Python SDKs for Office files, React SDK for embedding, public API with budgets, and a connector editor—build custom tools and ship applications, included in Athena services, with full attribution and governance.
About 3,000 merged PRs a month; a PR in staging roughly every four minutes; about eight engineers.
Enterprise AI platforms come in two kinds: closed boxes you configure, or toolkits you assemble from scratch. Neither respects the fact that your team already writes Python against Office files, already ships React, and already has a CI pipeline.
Same libraries. Same patterns. Governed runtime underneath.
Import. from pptx import Presentation, from openpyxl import Workbook, from docx import Document. Same API surface as the upstream libraries; every mutation writes immediately to the live Studio.
Write. Cells, slides, paragraphs, charts, tables, citations. Collaborators see the edit as it lands. Every change attributed to the API key's owner.
Run. POST /api/v0/aop/execute-async with run_budget: {max_cost_usd, max_model_calls}. The runtime refuses the call that would exceed it. API-created sessions are titled and filterable like any other.
Ship. Host your NextJS or FastAPI app on a Computer; promote to an Application with versions, staging, and rollback. Export the repo to your GitHub whenever you like.
A finance lead built an FP&A application by talking to the agent, which wrote the code against the SDK. "I think I've built more software in Athena than everybody else except for our head of finance. Who was also not technical."
A law firm's team built a custom research and drafting assistant on the SDK in about a week, white-labeled, behind SSO, included in Athena services.
Embed Athena functions in a Databricks application with the React SDK; Databricks precomputes, Athena renders and interacts.
About 3,000 merged PRs a month from a team of about eight engineers, with agents writing the code, reviewing, resolving conflicts, and filing upstream issues. A PR in staging roughly every four minutes. This is how Athena is built.
Package agents, workflows, and applications; redeploy across workspaces from a repository. Standardized use-case packages for a global professional services firm's 100+ offices.
Paste an OpenAPI spec or a bearer token. The agent learns the API and writes the connector. Test as a user before you ship.
“So we use the SDK, and we write that in Python, and it calls Athena majority by API. The results appear in the interface itself.”
“The developer platform that Athena comes up with [...] basically unlocks the next level engineering productivity.”
“It's good to understand the capability of the platform. That how far, and how quickly you guys can get these things going [...] that has been impressive overall.”
“Lets us get a lot more out of our data than [...] We can sit on top of all of the data in [our data warehouse] as opposed to just, like, our little ingested, you know, three gigabytes semantic models. I think we have a lot of power here.”
“Gave Athena the spreadsheet, explained which column I was trying to figure out, and then ten secs it told me... exactly how the calculation was based on the other data.”
“He wrote the entire stuff. By itself. And I was there, and I was thinking, alright. If I had to write all this stuff, I mean, I would've spent days, days, days.”
“I send that to the programmer and he said, alright. I read your file. I copied the section of the code because he has the right interface, and it works. Wow. Just like magic.”
“One workspace. All different, let's say, avatars of their output data. Right? Suddenly, it's dashboard. Excel is here. PowerPoint is when it's all together. It's very impressive.”
“Use the Athena platform probably closer to the concept and how it was designed, like, with the spaces architecture where you've got a set of primitives and capabilities, and you bring together the right set of capabilities to solve a task.”
“Digital worker, it gets spun up, it gets given access to the toolkits that it needs. It gets given access to the data that it needs. Just exists for the period it needs to exist to perform the task. And then it gets torn back down again afterwards.”
Verbatim from customer calls. Customers anonymized.
Every SDK and API action attributed to the key's owner; reversible like any other edit.
Run budgets enforced at the runtime; fails closed if the ledger is unreachable.
Keys scoped per workspace; sessions filterable by origin.
Your code is yours. Export it.
The SDK surface is young. The Office SDKs track upstream closely; the React SDK and connector editor are moving fast. Expect to file issues; we read them and often fix them the same day.
Custom applications, agents embedded in your own products, and automations that call Athena from your code.
Yes. The same permissions and budgets apply to code as to people.
Yes. Export it to your own repository.
Records every change by a person or an agent, rolls back one contributor's edits without losing anyone else's, and keeps the model, instructions, and sources behind each agent action.
How the platform is deployed: Athena's managed cloud, your cloud on AWS, GCP, or Azure, on-prem, air-gapped, or GovCloud. Same platform in every option.
Build, Work, and Data on top; 150+ connectors and every surface in and out; one map of the whole platform.