← Plugin catalog
Data & Analytics

Proofsource

Grovio Labs, Inc. v1.0.0

Brand visibility in AI answers

Full description ↓

View on ChatGPT ↗

Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.

Description

From the marketplace listing

Proofsource is a brand visibility analytics tool for marketing teams. It asks leading AI answer engines the questions your buyers ask, then shows how often the answers mention your brand, which competitors they recommend instead, and which sources they cite. Ask for a visibility audit or a fix plan and get answers backed by the measured responses, with a link to check each one in Proofsource. Proofsource only reads the workspace you connect, and asks before it changes anything.

Language: English · Automatically detected from descriptions.

Competitor profile

From the developer’s listing and package; capabilities are not independently tested. Package observed Nov 2, 2026.

Declared capabilities

  • Show AI visibility by engine and by question
  • Name the competitors AI recommends instead
  • Rank the sources AI answers cite

Declared limitations

  • General knowledge question
  • Data for a brand outside the connected workspace
  • Unsupported destructive request

Review scenarios; not an exhaustive list.

Cost & access

This plugin does not sell products or process payments.

Terms may have changed since this observation.

Starter prompt

Is my brand mentioned in AI answers?

View onboarding →

View package source →

Keywords

Files & skills

File archives

Plugin package7 files · 19.3 KBBrowse files →
Skill instructions
ai-visibility-audit2.08 KB

View saved version →

---
name: ai-visibility-audit
description: Audit how AI answers talk about the user's brand, using Proofsource data. Use when the user asks whether AI mentions their brand, who AI recommends instead of them, which sources AI cites, or what changed in their AI visibility.
---

# AI visibility audit

Answer with Proofsource's measured data only. Never guess a number. Every claim names the tool result it came from.

## Steps

1. **Pick the brand.** Call `list_brands`. One brand: use it. Several: ask which one, unless the user already named it.
2. **Visibility.** Call `get_visibility` with `by: "engine"` (default 30-day window). Note the overall mention rate, each engine's rate and the change against the previous period.
3. **Competitors.** Call `get_competitors`. Note the top 3 by share of voice and any that gained since the last period.
4. **Sources.** Call `get_citations`. Note the domains AI cites most for this brand's questions, and whether the brand's own site is among them.
5. **Changes.** Call `get_changes`. Note the visibility trend over the window, meaningful changes on competitors' websites and new pages about the category.
6. **Weak questions.** When visibility is low on an engine, call `get_visibility` with `by: "question"` and name the 3 questions where the brand is missing.

## Report

Write a short report in this order:

- **Headline:** one sentence with the overall mention rate and its change.
- **By engine:** a small table (engine, mention rate, change).
- **Competitors AI recommends instead:** top 3 with their share of voice.
- **Sources AI trusts:** top 5 cited domains.
- **What changed:** up to 3 bullet points.
- **Proof:** for each number, the tool and window it came from (for example "get_visibility, last 30 days"). Link the `open_url` from the results so the user can check every answer in Proofsource.

End by offering the fix-plan skill: "Want a prioritized plan to close these gaps?"

## Rules

- Say "competitors", never "rivals".
- No prices, plan names or upgrade links.
- If a tool says the workspace has no data yet, say so plainly and stop. Do not fill gaps with estimates.
fix-plan1.96 KB

View saved version →

---
name: fix-plan
description: Turn Proofsource's open AI visibility gaps into a prioritized fix plan, then track new buyer questions and record shipped fixes. Use when the user asks how to get mentioned by AI, what to fix first, or says they shipped a fix.
---

# Fix plan

Build the plan from Proofsource's open gaps only. Never invent a gap, a source or an impact number.

## Steps

1. **Pick the brand.** Call `list_brands`. One brand: use it. Several: ask which one, unless the user already named it.
2. **Open gaps.** Call `list_fix_opportunities`. Each gap carries its evidence (the questions and engines where AI leaves the brand out) and a suggested fix.
3. **Prioritize.** Rank gaps by the number of buyer questions affected, then by how many engines miss the brand, then by effort (an edit to an existing page beats a new page). Keep the top 5.
4. **Plan.** For each gap, turn its suggested fix into one concrete action: the page to change or create and what to add. Quote the gap's evidence so the user sees why it matters.
5. **Confirm before writing.** Ask before any write. Then:
   - To track a buyer question the plan depends on, call `list_topics` for the topic id and `create_prompt` with the question phrased the way a buyer would ask.
   - When the user says a fix is live, call `mark_fix_shipped` with the gap id, one or two sentences on what shipped, and the ship date.
6. **Check results.** For fixes already shipped, call `get_fix_verification` and report each verdict as given: moved, within normal answer churn, or waiting for more answers.

## Output

- A numbered plan: action, gap questions, engines that miss the brand, effort (small, medium, large).
- Proof for each item: the gap id and the tool it came from. Link `open_url` when the results carry one.
- After a write, confirm exactly what was recorded.

## Rules

- Write tools change the user's workspace. Never call them without a clear yes.
- Say "competitors", never "rivals".
- No prices, plan names or upgrade links.

Release notes

First release: AI visibility audit and fix plan skills, connected to the Proofsource MCP server.

Declared in the saved package. Remote tools may change independently.

Package details

Publisher declarations from the archived package. These are separate from our research and the live service's terms.

Package license
Proprietary
Package author
Proofsource
Keywords
See keywords
Getting started skill
./skills/ai-visibility-audit/SKILL.md
Commerce declaration
Does not support commerceThis does not establish whether access is free or paid.
Review scenarios
5 positive · 3 negativeScenario counts, not test results.

Declared capabilities

  • Show AI visibility by engine and by question
  • Name the competitors AI recommends instead
  • Rank the sources AI answers cite
  • Explain what changed over time
  • Build a prioritized fix plan
  • Track new buyer questions and shipped fixes

Package observed Nov 2, 2026.

Technical details
First seen
Oct 26, 2026 · 18:00 UTC
Last seen
Nov 3, 2026 · 18:00 UTC
Collection status
Collected

plugin_asdk_app_6ac9d64a11848191a83cf338c49ec71b

Download plugin data (JSON)