The Library is your organization's shared, owned, governed collection: context, agents, skills, AOPs, apps. Package a procedure once as a skill and every agent can load it.
Brand voice Skill distilled from meeting transcripts and merged PRs
A great session is a one-off unless you capture how it worked. Prompts get pasted into wikis. Each team re-teaches the same procedure. Behavior drifts between agents and between weeks.
Templates are the wrong fix: too rigid for real work, which is messy and inconsistent. What you need is strong, customizable primitives, and a way to package the ones that work.
Capture the procedure, not the prompt.
Capture. After a session that produced the right output, ask Athena to create a Skill. It writes the procedure, the tools it used, and the checks it applied.
Version. Skills live in a library synced to a Git repository. Admins edit centrally; changes are attributed; roll back a version if a change misbehaves.
Load. Agents pull the Skills a task needs at runtime. An agent reading a Skill automatically enables the toolkits it references—no manual configuration per agent.
Improve. Every human correction is a signal. Compound the learnings back into the Skill.
Library. Your organization's shared, owned, governed collection: context, agents, skills, AOPs, apps. Starts full with Athena's general-purpose set.
| Capability | People can | Agents can | Together |
|---|---|---|---|
| Library | Save a good chat as a skill, share it, set the owner. | Load what the job needs; suggest new entries from repeated work. | One library that people and agents both improve. |
Anything a person can do here, an agent can do with the same permissions, and both land in the same audit trail.
A global professional services firm's methodology packaged as Skills and rolled out from a global library to engagement workspaces. Sample testing, work-paper generation, prepared-by-client (PBC) intake. Edited once; live everywhere.
Our own voice is a Skill distilled from 472 meeting transcripts and roughly 2,900 merged PRs: positioning, vocabulary, the never-list, proof points. Every draft runs through it.
A procurement workflow built for one customer packaged as a generic Skill any enterprise can run weekly: watch the contract sheet, classify by status, format data, produce the three-view summary deck.
A Skill that loops learnings back into itself: produces blog posts in the company's voice with live diagrams and a diagram-redesign step.
A Skill referencing the Databricks connector and the PowerPoint Studio loads both when an agent picks it up. No configuration per agent.
“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.”
“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.”
“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.”
“I like that direction, that concept of the agent is the agent. It becomes an entity in its own right with its own ownership and its own missioning, and you get rid of the gray area and the blurry lines.”
“It was PowerPoint... there was no kind of distinction between the two. So that was killer. And I literally had a meeting on it today, and people said how great it was.”
Verbatim from customer calls. Customers anonymized.
Version-controlled; every edit attributed; rollback per version.
Central editing with runtime pull; Git as the backup and review surface.
Skills respect the same permissions as the agent loading them.
Cost and usage per Skill on the owner dashboard.
A Skill is only as good as the examples you gave it. Six good ones and it finds the seventh. Two vague ones and it finds two vague answers.
Your organization's know-how, such as a methodology or standard, captured once so every agent applies it.
Update a skill once and every agent uses the new version.
You decide who can publish to the shared library.
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.
Start from a ready-made procedure.
We will turn it into a Skill and run it again in front of you.