extraction, and one multi-step flow. Pages are public and do not require a personal login. We name the pages in the pack when the first run is scheduled, and we do not swap a page because a tool struggled.
Inputs
The three task briefs. No saved passwords and no customer accounts.
Time limit
One wall-clock cap for every tool in the job. The number is published with the pack before the first run and does not move between tools.
What we record
- Tasks completed
- Human takeovers
- Time
- Cost
- Tool version
- Plan
How the FitScore is built
FitScore = weighted average × 20, rounded to the nearest integer. The weighted average is the sum of (criterion score × weight) divided by 100.
- Output quality30
- Reliability15
- Cost and free tier15
- Speed10
- Setup friction10
- Agent, API, and MCP support10
- Privacy and data10
5 excellent · 4 good · 3 usable · 2 poor · 1 fails. Full method.
Candidates
Candidates for Browser agents. This order is the launch list, not a ranking. No FitScores are published.
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Questions this page answers
- Which AI can use a website for me?
- FitForTool has not published a FitScore for this job. The launch candidates are ChatGPT agent, Browser Use, Perplexity Comet, Browserbase Stagehand, Skyvern, and Claude for Chrome. Each one is listed as not yet tested. A ranking is published only after every tool in the comparison has had the same test pack run, and a person has reviewed the result. Until that page shows a FitScore, there is no winner.
- How will FitForTool test browser agents?
- 3 fixed tasks on stable public sites. Three tasks written in advance: one navigation, one extraction, and one multi-step flow. Pages are public and do not require a personal login. We name the pages in the pack when the first run is scheduled, and we do not swap a page because a tool struggled. We record tasks completed, human takeovers, time, cost, tool version, and plan. Those notes are then scored from 1 to 5 on seven shared criteria. The pack has been specified and has not been run.
- Can a vendor pay to rank higher on this job?
- No. FitForTool does not sell position or score. A sponsorship, if we run one later, is labelled and sits outside the ranked list. An affiliate link is disclosed and does not change order. A vendor may ask for a retest, and we rerun the same pack. Sponsors do not see the result before it is public.
- What does "Not yet tested" mean?
- The tool is a candidate for this job. There is no published hands-on run, so there is no FitScore, no criterion score, and no rank. Research-only is a different label, used when we have read the docs and still have not run the pack. Neither label is a score.