# Brand DNA: agent guide

One brand name in: reads the official site, ads and search data, and returns an evidence-graded Brand DNA (purpose, voice, design, products, ads, market perception).

## Connect
- MCP: `https://brand-dna.listeningmind.ai/mcp` (Streamable HTTP). Start with `app_guide`.
- Browser agents: tools are registered on every page through WebMCP (`document.modelContext`).
- REST: `https://brand-dna.listeningmind.ai/.well-known/openapi.json`

## Approval
- read and action tools run at once.
- run and delete tools need a person's approval. Over MCP the tool returns `confirm_url`; show it to the person, then call `confirmation_status` with the token until state is done.
- In the browser the page shows the person a confirm box.

## Workflow
1. `estimate_run` (read): Check the price before the run
2. `start_run` (run): Start the Brand DNA extraction
3. `get_run_status` (read): Poll until done
4. `get_run` (read): Read the DNA
5. `get_guardrails` (read): Get the asset-production guardrails

## Inputs
Brand name, market (us, jp, kr), DNA language, official domain (optional), category hint (optional)

## Outputs
Brand DNA JSON (parameters, evidence, grades), Marketing Truth Alignment per moment of truth, asset-production guardrails, comparison-ready data

## Cost and time
500 Lima per Brand DNA (launch price; list 5,000 Lima). Reading results is free.

## Limits
Official sites are read under robots.txt. Creatives from the last 5 years only, newer ones weigh more.

## Continue in another app
- [Creative Director](https://daas-creative.listeningmind.ai/llms.txt) (MCP `https://daas-creative.listeningmind.ai/mcp`): When you want ads per buying situation made inside the DNA's guardrails. Carry: The brand, the market and the guardrails address (/api/dna/{dna_id}/guardrails).
- [Brand Naming Agent](https://daas-naming.listeningmind.ai/llms.txt) (MCP `https://daas-naming.listeningmind.ai/mcp`): When you need new product names in the brand's naming rules and lexicon. Carry: The DNA's naming rules, signature words and purpose sentence.
- [Brand Finder](https://daas-brand.listeningmind.ai/llms.txt) (MCP `https://daas-brand.listeningmind.ai/mcp`): When you pick the brands to compare in the same category. Carry: The category and the market.

## Using the screens (browser agents)
- `describe_screen`: menus, tabs, fields and buttons of the current screen, and what the page is for
- `go_to`: open a menu or page of this app by its label or path
- `fill_field`: type a value into a field by its label (never presses run; runs go through the run tools, which ask the person)
- `read_this_page`: the text and ids of what the person is looking at

## The ListeningMind apps (same account, same tools, call any of them)
Each app has `/mcp`, `/llms.txt`, `/agents.md` and WebMCP on its pages. `family_apps` and `recommend_app` return this list with addresses.
- [ACO](https://daas-aco.listeningmind.ai/llms.txt): Diagnoses whether a product detail page can be cited by AI answers and used by shopping agents (MCP `https://daas-aco.listeningmind.ai/mcp`)
- [AOO](https://daas-aoo.listeningmind.ai/llms.txt): Measures whether AI agents can get real tasks done on a website (MCP `https://daas-aoo.listeningmind.ai/mcp`)
- [AXO](https://daas-axo.listeningmind.ai/llms.txt): AXO · Agent Experience Optimizer (MCP `https://daas-axo.listeningmind.ai/mcp`)
- [Brand Finder](https://daas-brand.listeningmind.ai/llms.txt): Which brands lead search by generation or field, and what their brand assets are (MCP `https://daas-brand.listeningmind.ai/mcp`)
- [Brand Naming Agent](https://daas-naming.listeningmind.ai/llms.txt): Creates and checks brand name candidates grounded in search data (MCP `https://daas-naming.listeningmind.ai/mcp`)
- [Brand Wiki](https://daas-wiki.listeningmind.ai/llms.txt): Turns a brand website into the entities, wiki pages and evidence AI assistants read (MCP `https://daas-wiki.listeningmind.ai/mcp`)
- [CEP Finder](https://daas-cep.listeningmind.ai/llms.txt): In which situations do people start looking for this category (category entry point map) (MCP `https://daas-cep.listeningmind.ai/mcp`)
- [Creative Director](https://daas-creative.listeningmind.ai/llms.txt): Finds purchase situations (CEP) in search data and drafts a creative, an image and a video for each (MCP `https://daas-creative.listeningmind.ai/mcp`)
- [Demand Forecast](https://daas-forecast.listeningmind.ai/llms.txt): What category demand looks like in the next 3-6 months and when to launch or campaign (MCP `https://daas-forecast.listeningmind.ai/mcp`)
- [Funnel Leak Finder](https://daas-funnel.listeningmind.ai/llms.txt): Where category search journeys leak to competitors (MCP `https://daas-funnel.listeningmind.ai/mcp`)
- [GEO Audit](https://daas-geo.listeningmind.ai/llms.txt): Checks whether a web page is ready to be read and cited by search engines and AI answer engines (MCP `https://daas-geo.listeningmind.ai/mcp`)
- [Intent KG](https://daas-intent.listeningmind.ai/llms.txt): What people look for about a topic, why, and how they choose (Intent Knowledge Graph) (MCP `https://daas-intent.listeningmind.ai/mcp`)
- [Intent Panel Survey](https://daas-icss.listeningmind.ai/llms.txt): Survey and interview consumer intent groups that share the same job, as often as you need (MCP `https://daas-icss.listeningmind.ai/mcp`)
- [Next Item](https://daas-pulse.listeningmind.ai/llms.txt): What is rising in search for a gender and age segment right now (MCP `https://daas-pulse.listeningmind.ai/mcp`)
- [Prompt Builder](https://daas-prompt.listeningmind.ai/llms.txt): Finds what consumers ask AI and builds managed brand prompts with AI visibility (MCP `https://daas-prompt.listeningmind.ai/mcp`)
- [Smart Store Suite](https://daas-store.listeningmind.ai/llms.txt): Which Smart Store products to grow, and how to rewrite their titles and detail pages in searchers' words (MCP `https://daas-store.listeningmind.ai/mcp`)
- [Taste Finder](https://daas-taste.listeningmind.ai/llms.txt): In what sensory and emotional words do people choose this (consumer taste report from search data) (MCP `https://daas-taste.listeningmind.ai/mcp`)
- [ListeningMind Data API](https://daas.listeningmind.ai/llms.txt): the search data behind every app (MCP `https://daas.listeningmind.ai/mcp`) · [glossary](https://daas.listeningmind.ai/en/glossary) · [all apps](https://daas.listeningmind.ai/en/apps)

## Run stages
- `resolve`: Brand
- `domains`: Domains
- `sitemap`: Site map
- `extract`: Brand's own words
- `seen`: Market perception
- `synth`: Synthesis
- `done`: Done

## All tools
### estimate_run
Price and expected duration of one Brand DNA run. Free. Read only, free. Usually followed by: start_run.
`POST /api/estimate`
- `brand` (required): brand name as people know it
- `market`: market: us, jp or kr
- `deep`: also read search paths
- `competitors`: Competitor brands to measure share of search and AI answers against (otherwise picked from the search data)

### start_run
Starts a Brand DNA run: resolves the brand, finds official domains for the market, maps the site, reads purpose (L0), identity, voice, design, products and ads, reads ListeningMind search and AI-answer data, and writes the DNA with evidence grades. Takes 4-10 minutes. Spends ListeningMind Data API credits or paid model calls. Over MCP a person approves it first (you get a confirm link); in the browser the page asks the person. Cost: 500 Lima a run (launch price; list 5,000 Lima). Usually followed by: get_run_status.
`POST /api/runs`
- `brand` (required): brand name as people know it
- `market`: market: us, jp or kr
- `lang`: language of the written DNA
- `domain`: official domain or start URL if known (a path scopes a sub-brand)
- `category`: category hint
- `deep`: also read search paths (Path Finder)
- `competitors`: Competitor brands to measure share of search and AI answers against (otherwise picked from the search data)

### suggest_brands
AI input helper for a category set. Give a category name or your own brand; returns 8-10 brands people search in that category (or together with the brand) with their monthly searches and trend, plus the category as people search it. Search data first; the model only names brands from it and tops up with known rivals when the data is thin. Changes saved data in the app; no credits. Usually followed by: start_set.
`POST /api/suggest`
- `query` (required): a category name or your own brand
- `kind`: brand: find its rivals; category: find the brands in it
- `market`: market: us, jp or kr
- `lang`: language of the labels

### start_set
Analyzes 2 to 5 brands in one category the same way and shows their positions: share of search, share of AI answers, fit at each step of the customer journey, a positioning map, what each brand owns, category codes, white space and the next moves for your brand. Every brand gets a full Brand DNA measured on the same category terms and the same rival set; Brand DNAs you made in the last 30 days are reused; only your brand gets the playbook and AI skill package. Takes 15-40 minutes. Spends ListeningMind Data API credits or paid model calls. Over MCP a person approves it first (you get a confirm link); in the browser the page asks the person. Cost: 1,500 Lima a set of up to 5 brands (launch price; list 15,000 Lima). Usually followed by: get_run_status, get_run.
`POST /api/sets`
- `brands` (required): 2 to 5 brands; mark exactly one as your own
- `market`: market: us, jp or kr
- `lang`: language of the written result
- `category`: the category as people search it (from suggest_brands)

### get_run_status
Status, stage and progress of a run. Read only, free. Usually followed by: get_run.
`GET /api/runs/{run_id}/status`
- `run_id` (required): run id from start_run

### get_run
The run and, when done, its Brand DNA document. Read only, free. Usually followed by: get_guardrails, compare_dna.
`GET /api/runs/{run_id}`
- `run_id` (required): run id

### list_runs
Your runs, newest first. Read only, free.
`GET /api/runs`
- `limit`: how many

### list_dna
Your Brand DNA documents (latest version each). Read only, free.
`GET /api/dna`
- `market`: filter by market
- `category`: filter by category text

### get_dna
One Brand DNA document by id (latest or a given version). Read only, free.
`GET /api/dna/{dna_id}`
- `dna_id` (required): Brand DNA id, e.g. us-patagonia
- `version`: version number

### get_guardrails
Asset-production pack for other apps (Creative Finder, Brand Naming). People get the same rules as a downloadable Claude skill, ChatGPT GPT or Gemini gem from the report page. Read only, free.
`GET /api/dna/{dna_id}/guardrails`
- `dna_id` (required): Brand DNA id

### compare_dna
Compares Brand DNAs: brand vs brand, products, or a category (codes and white space). Uses a little model time. Changes saved data in the app; no credits.
`POST /api/compare`
- `dna_ids` (required): Brand DNA ids to compare
- `mode`: comparison mode
- `lang`: language of the reading

### delete_run
Delete one of your runs. Deletes data. A person approves it first.
`DELETE /api/runs/{run_id}`
- `run_id` (required): run id

### build_playbook
Write (or rewrite) the brand playbook and AI skills for an existing Brand DNA: constitution, audience, voice, visual rules, one playbook per format (banner, shorts, video ad, brand film, brand content, blog, PR article, social post), examples, self-check, prompts and a sonic logo. Owner only; included in every new run. Changes saved data in the app; no credits.
`POST /api/dna/{dna_id}/playbook`
- `dna_id` (required): Brand DNA id

### get_brand_brief
Start here before writing anything for the brand: a compact brief (purpose, customer words, market entry points with search volume, voice, colours, fonts, film patterns, big idea, priorities, exact rules), each fact with its evidence grade. Read only, free.
`GET /api/dna/{dna_id}/brief`
- `dna_id` (required): Brand DNA id (from list_dna or get_run)

### get_format_guide
One format's playbook with voice essentials, the customer's words, colours, the self-check and length limits. Read only, free.
`GET /api/dna/{dna_id}/format/{format}`
- `dna_id` (required): Brand DNA id (from list_dna or get_run)
- `format` (required): Content format

### review_content
Check a draft against the brand before handing it over: exact checks (avoid words, brand vocabulary, length) and judged checks (rules, voice, checklist) with a score, fixes and a rewrite. Changes saved data in the app; no credits.
`POST /api/dna/{dna_id}/review`
- `dna_id` (required): Brand DNA id (from list_dna or get_run)
- `text` (required): The draft: copy, script, article, post or prompt
- `format`: Content format, optional

### get_brand_kit
Download links: Claude skill, ChatGPT GPT, Gemini gem, everything (with the report as HTML, PDF and JSON), the raea project and rendered drafts. Read only, free.
`GET /api/dna/{dna_id}/kit`
- `dna_id` (required): Brand DNA id (from list_dna or get_run)