-
Notifications
You must be signed in to change notification settings - Fork 4.7k
appointment bots explained
Searches about appointment bots almost always mean one of two systems: embassy and consulate visa-appointment calendars, or DMV-type government booking sites, both defined by the same shortage of open slots. Around that shortage two very different things have grown: a narrow, legitimate use of automation, and a paid ecosystem that embassies now publish warnings about. This page separates them, leads with the legitimate one, and quotes the official sources on the rest.
There is exactly one appointment-related task this wiki considers an agent fit for: watching availability for yourself, and telling you when it changes. That is not a special appointment feature, it is ordinary page monitoring, and the full treatment already exists on the monitoring page: checking a page the way a patient person would, remembering what was seen last, and raising an alert instead of taking an action. Applied here, the shape is a check of the public availability page at a human cadence, an alert to you when something opens, and then you, in your own session, as yourself, doing any actual booking by hand.
Three properties separate this from everything described below, and all three have to hold: it is your own appointment need, not a service to others; the checking rhythm is what a person would do, not what a machine can do; and a human makes the booking. This page does not go one step further than that. There are no auto-booking instructions here, and the rest of the page is the explanation of why.
Two neighbouring tasks sit inside that same boundary, because both read and neither acts: checking order and delivery status with an AI agent, where the value is in the account pages rather than the carrier's, and collecting event and course listings with an AI agent, which stops at recording what is offered and never registers for any of it.
Conflict of interest, declared where it belongs: you are reading the wiki of a browser-automation tool. An agent can be pointed at either half of this subject, which is exactly why the boundary is written down rather than left to the reader's imagination.
Mechanically, an appointment bot is a program that polls a booking calendar at high frequency and reacts the moment a slot appears. The polling is the whole trick: cancelled or newly released slots surface at unpredictable times and disappear in minutes, so a bot checks many times a minute, around the clock, which no person can or would do. What happens on a hit divides the category in two: alerting bots notify a human, booking bots seize the slot themselves, logged in with someone's credentials, at machine speed.
That polling profile is also the built-in weakness. Checking a page hundreds of times an hour is a pure volume signature, the third of the four layers on why does my AI agent get blocked?, and the way automated loops amplify it has its own page, agent retry loops and rate limits. No fingerprint work and no clean address survives a request rate that announces itself, and booking systems do not need anything sophisticated to see it: they count.
The systems say so themselves. The FAQ of the Italian Consulate General in London, on the Italian foreign ministry's own booking platform, explains that an account still locked after the ordinary 24 hours "has been automatically blocked by the system", and that this "typically occurs when anomalies are detected, such as booking attempts that are too rapid to be performed by a human operator (e.g., the use of bots) or multiple booking attempts across different services." That is a government booking system stating, in its own help text, that too fast is the tell and an automatic block is the response.
Where slots are scarce, intermediaries run booking bots at scale, seize appointments as they are released, and sell them. This is the half of the subject that official sources have started addressing by name, and their statements are worth reading in full.
The U.S. Embassy in Santo Domingo maintains a page titled "Beware of Visa Fixers, Bots, and Offers of Earlier Visa Appointments". It advises applicants to "stay far away from visa fixers offering earlier appointments", says the embassy "is aware of individuals who are attempting to manipulate the visa appointment system through bots and other unauthorized methods", and spells out what manipulation costs the applicant: "Potential consequences include: appointment cancellation, visa refusal, and visa cancellation." The same page adds the sentence that frames the whole ecosystem: "Any attempt to manipulate the appointment system is both unfair to other applicants and puts your application at risk."
Enforcement is not hypothetical. In March 2025 the U.S. Embassy in India publicly announced that it was canceling about 2,000 visa appointments made by bots and suspending the scheduling privileges of the associated accounts, stating zero tolerance for agents and fixers who violate its scheduling policies; the announcement is cited by name in the sources below.
And the question people actually type, answered plainly: can a visa bot guarantee approval? No, and approval was never the bot's to give. A bot touches a calendar; a visa decision is made by a consular officer, on the applicant's own case, at the interview the slot merely schedules. A paid slot buys, at best, the same interview and the same decision; at worst, per the embassy's own list, it costs the appointment or the visa because of how the slot was obtained. Anyone selling a "guaranteed" outcome is selling something that is not theirs.
One more thing needs saying without hedging. Government booking systems are a public service with a fixed pool of slots. A bot does not create appointments; it moves them, to whoever paid, away from whoever did not. And the polling itself has a cost even before any slot is taken: a public calendar hammered around the clock by scripts serves everyone worse, and pushes the operator toward tighter limits and stricter defenses that ordinary applicants then climb over. Hammering a public queue is not a clever trick around scarcity; it is queue-jumping that also degrades the queue.
That is the fairness half of why the legitimate slice at the top of this page is drawn where it is: watching for yourself at a human cadence takes nothing from anyone.
Can a visa bot guarantee approval? No. Approval is decided by a consular officer on your case, not by whoever booked the slot, and it was never the bot's to give. Official warnings add that manipulated bookings risk appointment cancellation, visa refusal, and visa cancellation.
Do appointment bots work? They can seize slots, which is exactly why embassies act against them: bot-made appointments have been cancelled by the thousands and the accounts behind them suspended. Whatever a bot books, the system can unbook.
Are appointment bots allowed? The booking systems' own help pages describe automatic blocks for bot-speed activity, and embassy statements attach consequences up to visa cancellation. Between those two sources there is no reading under which they are welcome.
Can an AI agent watch appointment availability for me? Watching a public availability page for your own need and alerting you is page monitoring, and the monitoring page covers doing it at a human cadence. The booking itself stays yours, by hand.
Why do booking-site accounts get blocked? Because high-frequency checking is a volume signal the systems watch for; one consulate FAQ names "booking attempts that are too rapid to be performed by a human operator" as a trigger for automatic blocks. The general mechanics are on the blocked page and the retry-loops page.
Should I pay someone who says they have appointment slots? The embassy warning quoted above tells applicants to stay far away from fixers, and its consequence list falls on the applicant, not the seller. The money buys, at best, an interview that was never theirs to sell.
Retrieved 2026-09-03 unless noted.
- Beware of Visa Fixers, Bots, and Offers of Earlier Visa Appointments, U.S. Embassy in the Dominican Republic, for the warning and consequence quotes.
- FAQ, booking system, Consulate General of Italy in London, for the automatic-block quote on too-rapid booking attempts.
- U.S. Embassy India statement, March 2025, cited by name and URL: the platform does not permit retrieval, so nothing is quoted from it here; the cancellation of about 2,000 bot-made appointments and the account suspensions it announced were corroborated across contemporaneous press coverage found in this session's searches.
See also: monitoring a page for changes with an AI agent, agent retry loops and rate limits, why does my AI agent get blocked?, and the rest of Using the Agent.
From the invisible_playwright_mcp wiki. The agent is good at watching pages patiently; the maintainer's position is that booking stays a human act, in your own name, at the queue's own pace.
- OpenAI Operator alternatives
- Open-source Operator-style agents
- Is OpenAI Operator still available?
- OpenAI Operator vs Claude computer use
- browser-use alternatives
- Choosing an AI browser agent
- Open-source AI browser agents
- Open-source computer-use agents
- What is an AI web agent?
- AI browser agents vs traditional scraping
- Cloud browser infrastructure for AI agents, explained
- Browserbase alternatives
- Firecrawl vs an AI browser agent
- Skyvern alternatives
- Stagehand vs browser-use
- Project Mariner is gone: what replaced it
- Manus alternatives
- Gemini computer use vs Claude computer use
- invisible_playwright_mcp, reviewed honestly by its own wiki
- AI browser vs AI browser agent: which one do you want?
- AI browser agent vs RPA: which one fits the job
- AI browser agent vs n8n, Zapier and Make
- Vercel agent-browser alternatives, compared honestly
- What is an agentic browser? Definition and the two kinds
- Open-source agentic browsers: the three layers, compared
- Choosing an MCP server for browser automation: four axes
- Stealth MCP servers compared: Camoufox, nodriver, Patchright
- Playwright MCP alternatives, and the three you don't need
- Autonomous browser agents: the four rungs of autonomy
- What is actually free in the AI browser agent stack
- browser-use on GitHub: what the repo actually gives you
- Playwright MCP vs Chrome DevTools MCP: different jobs
- How to choose among MCP servers: a map by category
- Which MCP servers are worth adding to Claude Code
- MCP on GitHub: finding servers and judging them fast
- MCP vs an API: the decision, and what the wrapper costs
- MCP alternatives: when the protocol is the wrong shape
- Why does my AI agent get blocked?
- The timing signal AI agents give off
- Agent retry loops trip rate limits, not fingerprints
- Claude computer use detected as a bot
- browser-use getting blocked: what you can and cannot change
- Playwright MCP session blocked: four causes, four fixes
- Playwright MCP and captchas: what actually gets you past
- Cloudflare and a browser MCP server: what is being read
- Can an AI agent solve a captcha? The honest answer
- Getting an AI agent to fill out forms
- Which model to use with invisible_playwright_mcp
- Browser problem or model problem?
- Running invisible_playwright_mcp's browser from Claude Code
- Extracting data to a CSV with an AI agent
- Monitoring a page for changes with an AI agent
- Running invisible_playwright_mcp's browser from Claude Desktop
- Running invisible_playwright_mcp's browser from Cursor
- Using an AI agent to hunt for apartments
- Getting website data into Google Sheets with an AI agent
- Using an AI agent to download invoices from portals
- AI agents for web research
- Using an AI agent to test your own website
- Running invisible_playwright_mcp's browser from Cline
- Posting to social media with an AI agent
- Posting to Facebook with an AI agent
- Posting to Instagram with an AI agent
- Posting to X with an AI agent
- Automating LinkedIn posts: read this first
- Appointment bots: what they are and what an agent can legitimately do
- Track prices across sites with an AI agent
- Build a lead list with an AI browser agent
- Run an AI browser agent on a schedule
- AI browser agent with a local LLM: what changes
- Should you log your AI agent into your accounts?
- How to write a task an AI browser agent can follow
- Move data between two web apps with an AI agent
- The MCP server
- How the tools are shaped, and why
- Playwright MCP vs the Playwright CLI: which fits when
- Playwright MCP: browser is already in use, and the fix
- Playwright MCP best practices: four decisions that matter
- Playwright MCP with a proxy, and the three leaks it leaves
- A browser MCP server in GitHub Copilot: setup and limits
- Using a browser MCP server for web scraping: the pattern
- Which LLM for browser automation: the four properties
- How to build a browser agent, and what to take instead
- Getting an AI agent to log into a website: three routes
- MCP tools, resources and prompts: who controls each
- How many MCP tools is too many? The context arithmetic
- How to build an MCP server: the decisions, not the scaffold
- Local or remote MCP server: what changes, and what does not
- Writing an MCP client in Python: the thirty-line version
- Self-hosted AI agent: what one actually costs to run
- How long an AI browser agent takes per step, measured
- Text, HTML, snapshot or screenshot: what the agent should read
- Giving an AI browser agent a stopping condition
- Keeping an AI browser agent out of destructive actions
- Why did the AI agent click the wrong thing
- When the page changes under the AI agent
- Running one AI agent task across a list of sites
- Seeing a page as it appears in another country
- Getting data out of a dashboard with no export button
- Two browsers in one session: main and support
- Finding the dead links on a site with an AI agent
- Filling a CRM record from a company's website
- One form submission per spreadsheet row, with an AI agent
- Dated screenshots of a page as evidence
- Checking order and delivery status with an AI agent
- Reading a PDF that opens inside the browser
- Summarising a long page or thread with an AI agent
- Collecting every image on a page with its caption
- Collecting event and course listings with an AI agent
- Cancelling a subscription with an AI agent
- What an AI agent can and cannot do inside an iframe
- Shadow DOM and an AI agent: you can click it, you cannot read it
- Running invisible_playwright_mcp's browser from Codex
- What a page snapshot costs, per control
- Native selects and the ones that only look like selects
- Running invisible_playwright_mcp's browser from Gemini CLI
- Clicking by selector or by coordinates
- How long the agent waits before it gives up
- What a second browser costs
- Uploading a file with an AI agent, and why this one cannot
- Watching the agent work, and when it is worth it
- When not to use an AI browser agent
- Agent or script: deciding once instead of every time
- Using the keyboard instead of the mouse
- Secrets in an agent task: where they end up
- What an agent run should log
- Deduplicating what an AI agent collects
- Normalising values across sites
- Validating an AI agent's output
- Reading a table with an AI agent
- Driving a site's own search and filters
- The task works headed and fails headless