The internal portal over M365.
Email, documents, and chat behind a white-labeled AI assistant for 10,000 employees, each with their own permissions, provisioned by directory group.
Documents, warehouses, CRMs, and legacy systems connected through per-user authentication—files stay in place, permissions inherited live.
150+ connectors. Files stay where they live.
That is how most AI vendors connect: one service account, full scope, and a mirror of your document store in their index. It fails the security review or passes it with a scope your CISO regrets.
And the systems that matter most, the legacy system, the admin console, the vendor portal, have no API at all.
Connect as the user. Copy nothing. Reach the systems without APIs anyway.
Link. Admins configure integrations; users link their own accounts. Two separate paths; short-lived scoped tokens for both. Tenant-wide O365 consent once, no click per user.
Inherit. Permissions read from the source per request. Live Assets: the file stays in SharePoint or iManage; Athena holds a TTL-only cache and the source stays authoritative.
Read. Agents, workflows, and Studios read through the connector as the user. Enterprise search across 200 SharePoint sites respects every ACL.
Write, with approval. Typed write actions: create the Jira ticket, post to the channel, update the Salesforce field. Each is attributed and can be approval-gated. GitHub gets typed PR and comment actions plus webhooks.
Email, documents, and chat behind a white-labeled AI assistant for 10,000 employees, each with their own permissions, provisioned by directory group.
Documents stay in the DMS. Athena reads as the attorney, drafts in Word Studio, and files back with attribution.
Pipeline re-read, call context pulled, follow-ups drafted, fields updated with approval. An internal CRM built in 30 minutes when Salesforce is the wrong shape for the team.
First-pass ticket triage. Typed PR comments and webhooks. Agents file upstream issues for the libraries they wish behaved differently.
A legacy system over SFTP. An Entra admin console. A vendor portal. A governed browser session with your credentials, recorded and attributable. Slower than an API; never described as bypassing a control.
The custom connector editor: scoped API access, OpenAPI or bearer-token testing, and an agent that learns the API from the docs and writes the Python.
“This combination is a winning combination for us, and this is where we see maximum traction, which is how do you apply all the intelligence that you have within [our data platform] and not worry about how you render that output.”
“I envision Athena and [our data platform] as the combination... that's the stack for me.”
“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.
Per-user credentials; admin integrations separate from user-linked accounts.
Permissions inherited live; TTL-only cache; source stays authoritative.
Writes are typed, attributed, and can require approval.
Deploy with the platform; connectors run inside your boundary.
For systems with no API, browser work is slower than an API call and depends on the page staying roughly the same. Sessions self-heal on small changes and stop for a human on large ones.
Your data platforms, files, email, chat, CRM, ERP, and any system with an API or web interface.
Each person's own.
Athena can build one from an API specification, or use a governed browser.
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.
We will connect the system as one user, with that user's permissions, and show you the trail.