Claude Opus 5.5 on Fill and submit job applications from a resume

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: 18s
Human step-ins: 0
Outcome: Pass

Compare with other models on this task →

Exact prompt

This is a sandboxed mock job portal. resume.json is the candidate. forms/ has two job application forms (field definitions). For each form, write a JSON file {"job_id": ..., "answers": {field_name: value}} filled truthfully from the resume (never invent facts), then submit it with: python3 submit.py <file>. Fix and resubmit if rejected. Both applications must end up SUBMITTED.

Task prompt given to the agent (headless, offline, synthetic fixture inputs): This is a sandboxed mock job portal. resume.json is the candidate. forms/ has two job application forms (field definitions). For each form, write a JSON file {"job_id": ..., "answers": {field_name: value}} filled truthfully from the resume (never invent facts), then submit it with: python3 submit.py <file>. Fix and resubmit if rejected. Both applications must end up SUBMITTED. Inspired by https://x.com/SAkasxh/status/2104655629021565156 (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: ACME submitted; Globex submitted; ACME identity fields match resume; ACME years_experience = 6-9; ACME authorized = yes; ACME skills only from resume; Globex names/title/email match; Globex relocation false; Globex salary = 165000; Globex linkedin from resume (if given).

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 (10/10 checks).

Estimated cost List-price estimate; not actually billed.

Metrics

Estimated cost: $0.10
Wall time: 18s
Human step-ins: 0
Turns: 3

Model usage
Model	Input tok	Output tok	Cost
AClaude Opus 5.5anthropic/claude-opus-5.5	57,201	1,413	$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: ACME submitted; Globex submitted; ACME identity fields match resume; ACME years_experience = 6-9; ACME authorized = yes; ACME skills only from resume; Globex names/title/email match; Globex relocation false; Globex salary = 165000; Globex linkedin from resume (if given).
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": 16554,
 "stop_reason": "end_turn",
 "session_id": "[REDACTED]",
 "total_cost_usd": 0.10305119999999998,
 "usage": {
  "input_tokens": 6,
  "cache_creation_input_tokens": 8119,
  "cache_read_input_tokens": 49076,
  "output_tokens": 1413,
  "output_tokens_details": {
   "thinking_tokens": 226
  },
  "server_tool_use": {
   "web_search_requests": 0,
   "web_fetch_requests": 0
  },
  "service_tier": "standard",
  "cache_creation": {
   "ephemeral_1h_input_tokens": 8119,
   "ephemeral_5m_input_tokens": 0
  },
  "inference_geo": "global",
  "iterations": [
   {
    "input_tokens": 2,
    "output_tokens": 439,
    "cache_read_input_tokens": 19365,
    "cache_creation_input_tokens": 900,
    "cache_creation": {
     "ephemeral_5m_input_tokens": 0,
     "ephemeral_1h_input_tokens": 900
    },
    "type": "message"
   }
  ],
  "speed": "standard",
  "fallback_credit": null
 },
 "modelUsage": {
  "claude-opus-5-5": {
   "inputTokens": 6,
   "outputTokens": 1413,
   "cacheReadInputTokens": 49076,
   "cacheCreationInputTokens": 8119,
   "webSearchRequests": 0,
   "costUSD": 0.10305119999999998,
   "contextWindow": 1000000,
   "maxOutputTokens": 128000,
   "thinkingTokens": 226,
   "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": "Both applications went through on the first try, with no rejections. Copies are saved in `submitted/`.\n\n- **ACME-1042 (Data Engineer):** I chose \"6-9\" for experience since the resume says 7 years, and \"yes\" for US work authorization because the resume says US citizen. For top skills (max 3) I picked Python, SQL and Spark. dbt was also allowed, but Airflow wasn't one of the options. The \"why Acme\" answer is 60 words, within the 40\u2013120 range.\n- **GLX-77 (Analytics Engineer):** Relocation is set to `false` because the resume says not willing to relocate. Desired salary is 165000, the resume's figure. The optional LinkedIn field has the URL from the resume. The cover note is 44 words, within the 30\u2013100 range.\n\nBoth free-text answers only use what's in the resume: title, Boston, 7 years and the listed skills. They say nothing specific about either company, because the resume gives no reason to apply to either one.\n\nThe answer files are `../apps/acme.json` and `../apps/globex.json`, which puts them outside the work directory.",
 "ttft_ms": 3115,
 "type": "result",
 "duration_ms": 16981,
 "uuid": "[REDACTED]",
 "ttft_stream_ms": 1610,
 "time_to_request_ms": 293,
 "first_content_frame_ms": 1610,
 "queued_turn_count": 0,
 "result_index": 0
}