How to Use the Looker Studio Connector
The LLM Pulse Looker Studio connector lets you visualize your AI visibility data inside Looker Studio (formerly Google Data Studio). Build live dashboards for mentions, citations, visibility, sentiment, and competitor benchmarks, then share them with your team or clients without giving them an LLM Pulse login.
With the Looker Studio connector, you can:
- Build live AI visibility dashboards in Looker Studio, refreshed from your LLM Pulse data
- Choose between four report types: Timeseries, Prompt performance, Share of Voice, and Top Sources
- Blend AI visibility metrics with your other marketing data sources
- Share client or stakeholder dashboards without giving them an LLM Pulse login
- Start from a ready-made template instead of building from scratch
Before you start
You need two things:
- A Scale plan or above. The connector authenticates with an API key, which is available on Scale and Enterprise plans.
- An LLM Pulse API key. Open the user menu in the bottom left of the app, go to API Keys, and create one if you haven't already. Keys start with
llmpulse_. Keep it private: anyone with the key can read your project data.
Quick start
You have three ways to get going. Most people start with the ready-made template.
- Ready-made template (fastest): Clone our pre-built dashboard, then point it at your data. Open the template
- Connector (build from scratch): Add the data source and design your own report. Add the connector
- Video walkthrough: Prefer to follow along? Watch the setup video
You can also reach all three links from Integrations in the LLM Pulse sidebar.
Set up the connector step by step
The connector uses a stepped setup: each step unlocks the next once it has the information it needs.
1. Add the data source
Open the connector link and authorize it with your Google account if Looker Studio asks.
2. Enter your API key
Paste your llmpulse_ API key into the first field. The connector validates the key and loads your projects. If you see "Enter API key above to load projects", the key is missing or invalid: double-check it and wait a moment for the fields to reload.
3. Select your project
Pick the project you want to visualize from the dropdown. The connector then loads that project's competitors, tags, prompts, models, and locales.
4. Pick a report type
The Report Type setting decides what each row of the data source represents:
- Timeseries (default): metrics per brand and competitor over time. This is the classic connector behavior and what the template uses.
- Prompt performance: one row per prompt, with its ID, text, classification (brand focus, prompt type, country, language, tags) and aggregated metrics. Optionally break rows down per AI model.
- Share of Voice: SoV percentage per brand and competitor over time.
- Top Sources: the domains cited in AI answers, ranked by how many responses cite them.
Each report type exposes its own set of fields. To combine several types in one report, add the connector once per report type.
5. Choose your metrics
For the Timeseries report type, tick the metrics you want to pull. You can mix and match:
- Core: Mentions, Citations, Mention Rate (visibility), Average Position, AI Visibility Score, Responses, Citation Rate. Citations and Citation Rate include visible citations and background source references. Average Position uses visible citations only.
- Sentiment: Very Positive, Positive, Neutral, Negative, and Very Negative percentages, plus Net Sentiment Score
If you skip this step, Looker Studio still works: the connector serves whichever fields your charts request.
6. Add filters and pick a date range (optional)
Narrow the data with any combination of:
- Competitors: Choose specific competitors to benchmark against. Leave this empty to include all of them automatically (see the note below). Applies to Timeseries and Share of Voice.
- Tag, Prompt, AI Model, Country, Language: Single-select filters to focus on a slice of your data. The prompt dropdown shows each prompt as "#id - text" so you can always tell prompts apart.
- Brand Focus: Limit to brand, competitor-brand, or non-brand prompts. Use non-brand for fair brand-vs-competitor comparisons, matching the in-app Overview default.
- Prompt Type: Limit to informational, navigational, commercial, or transactional prompts.
- Domains and Domain search: Top Sources only. Restrict the domain list or search within it.
- Date range: Last 7, 30, 90, 180, or 365 days, All time, or Follow report date range (uses the date range control of your Looker Studio report).
- Granularity: Daily, weekly, or monthly.
7. Connect
Click Connect in the top right. Your data source is ready, and you can drop the fields into any chart or table.
Use the ready-made template
If you'd rather not build from scratch:
- Open the template.
- Click Use my own data (or Make a copy) in the top right.
- When prompted, add the LLM Pulse connector and authenticate with your API key.
- Select your project, and the charts repopulate with your data.
The template ships with the essential AI visibility charts already built, so you get a working dashboard in a few clicks.
Available fields
Timeseries
| Field | Type | Description |
|---|---|---|
| Date | Dimension | The date of the data point |
| Actor Type | Dimension | "project" (your brand) or "competitor" |
| Actor Name | Dimension | Name of the brand or competitor |
| Actor Domain | Dimension | Domain of the brand or competitor |
| Actor ID | Dimension | Internal ID of the project or competitor |
| Mentions | Metric | AI responses that mention your brand |
| Citations | Metric | AI responses that cite your brand's URL |
| Mention Rate | Metric | Share of queries where your brand appears |
| Average Position | Metric | Average ranking position when mentioned (lower is better) |
| AI Visibility Score | Metric | Position-weighted visibility (higher is better) |
| Responses | Metric | Total prompt executions (queries sent to the AI models) |
| Citation Rate | Metric | Share of responses that cite the actor |
| Sentiment (5 levels) | Metric | Share of responses at each level, from very positive to very negative |
| Net Sentiment Score | Metric | Overall sentiment balance, from -100 to 100 |
Prompt performance
| Field | Type | Description |
|---|---|---|
| Prompt ID | Dimension | Internal ID of the prompt |
| Prompt | Dimension | The prompt text |
| Brand Focus | Dimension | brand, brandother, or nonbrand |
| Prompt Type | Dimension | informational, navigational, commercial, or transactional |
| Prompt Country | Dimension | Country the prompt runs in |
| Prompt Language | Dimension | Language the prompt runs in |
| Prompt Tags | Dimension | Tag names separated by "; " |
| AI Model | Dimension | Only populated with "Break down by model" enabled |
| Responses | Metric | Executions of the prompt in the period |
| Mentions | Metric | Responses mentioning your brand |
| Citations | Metric | Responses citing your brand |
| Visibility | Metric | Share of the prompt's responses mentioning your brand |
| Citation Rate | Metric | Share of the prompt's responses citing your brand |
| Average Mention Position | Metric | Average position of your brand's mention |
| Average Position | Metric | Average citation position |
Share of Voice
| Field | Type | Description |
|---|---|---|
| Date | Dimension | The date of the data point |
| Actor Type / Name / Domain / ID | Dimension | Same actor dimensions as Timeseries |
| Share of Voice | Metric | The actor's share of all mentions in the period |
Top Sources
| Field | Type | Description |
|---|---|---|
| Domain | Dimension | The cited domain |
| Responses Citing Domain | Metric | Distinct AI responses citing the domain |
| Domain Visibility | Metric | Share of all responses citing the domain |
Good to know
A few behaviors that trip people up:
- Percentages use a 0 to 1 scale. Looker Studio expects percentage fields between 0 and 1, so a Mention Rate of 45% appears as
0.45. This is correct: Looker Studio adds the % sign automatically in charts. It is the same value you would see in the REST API (45), just on a different scale. - No competitors selected means all competitors. If you leave the competitor filter empty, the connector includes every competitor in the project alongside your brand. Select specific competitors to narrow the comparison. Your own project data is always included.
- Gaps in charts are normal. LLM Pulse runs prompts on a weekly schedule (Mondays by default), so days without executions show no data. If a daily chart looks sparse, switch to weekly granularity.
Change your configuration later
To switch projects, add filters, or adjust the date range after setup:
- In Looker Studio, go to Resource → Manage added data sources.
- Click Edit on the LLM Pulse data source.
- Update the configuration.
- Click Reconnect to apply.
Every chart using that data source updates automatically.
Troubleshooting
"Unable to fetch data"
Check that your API key is active and starts with llmpulse_, that the selected project still exists, and that your Scale (or higher) plan is current.
No data in the charts
Extend the date range to 90 or 180 days, switch to weekly granularity if your prompts run weekly, make sure at least one metric is selected, and remove restrictive model, country, or language filters.
Data looks out of date
Looker Studio caches results. Use Refresh data in the report or data source. Remember that the underlying data only changes after each weekly execution cycle.
A competitor shows no data
They may have no mentions for your selected date range or filters. Confirm the competitor exists under Preferences → Competitors in the LLM Pulse sidebar.
Frequently asked questions
Can I blend this with Google Analytics or Search Console?
Yes. Use Looker Studio's data blending and join on the Date field to combine LLM Pulse data with any other source.
Can I build calculated fields?
Yes. Create custom calculated fields in Looker Studio from any of the metrics above, for example your own ratios or combined scores.
Can I add more than one LLM Pulse data source to a report?
Yes. Add the connector multiple times with different projects or filters and use them together in the same report.
Does Looker Studio's own date range control work?
Yes. Set the connector's date range to Follow report date range and the connector fetches exactly the window selected in your report. With any other setting, the connector pulls its configured window (7 to 365 days, or All time) and the report control only filters what was fetched.
Can I use this on a free or Starter plan?
No. The connector needs an API key, which is available on Scale and Enterprise plans.