Agent classes / Browser agent / Managed browser-agent loop
Managed browser-agent loop for a browser agent
Updated 2026-10-27 (newest stored date on this page) · score asOf 2026-09-14 (stale)
The class: Completes a task by reading and operating a website in a browser, then stops before a consequential submit unless confirmation exists.
- Confirmation before submit, pay, or send
Depot Pick: Browser Use Cloud
When not to use it: You already have an agent framework and only need hosted Chromium.
Runner-up: Browserbase.
Cheapest matching sourced SKU (usd_per_browser_hour): Browser Use Cloud Browsers $0.02 — source, asOf 2026-10-03. All sourced prices
Failure modes this class and job share (11)
- Benchmark protocol mismatch: Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.
- Collateral side effects: Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
- Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
- GUI grounding miss: After each GUI action, compare the resulting screen or accessibility tree to the control the plan named. Stop when they differ.
- Hallucinated tool arguments: Reject a call that fails the current schema or names an unknown id, and do that before the tool runs a side effect.
- Instruction drift: Restate the stop condition in the trace. End the run when it is met. Review long traces for steps that do not serve the original task.
- Non-determinism: Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
- Over-refusal: Log refusals separately from successes. Review a sample against the written policy. Do not treat a refusal as a pass, and do not weaken a safety check to raise the pass rate.
- Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.
- Prompt injection: Compare each tool call to the original user task. If the call only makes sense given text that arrived from a fetched page, file, or message, stop and ask. Record which source the instruction came from. This catalog does not store payloads or attack steps.
- Tool loop: Hash the last several tool names and arguments. Stop when the same call repeats and the observation did not change. Cap tool calls per task.
Free options this class uses (0)
No free row lists this job with a kind this class needs.