AI Answer Visibility Check: does an assistant name you when a buyer asks, and who gets named instead
by PaperChaseWebb
Ask each buyer question three times per assistant in fresh chats, paste the answers, and get a dated record of where you were named, where you were missed, who was named instead and which sources each answer cited. Fifteen read-only checks keep it honest: no brand in the question, three runs before a gap, answers hashed as given, nothing older than a month treated as current, and only your own brand. Page changes wait for the owner's yes.
- Price
- $19
- Difficulty
- Beginner
- Setup
- 45 min
- Format
- .md file
ai-answer-visibility-check-does-an-assistant-name-you.md · 48 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
You know which buyer questions leave you out, who the assistants name instead, and the pages they lean on, from three runs each, with a record you can rerun next month; and no page changes without your yes.
What you get
- 18 sections in one .md file, with a one-line unpack
- How to write buyer questions without your name, and how to ask so one odd answer is not read as a pattern
- The check folder: visibility.json, answers, verdicts, actions and approvals, with blank templates
- vis.py: record a pasted answer (hashed, read for your name, position, others named and sources), score, a report, and owner approval tied to a sha256
- visibility_check.py: fifteen read-only checks, with a seeded test folder (15 findings, then 0) and the unit tests
- A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block
- Ten prompts, a failure table, a worked example on a made-up bookkeeping firm, and a look at the paid trackers with sources
Who it is for
People who want to know, three runs at a time, whether AI assistants recommend them to buyers, and which pages to change, without a monthly tracking subscription.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block; the scripts were tested on Linux with Python 3.13, the agent files were not loaded inside each harness and no real assistant was asked anything for the worked example.
Tools needed
Cost to run: The pack is the only purchase. The scripts use no model tokens; asking the assistants uses your own accounts.
Time to result: A first report in an afternoon of asking, for five questions on two or three assistants
How it works
Run the tests
Unpack the pack and run sh test_all.sh.
Expected: 15 findings on the seeded folder and 0 on the fixed one, 15 of 15 single faults caught alone, checker tests 29 passed, vis.py tests 39 passed, exit 2 on a missing folder.
Write the questions
Run vis.py init, then write five to ten buyer questions without your name, list your competitors, and set own_brand_attested yourself.
Expected: V01 to V04 clean.
Ask three times
Ask each question in a fresh chat on each assistant, three times, and save each answer as a .txt file. Record each with vis.py record.
Expected: answers.csv fills in with who was named and the links cited.
Score, report, get the yes
Run vis.py score, the checker and vis.py report. Propose one page change per gap in actions.csv; the owner approves each at their own terminal.
Expected: A dated report of gaps, others named and sources, and every change tied to the owner's yes.
Sample prompts, free to use
Help me write eight buyer questions for my business without using my name. Mix find, compare and check questions, and keep my city in the local ones.
Prompt 1 of 10.
Run vis.py score, visibility_check.py and vis.py report. Tell me, in plain words, where I was missed and who was named instead.
Prompt 4 of 10.
Propose one page change per gap in actions.csv. One change per row, on my own site only, no listings to buy and no one to contact.
Prompt 6 of 10.
Free preview of the file
# AI Answer Visibility Check: does an assistant name you when a buyer asks? Version 1.0, 2026-10-29. By PaperChaseWebb. For small businesses, consultants and agencies who want to know, in a dated record they can show someone, whether ChatGPT, Claude, Gemini, Perplexity or Grok names them when a buyer asks the kind of question that leads to a sale. You ask each buyer question three times per assistant in fresh chats, paste the answers into a folder, and a script reads every answer for your name, the competitors named instead, and the links the assistant cited. Fifteen read-only checks keep the record honest: questions that do not leak your name, three runs before anything is called a gap, answers kept exactly as given and hashed, nothing older than a month treated as current. Page changes you decide to make wait for your yes, typed at your own terminal and tied to a sha256. Python 3 standard library only, no network. Works with Claude Code, Codex and Hermes through a skill file and an AGENTS.md snippet, and with Grok Bot through a rules block. Tested as described in section 11 on Linux with Python 3.13, including owner approvals typed at a pseudo-terminal. The agent files were not loaded inside the harnesses for this release, and no assistant was asked anything to make the worked example: the business, competitors and answers are made up. The tools that track this today are mostly monthly subscriptions that ask the assistants for you on a schedule and show a chart. Several a
Test record
- Date
- Oct 29, 2026
- What was run
- visibility_check.py on a seeded folder and a fixed copy, each planted fault alone, a missing input, and the unit tests. Linux, Python 3.13.
- Result
- 15 findings on the seeded folder, 0 on the fixed one; 15 of 15 planted faults caught alone; exit 2 on missing input; nothing written. 29 checker and 39 vis.py tests passed, 0 failed.
- Not run
- The agent files inside Claude Code, Codex, Hermes or Grok Bot. Windows and macOS. The scripts open no network connection.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- No real assistant was asked anything for the worked example; the business, competitors and answers are made up. Answers vary by account, location, model version and day, so the report is a dated record of what you saw.
- The pack does not ask the assistants for you and contains no browser automation or API caller. You ask by hand, or with your own official API key.
- Name matching is word matching on the names and aliases you list. It misses misspellings you have not added as aliases, and it cannot tell a recommendation from a warning.
- The pack makes no claim about mentions, sales, traffic or ranking.
- The skill file, AGENTS.md snippet and Grok Bot rules block were not loaded inside Claude Code, Codex, Hermes or Grok Bot. Linux only; Windows and macOS were not tested. The scripts open no network connection.
- The approval step refuses piped input and the environment variables Claude Code, Codex, Hermes and Grok Bot set. That stops an agent approving its own change; it is not a lock against someone with the same account.
- On 2026-10-29, on Linux with Python 3.13: visibility_check.py gave 15 findings on the seeded folder (each check once) and 0 on the fixed one, caught 15 of 15 single faults with only its own check, wrote nothing, and exited 2 on a missing folder, missing or broken visibility.json; checker tests 29 passed, 0 failed; vis.py tests at a pseudo-terminal 39 passed, 0 failed.
Questions
Why three runs?
The same question in a new chat can name different businesses. One answer is not a pattern, so the check will not call a gap on fewer than three fresh runs.
Why not have the agent ask the assistants?
Automating a consumer chat window breaks most assistants' terms. You ask by hand, or with your own official API key, and the agent records and reads the answers.
How is this different from a tracking subscription?
Paid trackers ask for you on a schedule and cover far more questions. This is a $19 pack for a small, careful, dated record and the pages to change. If you need daily numbers across hundreds of questions, use a tracker.
Can I check a competitor?
No. The check runs only on a brand the owner attests is theirs, or one they are hired to represent.
Details
Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
License: Use for your own business and for clients you are hired to represent. Do not resell or republish the pack itself. Download terms
Related
AI Answer Visibility Check: five rules and a five-check script (free sample)
From the AI Answer Visibility Check: five rules for checking whether assistants name you (leave your name out of the question, a fresh chat each time, three runs before you call it, save the answer as it came, change your own pages with your own yes), and a read-only script that checks your saved answers.
Agent-Ready Storefront Check: can an AI agent find, read and buy from your store, and which file fixes it
Fifteen read-only checks on the folder your build writes and the repo behind it, not a live URL: robots.txt and an export of your CDN or firewall bot rules let agent shoppers reach product and checkout pages, llms.txt links every machine-readable file, Product JSON-LD and prices agree, every paid page has a real checkout link, buy controls are links or buttons, no CAPTCHA sits on a product or checkout page, and policies are linked. Every finding names the source file to change. Source edits wait for the owner's yes; checkout and bot rule changes stay with the owner.
Source Shelf: a short, owner-approved list of industry reports your team reads, and a way to read them
Keep a small set of major industry reports as your team's default evidence base: each with its edition, publish date, link on the publisher's own site, the date someone last looked for a newer edition, and a note on what the publisher sells. Read any one of them against three questions (what is changing, who is struggling, what could help them), with word-for-word quotes and page numbers, the third answer marked as your inference, and every figure matched to its quote. Every add, drop and replace waits for the owner's yes. Fifteen read-only checks run on the folder.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Name the decision, then score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule, three gate rules and a skeptical pass, and read your band and the next steps it allows. v1.1 starts with the decision the score will change, scores unknowns as unknown, adds rules for conflicting facts and lookalike public records, ties every band to the next steps it allows with the Production Readiness Audit before go-live, makes owner approval concrete (prepared and approved status, a one-reply approval line, decisions the agent must leave open, a done test), adds agent files for Grok Bot, Claude Code, Codex and Hermes, a second worked example (missed call to booked job), a readiness folder with a fifteen-check read-only checker, a front door test with four questions to ask anyone selling you an agent install, and a plain note on how it was tested. Still free.
Agency Install Kit: install one agent workflow in two weeks, with a binder a script can check
Five paid packs and the free Readiness Self-Check, tied into one two-week install by a new Install Binder: plain files for readiness, one workflow, agent owners and tested pauses, a gate register, a reach inventory, a cost cap, a dry run with refusal cases, a scorecard with kill rules and a run sheet with an off switch. A fifteen-check script names every missing decision, and the owner's go-live yes is tied to the binder's sha256.