---
ref: workflow:ai-answer-positions
title: Sort AI answers by how they treat your brand
author: thedogwiththedataonit
tools: [tool:profound/list-organizations, tool:profound/list-categories, tool:profound/get-prompt-answers, tool:typesafe/answer-typed-questions, tool:notion/create-page]
tags: [capability:classify-signals, capability:manage-docs, capability:track-ai-visibility, motion:content]
updated: 2026-09-29
---

# Sort AI answers by how they treat your brand

Pulls the AI answers Profound recorded for your category, labels how each one treats your brand with Jev, and saves a report in Notion.

Set up the tools below, then run the steps in order for the user, carrying each step's results into the next. The run is done when the user has the outcome below.

## Outcome

- A table of every answer read, with how it treats your brand, the product it recommends first, the prompt's buying stage and Jev's confidence.
- The answers that describe you negatively or contradict your facts, quoted and checked by you.
- A Notion page with the counts by engine and buying stage, and the answers to fix first.

## Inputs

Ask the user for these before you start.

- `category`: the Profound category to read, by name, e.g. Email marketing platforms
- `brand`: your product's name as buyers write it, e.g. Acme
- `competitors`: the products an answer might recommend instead, e.g. Mailchimp, Klaviyo, Brevo
- `brand_facts`: the facts about you an answer should get right, e.g. has a free plan; integrates with Shopify; SOC 2 Type II
- `lookback_days`: how many days of answers to read, e.g. 7
- `max_answers`: the most answers to read in one run, e.g. 300
- `min_confidence`: how sure Jev must be before its answer is used without you, e.g. 0.8; a yes-or-no answer counts as yes at or above it and as no at or below 1 minus it
- `report_parent`: the Notion page the report goes under, by name, e.g. AI visibility

## Set up

### Profound (tool:profound/list-organizations, tool:profound/list-categories, tool:profound/get-prompt-answers)

Use the MCP server. Add it to your agent's MCP settings, then sign in when asked.

```json
{ "mcpServers": { "profound": { "url": "https://mcp.tryprofound.com/mcp" } } }
```

- List organizations: call the MCP tool `list_organizations`
- List tracked categories: call the MCP tool `list_categories`
- Get recorded AI answers: call the MCP tool `get_prompt_answers`

Note: Sign in with your Profound account through OAuth; tools return only data the authenticated user can access. Available data depends on your account permissions.

Notes:

- List organizations: No inputs required; keep the organization ID for category discovery.
- List tracked categories: Requires org_id from list_organizations; keep the category ID for reports.
- Get recorded AI answers: Requires category_id and inclusive start_date/end_date. Use prompt_id for one prompt; paginate with limit and offset. Country and region filters cannot be combined.

### Answer typed questions (TypeSafe AI, tool:typesafe/answer-typed-questions)

Use the API.

- Base URL: https://api.typesafe.ai
- Endpoint: `POST /v1/systemone`
- Auth: send the header `Authorization: Bearer $TYPESAFE_API_KEY`
- Get a key: https://console.typesafe.ai

Note: Put every question about one record in one request. `GET /v1/models` lists the models and is the cheapest check of a key; a request over the rate limit gets a 429 with a Retry-After header.

Note: Send `state`, `model` (`jev-latest`) and named `questions`, each with `type`, `instructions` and `criteria`: a choice maps labels to descriptions, a score lists its levels in order, a noul's is optional. Read a score by its most likely level; send unsure answers to a person.

### Create a page (Notion, tool:notion/create-page)

Use the first option your agent supports.

Note: To add a row to a database, set the parent to its data source and match that data source's property schema.

#### MCP (official, remote)

Add this server to your agent's MCP settings, then sign in when asked.

```json
{ "mcpServers": { "notion": { "url": "https://mcp.notion.com/mcp" } } }
```

Call the MCP tool `notion-create-pages`.

#### CLI (official)

Install the command, then confirm it runs.

```sh
npm install --global ntn
ntn --version
```

Run `ntn api v1/pages`.

Set `$NOTION_API_TOKEN` in your environment first (get a key: https://www.notion.so/developers/tokens).

Before step 1, confirm access to each service with its cheapest read-only call, like a list or a search. Never send or change anything to test access.

## Steps

1. **Find the organizations** with List organizations (Profound). Keep each organization's ID.
2. **Find the category** with List tracked categories (Profound). List each organization's categories. Keep the organization and category IDs of `category`.
3. **Pull the answers** with Get recorded AI answers (Profound). Get the answers recorded in the last `lookback_days`, up to `max_answers`. Keep each answer's prompt, engine, date and text.
4. **Read each answer** with Answer typed questions (TypeSafe AI). Send the prompt, the answer and `brand_facts` as the state, with a choice `position` of recommended_first, recommended, listed (named without a recommendation), mentioned_with_caveat, mentioned_negatively and absent, all about `brand`; a choice `top_pick` over `brand`, `competitors`, another_product and none, for the product the answer recommends first; a choice `stage` of problem, solution, comparison and brand, for what the prompt asks; and a noul `contradicts_facts` (says something about `brand` that `brand_facts` contradicts). Keep every answer with its confidence or probability.
5. **Check the unsure ones with the user** yourself. Show the user every answer whose position, top_pick or stage confidence is below `min_confidence`, every answer mentioned_negatively, and every answer whose `contradicts_facts` is yes or unsure, quoted, and keep what the user decides.
6. **Find what to fix** yourself. Count the answers by position, engine and stage. List the answers where `brand` is mentioned negatively or contradicts its facts, quoted, and the comparison prompts where a competitor is the top pick.
7. **Save the report** with Create a page (Notion). After the user approves, create a page under `report_parent`, found with a read-only Notion search, with the counts, the quoted answers and the comparison prompts to fix first.

## Notes

Visibility scores count mentions, and an answer that lists you last with a caveat counts the same as one that recommends you first. The position labels tell them apart. For an answer that contradicts your facts, check the pages the engine cites before writing new content.

Run it weekly with `lookback_days` set to 7.

## Rules

- Use only the services set up above. The read-only calls they need, like listing ids or polling for results, are fine.
- Ask the user before anything that sends messages, costs money, or changes data, and say how many records it touches. One approval covers a batch the user has seen.
- Never print API keys.