Data to AI™ / Claude/Instagram Public Data
Ask Claude how rival brands post on Instagram and how their audiences respond, using public profile and post data that Dataddo refreshes on your schedule.
Better answers, fewer tokens.
Claude
How often did each competitor post in September, and whose posts drew the most likes?
@northpeak_coffee posted least but averaged the most likes per post. @harbor_roasters published almost daily, with about a third of the likes per post.
| Username | Posts | Avg Like Count | Avg Comments Count |
|---|---|---|---|
| @northpeak_coffee Posts | 9 | 4,820 | 212 |
| @harbor_roasters Posts | 27 | 1,610 | 48 |
| @bluestone_brew Posts | 14 | 2,370 | 95 |
Posts are counted by Timestamp; Like Count and Comments Count are the public totals at extraction time, averaged per post.
Instagram Public Data reads what anyone can see on a public Instagram profile you name by username, such as a competitor, a peer brand or a creator: the profile with its follower and post counts, and its posts with likes, comments and views. It is not for personal accounts.
For every tracked Username, count Posts by Timestamp for last month and average Like Count and Comments Count per post. Rank the accounts and explain the gaps.
The social media lead opens the monthly marketing review with one table that compares posting cadence and audience response across rival brands, instead of screenshots collected profile by profile.
Split the Posts of the account with the highest average Like Count by Media Type and show which format they publish most and which earns the most comments.
The content team sees which Media Type the leading competitor relies on and which one actually earns comments, then tests that format in next month's plan with a clear baseline to beat.
Use the dataddo server to pull Followers Count and Media Count from Profile for all tracked accounts and write benchmarks/instagram-competitors.csv with today's date.
A marketing analyst runs Claude Code inside the reporting repository, so each monthly snapshot is committed next to the dashboard code and diffs show who grew.
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.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Competitor tracking | Someone visits each rival profile, copies follower counts and recent likes into a spreadsheet and pastes it into the chat. | One source per tracked Username extracts Profile and Posts on schedule, and Claude reads every account from the same flows. | No profile-by-profile copying |
| Posting cadence | Counting how often a rival posts means scrolling their grid and guessing dates from thumbnails. | Posts carries the Timestamp of each post, so Claude counts posts per week or month for every account exactly. | Cadence measured, not guessed |
| Linking posts to profiles | Likes per post and follower counts sit in separate exports, so comparing response against audience size is manual. | The Id in Posts points to the Id in Profile, so Claude puts likes and comments next to Followers Count. | Response put in context |
| Token consumption | Claude spends tokens exploring raw Instagram Public Data 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 grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The Instagram Public Data 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
|
|---|---|---|
| Posts |
|
Which Media Type earns the highest average Like Count per post across the competitor accounts we track? |
| Profile |
|
How does Followers Count compare across the competitor profiles we track, ranked by Username? |
We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Create an Instagram Public Data source in Dataddo, authorized through Instagram or Meta Admin Center, and enter the Username of the public profile you want to follow, with the Posts and Profile datasets. Attach it to a Claude destination or AI Model, then connect Dataddo Data Access from the Claude connectors directory and sign in.
Any public profile you name by its Username, for example dataddo_com from instagram.com/dataddo_com. The connector is not for personal accounts. Each source covers one Username, so add one source per competitor and attach them all to Claude.
Instagram Organic gives insights for accounts you manage, such as Reach, Saves and follower demographics. Instagram Public Data covers other public profiles and only what is public: Like Count, Comments Count, View Count, captions and follower counts.
Not by default. Neither dataset uses a date range, so each run returns current totals. Add the dataddo_extraction_timestamp column and keep the scheduled runs, and Claude can then compare Followers Count between extraction dates.
Yes. Signed in with your Claude account, Claude Code loads the same Dataddo connector, so you can query Posts and Profile from the terminal and write benchmark files straight into a repository.
No. Claude queries extracted data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model and nothing is written back to Instagram.
Yes. On Team and Enterprise an Owner adds Dataddo Data Access once for the organization, and every member signs in with their own Dataddo account, so each person reaches only the data that account can see.
