Claude Opus 5.5 on Test AI browser agents on real workday tasks

AClaude Opus 5.5 · Claude Code 2.1.299 (headless -p) · cloud · 2026-10-14 · by @bobsiopener

Trust 80%Fully autonomoussuccess · first tryCompare

Estimated cost: $0.10
Wall time: 15s
Human step-ins: 0
Outcome: Pass

Compare with other models on this task →

Exact prompt

You are a workday assistant on a mock calendar (no real accounts). Complete requests.md by editing calendar.json.

Task prompt given to the agent (headless, offline, synthetic fixture inputs): You are a workday assistant on a mock calendar (no real accounts). Complete requests.md by editing calendar.json. Inspired by https://agentusecases.ai (listing: 'Test AI browser agents on real workday tasks', natesnewsletter.substack.com) (unverified; not checked with the author). This is an independent re-run on a reproducible synthetic task; it does not report or reproduce the original post's numbers. Cost shown is a list-price API-equivalent estimate (run on a Claude Pro subscription, not billed).

Success criteria: All automated rubric checks pass: Q4 planning 2026-10-21 12:00-13:00; 1:1 2026-10-21 14:00-14:30; exactly 2 events; busy lists updated; SUMMARY.md written.

Setup notes: Cost is an ESTIMATE: Claude Code's list-price API-equivalent figure. The run used a Claude Pro subscription, so nothing was billed. input_tokens = all input incl. cache-creation and cache-read tokens; cached_tokens = cache reads (subset of input). Claude Code's cost bills cache writes at the 1h cache-write premium, so it can differ from a flat input-price recompute. Web disabled; tools Read/Write/Edit/Glob/Grep/Bash; single run; scored automatically (5/5 checks).

Estimated cost List-price estimate; not actually billed.

Metrics

Estimated cost: $0.10
Wall time: 15s
Human step-ins: 0
Turns: 3

Model usage
Model	Input tok	Output tok	Cost
AClaude Opus 5.5anthropic/claude-opus-5.5	55,286	1,452	$0.10

Reproduce this run

Use the use case prompt on the use case page.
Same setup: Claude Opus 5.5 (anthropic/claude-opus-5.5) via Claude Code 2.1.299 (headless -p), cloud.
It counts as a success only if it meets every success criterion: All automated rubric checks pass: Q4 planning 2026-10-21 12:00-13:00; 1:1 2026-10-21 14:00-14:30; exactly 2 events; busy lists updated; SUMMARY.md written.
Log model, tokens, wall time, human step-ins and the evidence log, then submit it as a reproduction. A different model? Submit a head-to-head rerun.

How runs are scored: Methodology.

Was this useful?

⇄ Rerun on another model

Automated checks

Trust 80% comes from these checks (how Trust % works).

Run date is not in the future : passed
Model is in the dated pricing table : passed
Cost recomputed from tokens matches : passed
Cached tokens are consistent : passed
Output throughput is plausible : passed
Autonomy matches step-ins : passed
Step-ins do not exceed turns : passed
Retries agree with first-try result : passed
Evidence log SHA-256 matches : passed
Evidence log is substantial : passed

Evidence log

{
 "duration_api_ms": 13475,
 "stop_reason": "end_turn",
 "session_id": "[REDACTED]",
 "total_cost_usd": 0.0971926,
 "usage": {
  "input_tokens": 6,
  "cache_creation_input_tokens": 7317,
  "cache_read_input_tokens": 47963,
  "output_tokens": 1452,
  "output_tokens_details": {
   "thinking_tokens": 298
  },
  "server_tool_use": {
   "web_search_requests": 0,
   "web_fetch_requests": 0
  },
  "service_tier": "standard",
  "cache_creation": {
   "ephemeral_1h_input_tokens": 7317,
   "ephemeral_5m_input_tokens": 0
  },
  "inference_geo": "global",
  "iterations": [
   {
    "input_tokens": 2,
    "output_tokens": 380,
    "cache_read_input_tokens": 18347,
    "cache_creation_input_tokens": 1116,
    "cache_creation": {
     "ephemeral_5m_input_tokens": 0,
     "ephemeral_1h_input_tokens": 1116
    },
    "type": "message"
   }
  ],
  "speed": "standard",
  "fallback_credit": null
 },
 "modelUsage": {
  "claude-opus-5-5": {
   "inputTokens": 6,
   "outputTokens": 1452,
   "cacheReadInputTokens": 47963,
   "cacheCreationInputTokens": 7317,
   "webSearchRequests": 0,
   "costUSD": 0.0971926,
   "contextWindow": 1000000,
   "maxOutputTokens": 128000,
   "thinkingTokens": 298,
   "canonicalModel": "claude-opus-5-5",
   "provider": "firstParty",
   "costBasis": "list"
  }
 },
 "permission_denials": [],
 "terminal_reason": "completed",
 "fast_mode_state": "off",
 "fast_mode_disabled_reason": "sdk_opt_in_required",
 "subagent_stats": {
  "spawned": 0,
  "requested": {
   "background": 0,
   "foreground": 0,
   "unset": 0
  },
  "started_in_background": 0,
  "max_depth": 0,
  "spawned_by_subagents": 0,
  "completed": 0,
  "failed": 0,
  "killed": {
   "parent": 0,
   "user": 0,
   "system": 0
  },
  "refused": {
   "depth_limit": 0,
   "concurrency_limit": 0,
   "budget": 0
  },
  "by_type": {}
 },
 "safety_stops": 0,
 "is_error": false,
 "num_turns": 3,
 "subtype": "success",
 "api_error_status": null,
 "result": "I scheduled both meetings in `calendar.json` and wrote `SUMMARY.md` (times are America/New_York).\n\n- **Task A: Q4 planning** is on **2026-10-21 from 12:00 to 13:00** with bob, priya and marco. There was no 60-minute window on 2026-10-20 when all three were free: the only open slots were 11:00\u201311:30 and 12:30\u201313:00, each 30 minutes. On 10-21, 12:00 is the first time all three are free, because bob is busy until then.\n- **Task B: 1:1 bob/priya** is on **2026-10-21 from 14:00 to 14:30**. Bob is busy until 13:00 (including Q4 planning) and priya is busy from 13:00 to 14:00, so 14:00 is the earliest time they're both free.\n- **Task C:** `SUMMARY.md` lists both events with their times, attendees and why each slot was chosen.\n\nBoth events are in `events`, and their times are added to each attendee's busy list. The request only asked for that on Task A, but I also added the 1:1 to bob's and priya's busy lists so their calendars stay accurate.",
 "ttft_ms": 2098,
 "type": "result",
 "duration_ms": 13903,
 "uuid": "[REDACTED]",
 "ttft_stream_ms": 908,
 "time_to_request_ms": 306,
 "first_content_frame_ms": 908,
 "queued_turn_count": 0,
 "result_index": 0
}