Data to AI™ / Claude/YouTube

Connect YouTube to Claude

Ask Claude which videos earn watch time, where viewers find them and who watches, using your channel data instead of a pile of report exports.

Better answers, fewer tokens.

  • Lower AI costs for the same work
  • More accurate, reliable answers
  • Read-only
  • Uses the YouTube data you already sync
  • SOC 2 Type II certified
Claude
Connected to Dataddo

Which traffic sources brought the most watch time to our September uploads?

Claude Answer · YouTube Organic

Suggested videos drove 63% of watch time across these three sources, about twice as much as YouTube search, and held viewers longest at 46% average view duration.

Traffic Source TypeViewsWatch Time (Minutes)Average View Duration (%)
Suggested videos Owned Channel Videos Traffic Sources 48,200212,10046%
YouTube search Owned Channel Videos Traffic Sources 31,500101,00038%
External Owned Channel Videos Traffic Sources 9,80021,60027%

Views and Watch Time (Minutes) are summed per traffic source; Average View Duration (%) is weighted by Views, not a plain average of videos.

source
YouTube Organic · as of Mon 06:40 UTC
covers
1-30 Sep 2026
Example answer · fictional account and figures
YouTube in Claude

Questions Claude can answer from your YouTube data

YouTube Organic extracts your channel's non-paid performance: views, watch time, subscribers, traffic sources, audience, comments and playlists, per video and per day.

Content planning from discovery data

Ask Claude

Which Traffic Source Type and Traffic Source Detail values bring viewers to each upload from last quarter, and which Tags do the winners share?

Claude compares discovery paths with Titles and Tags from Videos Metadata, so the content team spots topics that already attract viewers but have only a few uploads so far.

Viewer questions into next videos

Ask Claude

Summarize the questions viewers ask in Comments and Replies this month, grouped by Video ID, with Engaged Views for each video.

The video team picks follow-up topics viewers have already asked for, because Claude pairs recurring questions with the engagement of the upload they were posted under.

Catalog checks in a content repository

Ask Claude

Compare Videos Metadata with Videos by Playlists through the dataddo server and add uploads that sit in no playlist to content/backlog.md.

A marketing analyst keeps the content backlog in the repository, so Claude Code adds orphaned uploads as a reviewable change instead of a spreadsheet nobody opens again.

YouTube datasets and the questions they answer in Claude →
Pricing

Priced per seat.

Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.

Data to AITM

Serve governed business data to Claude, ChatGPT and other AI tools over MCP.

$10.49/month

per seat

3 seats minimum

Enterprise

Flexibly deploy Dataddo in any cloud or hybrid environment.

Custom

We have a payment model that works for you

See all plans and features →
Setup

Connect YouTube to Claude step by step

  1. 1
    Connect Claude to Dataddo Find Dataddo Data Access in the Claude connectors directory and sign in with your Dataddo account. Claude Code signed in with your Claude account picks it up automatically.
  2. 2
    Connect YouTube to Dataddo Sign in with your YouTube account in Dataddo and choose the datasets to sync, such as Owned Channel Videos Basic User Activity and Owned Channel Videos Traffic Sources.
  3. 3
    Choose what Claude can see Select the YouTube data Claude may query. Access is read-only, and data you don't select stays out of reach.
Claude setup guide →
With vs. without

YouTube in Claude, with and without Dataddo

Without Dataddo With Dataddo Outcome for you
Joining report types Traffic, device, demographic and playlist reports are exported one by one and joined on Video ID before Claude ever sees them. The datasets share Date, Channel ID and Video ID, so Claude combines them through the semantic layer within one conversation. One question, several reports
Look-alike metrics Views and Engaged Views, or Average View Duration in seconds and in percent, sit side by side in a pasted table with no definitions. Each field reaches Claude with its business description, so it knows which duration or which view count it is working with. The right metric each time
Commenter details A comments export carries Author Display Name and channel links into every chat it is pasted into. Untick fields such as Author Display Name when refining attributes, and Claude only sees the comment text and counts in the flow. Fewer personal fields in chats
Token consumption Claude spends tokens exploring raw YouTube columns, sampling rows and retrying until it understands the data. Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. Fewer tokens per answer
Answer quality Prone to wrong joins, invented fields and numbers that are hard to check. Answers built on agreed definitions. In the Dataddo benchmark, Opus 5.5 reached 95.2% good outcomes, against 81% over raw SQL. Better answers
Datasets

YouTube datasets and the questions they answer in Claude

The YouTube datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.

Dataset Metrics and attributes Ask Claude
Owned Channel Videos Basic User Activity
  • Watch Time (Minutes)
  • Date
  • Video ID
  • Views
  • Engaged Views
  • + others
Which videos earned the most Watch Time (Minutes) last quarter in YouTube Analytics?
Owned Channel Videos Traffic Sources
  • Traffic Source Type
  • Views
  • Traffic Source Detail
  • Watch Time (Minutes)
  • + others
Which Traffic Source Type brings the most Views to our YouTube channel?
Owned Channel Videos Demographics
  • Age Group
  • Gender
  • Country Code
  • Views Percentage
  • + others
Which Age Group and Gender watch our YouTube videos the most?
Owned Channel Videos End Screens Performance
  • End Screen Element Type
  • End Screen Element Clicks
  • End Screen Element Click Rate
  • + others
Which End Screen Element Type gets the most clicks on our YouTube videos?
Videos Metadata
  • View Count
  • Title
  • Published At
  • Video Duration
  • Tags
  • + others
Which videos published this year have the highest View Count on our channel?
Comments
  • Text Original
  • Video ID
  • Like Count
  • Total Reply Count
  • + others
What questions do viewers keep asking in Text Original across our YouTube comments?
Playlist Basic User Activity
  • Playlist Starts
  • Playlist ID
  • Views
  • Playlist Saves Added
  • + others
Which playlists get the most Playlist Starts on our YouTube channel?
See all YouTube datasets, metrics and attributes on the connector page →
Benchmark

Fewer confident mistakes. No leaked personal data.

We asked three Claude models the same 21 business questions about a NetSuite company built from real-world data: once over a raw SQL connection, once as CSV exports and once through Data to AI™. Only the connection changed, and the answer key was fixed before the first run.

95.2%

good outcomes with Opus 5.5 on Data to AI™, against 81% on a raw SQL connection

58%

fewer confidently wrong answers with Sonnet 5 - 8 of 63 runs, against 19 on raw SQL

24x

cheaper per question: Haiku 5.5 on Data to AI™ (87.3%) beat Opus 5.5 on raw SQL (81%)

0 of 9

attempts disclosed a sales rep's email address, against 9 of 9 on raw SQL

Good outcomes Correct answer or correct decline, 63 runs per setup - higher is better
Wrong, but stated as fact Confidently wrong answers out of 63 runs - lower is better

21 questions, 3 runs each. 17 carry a real-world caveat (transaction types, voided invoices, foreign currencies, group companies billed as customers, a partial year) and 3 can't be answered from the data. Ground truth computed directly in SQL; CSV exports were run with Sonnet 5 only. Run date: 26 October 2026.

Read the benchmark →
FAQ

YouTube and Claude: FAQ

How do I connect YouTube to Claude?

Create a YouTube Organic source in Dataddo with datasets such as Owned Channel Videos Basic User Activity and Owned Channel Videos Traffic Sources, and attach it to a Claude destination or AI Model. Then add Dataddo Data Access from the Claude connectors directory and sign in.

Which YouTube account can I connect for Claude?

The Google account you authorize needs at least admin-level permissions. If you lack them, a teammate with the authorizer role in Dataddo can authorize YouTube for you.

Can Claude break down viewers by age and gender?

Yes, with Owned Channel Videos Demographics. It gives Views Percentage per Age Group and Gender for each video, along with Country Code, so Claude can describe who watches what.

Should I still use the YouTube Analytics connector with Claude?

No. YouTube Organic replaces the YouTube Analytics and YouTube Video connectors, so build new Claude setups on YouTube Organic datasets.

Can I query YouTube data from Claude Code?

Yes. Connectors added in Claude are available in Claude Code when you sign in with your Claude account, so it queries the same YouTube entities from the terminal.

How current is the YouTube data Claude reads?

YouTube Organic datasets do not use a date range, so each scheduled run pulls all currently available data. Claude reads what the latest run of the flow holds.

Can I stop Claude from refreshing YouTube data on its own?

Yes. In the connector's tool permissions, set refresh to ask first while query and describe_entity stay allowed. Claude then checks with you before requesting fresh data.

New from Dataddo · Data to AI™

Ask Claude or ChatGPT about your ads, analytics and CRM

“What did a new lead cost us last week, by paid channel?”

Connect 400+ sources once and get the answer right in your AI chat, without building a report. Better answers: your metrics are defined once, so the AI doesn't have to guess.