Data & Storage · Integration
ThoughtSpot
Add ThoughtSpot to your product for your customers, and give your AI agents governed access to it.
ThoughtSpot sits on top of a warehouse rather than holding data itself, which changes what an integration is actually doing. A customer models their Snowflake, BigQuery or Databricks tables into worksheets, people ask questions against that model, and the saved results become Answers and the Liveboards they are pinned to. So an embedded ThoughtSpot integration reads the metadata that says what a customer has modelled, runs a search or fetches a saved Answer, and brings the rows back into your product, while the query itself executes against the customer's own warehouse under their own compute and their own cost. Row level security defined in ThoughtSpot follows the connected identity, which means what your product can see is exactly what that person could see in the console. Credentials are held per tenant by fastn, and API changes are absorbed there.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let each customer connect their own ThoughtSpot instance so answers in your product come from the model their analysts already trust.
Read the worksheets and Liveboards a customer has actually built, so your product offers their metrics rather than a list you invented.
Fetch the rows behind a saved Answer and render them in your own interface instead of sending users to a second tool.
Respect the row level security the customer configured, so a connected user never sees data the console would have withheld.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent runs a question against a customer's own model and cites the worksheet the numbers came from.
An agent reads a Liveboard and explains which metric moved and by how much, scoped to one tenant.
An agent checks what a customer has modelled before it phrases a question, so it does not ask for a field nobody defined.
Example prompt
Ask our revenue model which regions are behind plan this quarter and show me the rows behind the answer.
Set up ThoughtSpot in 4 steps
- 01Enable the ThoughtSpot connector in your fastn dashboard.
- 02Have each customer authorise their own ThoughtSpot instance so searches run under their identity and their warehouse compute.
- 03Map the worksheets, Answers and Liveboards your product surfaces, per customer, as configuration.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the ThoughtSpot integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a ThoughtSpot integration without building it. Your customers connect their own ThoughtSpot account inside your product and work their records, datasets and fields there, with no per-customer code on your side.
- Handle the part that actually costs time: schemas differ per customer and change without notice, and volumes can be large. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a ThoughtSpot update is not your on-call problem.
- One integration serves your product and your agents. The same governed ThoughtSpot connection powers in-product features and gives AI agents scoped, audited access, so you read and write your customers' data where it already lives without wiring it twice.
Used by these teams
Compare with
Looker
Tableau
Power BIOften used alongside
Tools the same teams tend to run next to ThoughtSpot, across other categories.
Anthropic Claude
OpenAI
Hugging FaceThoughtSpot integration FAQ
How do I add a ThoughtSpot integration to my product?
Enable the ThoughtSpot connector in your fastn dashboard, then let each customer authenticate their own ThoughtSpot account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no ThoughtSpot client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own ThoughtSpot account?
Yes. Every connection is scoped to the individual customer, so each authorises their own ThoughtSpot account and only ever sees their own records, datasets and fields. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this ThoughtSpot integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent runs a question against a customer's own model and cites the worksheet the numbers came from.
Who maintains the ThoughtSpot integration?
fastn does. When ThoughtSpot changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Does the ThoughtSpot integration adapt when a customer's schema changes?
Schema and field mapping is configuration per customer, so a change on their side is a mapping update rather than a code change and a release on yours.
How are large ThoughtSpot reads handled?
Pagination and throttling are handled for you, and initial backfills are rate-limited so a large import does not exhaust a customer's API allowance.
What can I build with the ThoughtSpot integration?
A common starting point: let each customer connect their own ThoughtSpot instance so answers in your product come from the model their analysts already trust. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the ThoughtSpot integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding ThoughtSpot does not change your per-connector cost. You can start free with 3 connected accounts.
Add ThoughtSpot to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.