{"slug": "i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill", "title": "I let an AI agent run my job search: the real numbers, including the LLM bill", "summary": "A backend developer in São Paulo built an AI agent to autonomously run his remote-job search and published the first four days of data, including the LLM bill. The agent discovered 360 roles from 11 sources, applied to 9, and received 2 recruiter replies, but the cost per application averaged $3.36 on a premium model, which the developer says makes the product nonviable without optimization. The developer also found that ATS anti-bot measures forced a real headed browser setup, and that the most valuable function was filtering out 87% of roles to avoid spamming recruiters.", "body_md": "# I let an AI agent run my remote-job search. Here are the real numbers — including the LLM bill.\n\nI'm a backend developer in São Paulo looking for a remote role paid in USD. The real grind of that search isn't interviewing — it's the pipeline: trawling job boards, judging fit, filling the same Greenhouse/Lever/Workable forms again and again, then watching the inbox so a recruiter reply doesn't rot for two days. So I built an agent that runs the entire cycle autonomously, and pointed it at my own search. This is the data from the first four days — including the part that almost killed the project: the LLM bill. One honest caveat up front: this is a single search, mine, so n=1.\n\n## What the agent actually does\n\n**Discovers** roles from 11 sources on a scheduler — remote job boards, ATS listings, hiring platforms.**Scores** every role against my profile: salary floor, timezone overlap, stack, work-authorization constraints. Low fit never becomes an application.**Applies** in a real browser: fills the real form with my canonical answers, uploads the résumé, clicks submit — saving a screenshot right before and right after.**Follows up**: reads confirmations and recruiter replies in the mailbox, classifies them, and answers from a Q&A bank I control.** Books**interview invites into my calendar working hours — wired up, but none of the agent's applications has reached that stage yet. It's been four days.\n\n## Four days of real numbers\n\n| Roles discovered (11 sources) | 360 |\n| Passed my fit rules | 47 (13%) |\n| Applications submitted end-to-end | 9 |\n| Recruiter replies received — answered by the agent | 2 |\n| Rejections so far | 2 |\n| Evidence screenshots captured | 230 |\n\n## Surprise #1 — the filter is the product\n\nThe most valuable thing the agent does is say *no*. 87% of everything it discovered never became an application, because a salary floor, a timezone window or a work-permit rule failed. Every one of those is a form I didn't fill and a recruiter who didn't get spammed. The auto-apply tools that promise “1,500 applications a day” invert this ratio, and it shows — recruiters can tell, and ATSs are responding with fraud detection. Applying less, better, is the only version of this category that survives contact with the hiring side.\n\n## Surprise #2 — the LLM bill\n\nI added per-call cost telemetry to every stage. The two most recent applications — same agent, same premium model — cost **$6.33** and **$0.39**. The expensive one burned about **8 million cache-read tokens**, because the agent re-reads large chunks of page DOM on every turn of its form-filling loop. Complex form, more turns, more re-reads — the cost compounds quietly.\n\n| Apply agent, mean per application (premium model, as run) | $3.36 |\n| Same workload repriced on a small model | $0.59 |\n| Job scoring, per role | $0.11 → $0.002 layered |\n| Inbox classification, per email | $0.03 → $0.0005 layered |\n| Target for a viable product | ≤ $0.03 per application |\n\nThe honest verdict: at premium-model prices this product cannot exist. The path down is not just “use a cheaper model” — it's a DOM diet (strip pages to the form skeleton before they enter context), hard turn caps, and layering (a cheap model for extraction, a better one only for eligibility decisions and answers). I'm publishing these numbers because every “AI agent” product is quietly fighting exactly this battle, and almost nobody shows the meter.\n\n## Surprise #3 — the web is hostile, even to honest automation\n\nATS forms live behind Cloudflare and assorted anti-bot walls, and headless browsers are detected trivially. What ended up working: a real, headed Chromium running under a virtual display (Xvfb) on a server, with WebGL intact and no automation flags leaking. The rule I converged on: the less you fake, the less you get detected — the browser's own real user agent, physically consistent viewport and screen, clock following the exit IP. Every clever spoof I tried was itself a fingerprint.\n\n## The constraints I won't relax\n\n**Max 5 applications a day.** Mass auto-apply is spam, and the hiring side is arming itself against it.**It never invents facts.** Work authorization, salary expectation, availability — answers come from my Q&A bank, or the form doesn't get submitted.**No LinkedIn, no Indeed.** Both prohibit automation and suspend accounts. Nobody's professional identity is worth it.**Evidence for everything.** Pre- and post-submit screenshots plus a full answer log, for every single application.\n\n## What's next\n\nThe agent keeps running my own search while I turn it into a product: [find-best-job.com](https://find-best-job.com/en). The free tier does 5 full applications a month — you paste the job link, the agent does everything, evidence included. If you want to push back on the engineering or the ethics, I'm genuinely interested: hello@find-best-job.com.", "url": "https://wpnews.pro/news/i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill", "canonical_source": "https://find-best-job.com/en/blog/agent-job-search-real-numbers", "published_at": "2026-07-24 13:05:05+00:00", "updated_at": "2026-07-24 13:22:06.069167+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "artificial-intelligence", "developer-tools"], "entities": ["Greenhouse", "Lever", "Workable", "Cloudflare", "Chromium", "Xvfb"], "alternates": {"html": "https://wpnews.pro/news/i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill", "markdown": "https://wpnews.pro/news/i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill.md", "text": "https://wpnews.pro/news/i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill.txt", "jsonld": "https://wpnews.pro/news/i-let-an-ai-agent-run-my-job-search-the-real-numbers-including-the-llm-bill.jsonld"}}