Sana
Also known as: Sana AI, Sana Labs, Sana Agents, Workday Sana
Enterprise AI knowledge assistant and no code agent platform grounded in company data. Connects 100+ apps with permission aware retrieval, model choice, and citations. Now part of Workday.
Sana is an enterprise AI platform that turns a company's scattered knowledge into a working assistant and a set of custom agents. It is organized around five things the platform does: find across every connected system, analyze, create content in any format, automate multi-step processes, and take action in the tools a team already uses.
The foundation is enterprise search over the customer's own material. Sana connects more than a hundred applications (Google Drive, SharePoint, Confluence, Jira, ServiceNow, Salesforce, Slack, Teams, Dropbox and Workday among them), indexes what it finds, and searches it semantically instead of by keyword, so a question phrased loosely still lands.
It reads documents, spreadsheets, presentations and video, transcribes and stores meetings automatically so the corpus grows without anyone filing anything, and returns answers with citations that deep-link back to the original document, meeting or record. Retrieval is permission-aware: the assistant only surfaces material the person asking is already entitled to see. Web search can be folded in, or switched off so answers draw on internal content alone.
On top of that, teams build assistants without writing code. Each one is scoped to particular sources, given its own web-access setting, and pointed at a job, such as preparing for calls and updating the CRM, answering RFPs, assigning support tickets, drafting contracts or running deal analysis. Pre-designed tasks and prompt templates give non-technical staff a starting point, and the number of assistants is unlimited even on the free tier.
Model choice sits with the customer. Sana is model agnostic and names Azure, Anthropic, Cohere, OpenAI and self hosted models as options, with OpenAI and Claude selectable on the Team tier and a wider range on Enterprise. Security covers SAML single sign-on, SCIM provisioning, custom user roles, flexible groups, advanced permissions, domain verification, audit logging and regional deploys, with ISO 27001 certification and SOC 2. Each customer's data sits in a single tenant architecture, and Sana can also be deployed on the customer's own cloud infrastructure. Sana does not train models on customer data.
Sana's pricing page lists one plan, Enterprise, at custom pricing, with unlimited members and documents, enterprise integrations, SAML SSO and SCIM, an extended model range, an analytics dashboard and an MCP client for building your own integrations.
A free account is still offered, and the help center describes a Team tier for up to 50 members that a workspace owner buys from inside the product, with no published price. Sana Labs also sells a separate product, Sana Learn, an AI-native learning platform.
Sana was acquired by Workday in September 2025 and continues to sell under its own name, and since October 2026 it is also the Workday Home inside Workday, where employees ask in plain language and Sana runs Workday's agents.
From our comparison video
Glean vs Sana: An Independent Platform, or the New Workday Home?
Our 3 minute video puts Sana side by side with Glean. It covers what each one does and how each is priced, then when to choose which.
Recorded in October 2026. The profile here is live and updates as research is verified.
Vendor details
Canonical URL
https://sana.ai
Category
Enterprise operations agent
Company status
acquired
Use cases & customers
In practice
A new sales rep needs to prep for a call but the answers are buried across the CRM, past decks, and old meeting recordings. They ask Sana and get a cited brief in seconds.
An operations team builds a no code agent that reads incoming vendor contracts, extracts the key terms, updates the system of record, and posts a summary to Slack, where a person can check it against the cited sources.
A compliance lead worries staff will surface data they should not see. Because Sana mirrors each source system's permissions, every employee only gets answers drawn from documents they are already cleared to open.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
9.0 / 14 capabilities · 64%
| Integrations & Tool Calling | Full |
|---|---|
|
Sana writes into outside systems and connects to a large, named catalog. Act, one of its five headline capabilities, means "take instant actions across your tools". Its team pages promise "AI that helps you prep for calls, answers your RFPs, and updates your CRM", and "AI that assigns tickets, answers product questions, and analyzes all your support calls". Updating a CRM record and assigning a ticket are authenticated writes into systems Sana does not own. "Sana connects with 100+ applications and unifies your company's data securely", among them Google Meet, Google Drive, Google Calendar, Dropbox, Confluence, Jira, ServiceNow, Salesforce, Microsoft Teams, SharePoint, Workday and Slack, with a full list on its own integrations page. Meeting capture spans Zoom, Teams and Google Meet on free and paid tiers. The custom route is open, since "Enterprise customers can also build custom integrations to Sana AI", with an "MCP client for building your own integrations" at the Enterprise tier, so the customer is not confined to the shipped connector list. Sourcesanalabs.com/products/sana integrations section and sanalabs.com/agent-pricingread 2026-09-12 |
|
| Workflow Orchestration | Full |
|
Automate, the first of the platform's five verbs (Automate, Create, Analyze, Act, Find), means "run complex, multi-step processes", and Sana pitches "AI agents that collaborate, automate, and think alongside your teams". An agent finds across connected apps, analyzes, generates content in any format, turns data into live dashboards, then takes action in outside tools. The examples are whole workflows, not single calls, such as a valuation memo that took a CFO almost a week finished in three or four hours, RFP responses, deal analysis and portfolio reviews, and prospecting through due diligence to investor communications. Assistants are built without code and scoped separately, so a firm runs several agents built for their purpose, and unlimited assistants on the free tier show the runtime hosts many instances. Sana names no runtime or BPMN. Sourcesanalabs.com/products/sanaread 2026-09-12 |
|
| Knowledge Grounding & RAG | Full |
|
Enterprise search over the customer's own content is a named product, a persistent, semantic index that respects permissions and cites its sources. Enterprise Search has its own capability page, and the Find capability covers "all the latest company docs and data". Content from 100+ connected applications is "indexed and stored in a cloud instance", with document quotas per tier (10,000 per integration on Team and unlimited on Enterprise), a retrieval index with capacity limits, not context assembled per run. Search is semantic, since "Sana Agents uses semantic search to understand concepts, not just keywords, making it easier to find what you need", even when a question is loosely phrased. It is multimodal, covering documents, structured files and video with more types "added continuously", current by design ("the platform always prioritizes the most recent and relevant information in your knowledge archive"), and it checks permissions at retrieval time, not at display time. Answers return citations that deep link back to the original document, meeting or record, and the corpus grows without manual capture because meetings are transcribed and stored automatically. Web search sits alongside it. The Search web toggle extends reach to the public web, and with it off the agent returns only internal content, so the internal index stands on its own. Sourcesanalabs.com/products/sana, sanalabs.com/agent-pricing, support.sana.ai/en/articles/148586-sana-agents-101 and support.sana.ai/en/articles/157324read 2026-10-24 |
|
| Human Oversight & Guardrails | Partial |
|
Administrators and users bound each assistant's scope before it runs, and nothing checks the agent during a run. Search web is a toggle. With it off, "searches will return only internal company content", and administrators can enable or disable web browsing for any assistant they create. Select sources lets a user "choose exactly where Sana Agents looks for answers", narrowing the corpus per question. Retrieval is bounded by permissions by construction, since "Sana Agents only shares documents or meeting notes that have been shared with you or placed in public folders". Every answer can be checked against deep linked citations. There is no approval queue, preview before commit, confirmation step, policy engine or calibration of risk for each action. That matters because the Act capability promises to "take instant actions across your tools", updating CRMs and assigning tickets, and nothing sits between the agent's decision and that write. Oversight is set at configuration time and verified after the fact, never during. Sourcesupport.sana.ai/en/articles/148586-sana-agents-101 and sanalabs.com/agent-pricingread 2026-09-12 |
|
| Security, Identity & Governance | Full |
|
Customers get a clear access surface of their own alongside the certifications. The security strip lists SAML single sign on, user provisioning, custom user roles, flexible groups, advanced permissions and domain verification. The enterprise entitlement is "domain verification, SAML-based SSO, and SCIM", and SSO setup guides cover Okta, Microsoft Entra, OneLogin, JumpCloud, Google Workspace, Auth0 and Salesforce, alongside a SCIM configuration guide. Identity federation, automated provisioning and a named role and group model are all aimed at the customer's own organization. The same strip shows SOC 2 Type 2 and ISO 27001. The pricing FAQ calls Sana Agents "SOC2 and ISO 27001 certified", while the AI agents page lists SOC 2 Type 1 compliance, so the SOC 2 report type differs between Sana's own pages. ISO 27001 is stated as certified on each. Retrieval also mirrors source permissions, so it inherits the entitlements of source systems instead of flattening them. Sourcesanalabs.com/products/sana security section, sanalabs.com/agent-pricing, sanalabs.com/products/sana/ai-agents and help.sana.ai/en/collections/271878-security-and-integrationsread 2026-10-24 |
|
| Observability & Auditability | Partial |
|
Visibility surfaces exist, but none is a record of agent behavior. Audit logging appears as a badge in the security strip, with no text about scope, retention, export or what is captured. The Enterprise tier includes an "analytics dashboard to measure impact". History logs a user's own activities, such as searches, files accessed and content changes. Every answer carries deep linked citations back to the source document, meeting or record. None of these reconstructs why the agent acted. History is a user's own activity log, not an administrator's record of agent behavior, the analytics dashboard measures adoption and impact, citations reconstruct the answer, not the agent, and the audit logging badge comes with no detail. Nothing lets a customer answer which agent updated which CRM record, when and under whose authority. Sourcesanalabs.com/products/sana and support.sana.ai/en/articles/148586-sana-agents-101read 2026-09-12 |
|
| Memory & State Persistence | Not documented |
|
Between runs, what persists is the corpus and a user activity log, not agent memory. Stored meetings, conversation history and indexed knowledge are the application's data model, and stored transcripts and indexed documents are retrieval content. History "keeps a log of your activities", such as searches, files accessed and content changes, so a user can revisit past work and track progress. That is a record of what the person did, not state the agent carries between runs. There is no memory scope for each user distinct from the workspace, no published lifetime, no expiry or purge path for memory as opposed to the account, and no surface to read or write it. The feedback function that helps "Sana Agents learn and improve" describes learning absorbed into the product, not a memory a customer can govern, and Sana says separately that it does "not train any language models on your data". Sourcesanalabs.com/products/sana and support.sana.ai/en/articles/148586-sana-agents-101read 2026-09-12 |
|
| Deployment & Data Residency | Full |
|
Customers can run Sana in their own cloud. Sana describes itself as a SaaS solution with managed hosting by default that "can be deployed on your cloud infrastructure", and it isolates each customer with a single tenant architecture, so no databases are shared between customers. Enterprise organizations can also get their own single tenant deployment, and a Regional deploys badge sits in the product page's security strip. Sana publishes no region list and no deployment guide for the customer cloud option, and it describes no on premises or air gapped mode. Enterprise partnership services add a dedicated deployment lead, implementation support, tailored onboarding and a change management model. Sourcesanalabs.com/products/sana/security, sanalabs.com/agent-pricing and sanalabs.com/products/sanaread 2026-10-24 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
A browsable templates surface and unlimited assistants come even on the free tier. Tasks are "pre-designed frameworks that help you quickly create and manage AI-driven content", which customers explore "to save time, maintain consistency, and boost productivity". Designed in advance, browsable and selected from a gallery, each does work when chosen. The help center's tier guide gives the Free tier "unlimited agents and prompt templates". Tasks are independent frameworks for unrelated content jobs, and none depends on another. Sana publishes no count of available tasks and has no agent template marketplace with third party contributions, so the surface exists but its size is unknown. Workday's own HR, finance and IT agents belong to the acquirer and are not part of Sana's catalog. Sourcesupport.sana.ai/en/articles/148586-sana-agents-101 and support.sana.ai/en/articles/157324read 2026-10-24 |
|
| Triggers & Channel Coverage | Partial |
|
People reach the agent across many channels, but work starts without a person asking in only one way. Channel coverage is broad, with the web workspace, an iOS app Sana calls "a polymath in your pocket", Slack (a customer quote describes asking Sana in Slack for someone's actions from the last meeting), Microsoft Teams, and meeting surfaces across Zoom, Teams and Google Meet on every tier. Email is reachable through the Gmail and Outlook integrations. Triggers are thinner. Meetings arriving on a connected calendar do make the agent act unasked, since "Sana AI transcribes, summarizes, and stores your meetings so you're always prepared", and it joins sessions on its own. Integration syncs pull new documents in continuously, but they feed the index and start no run. There are no scheduled runs, cron, webhook, inbound work queue or monitoring mode that starts an agent. Sourcesanalabs.com/products/sana and sanalabs.com/agent-pricingread 2026-09-12 |
|
| Model Flexibility & Routing | Full |
|
Customers choose and switch models. A model agnostic section says "Only use the AI models that work best for you. With Sana, you can choose and switch between leading models as you need." The AI agents page names the options as Azure, Anthropic, Cohere, OpenAI and self hosted models, beside the line "Choose the best model for the task and optimize performance continuously." The help center's tier guide puts OpenAI and Claude model selection on the Team tier and additional models on Enterprise, and the Enterprise plan lists an extended range of LLMs. Assistants are configured per instance, and administrators can enable or disable web browsing for any assistant they create. Sana uses third party providers under enterprise security arrangements and, whenever possible, a zero day retention policy. Sana does not say how a model is picked for each step. Sourcesanalabs.com/products/sana, sanalabs.com/products/sana/ai-agents and support.sana.ai/en/articles/157324read 2026-10-24 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
Extension mostly runs outward, with Sana calling what the customer builds. The Enterprise plan includes an "MCP client for building your own integrations", and "Enterprise customers can also build custom integrations to Sana Agents". An MCP client means Sana consumes servers the customer stands up. The AI agents page and the help center's tier guide also list API access on Enterprise ("API access for building your own integrations", "Custom integrations & API access"), but Sana publishes no REST or GraphQL API reference for Sana Agents, SDK, developer portal, webhook or A2A card, so what an outside system can call is not described. A REST API exists for Sana Learn, Sana Labs' separate learning product, on a different help center, and does not cover Sana Agents. Sourcesanalabs.com/agent-pricing, sanalabs.com/products/sana/ai-agents and support.sana.ai/en/articles/157324read 2026-10-24 |
|
| Testing, Debugging & Optimization | Not documented |
|
Customers have no way to evaluate a change. There is no sandbox or dry run to test an assistant before it acts on live data, no evaluation harness, no scored test cases, no regression check when a prompt template or assistant scope is edited, and no A/B comparison of configurations. That matters here because customers build their own agents in Sana, creating unlimited assistants with no coding, scoping each one's sources and web access, and letting them "take instant actions across your tools". With no test surface, the first run of a new assistant is the production run. The Enterprise "analytics dashboard to measure impact" is adoption reporting, the feedback function is a signal feeding Sana, not a harness the customer runs, and deep linked citations let a person verify one answer by hand, which checks an output, not a change. The enterprise surface is gated behind sales. Sourcesanalabs.com/products/sana and support.sana.ai/en/articles/148586-sana-agents-101read 2026-09-12 |
|
| Browser & Computer Use | Not documented |
|
Connectors, not screens, carry the work to outside systems, so there is no browser or computer control. There is no hosted or local browser the agent drives, desktop session, or remote or local computer control. The architecture is 100+ named application connectors authenticated with OAuth, plus an MCP client for anything not covered. The word browsing appears prominently, but it means retrieval. "Search web extends your reach by integrating internet search results directly into Sana Agents", and administrators can enable or disable web browsing per assistant. That folds public web results into the answer alongside internal content, and nothing navigates, clicks, fills a form or keeps a session on the customer's behalf. The iOS and web apps are Sana's own clients. Sourcesanalabs.com/products/sana and support.sana.ai/en/articles/148586-sana-agents-101read 2026-09-12 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Sana is now the Workday Home, an agentic experience that brings tasks, decisions, meetings and agent activity into one view. Employees ask in natural language and Sana orchestrates Workday agents to finish the work, such as approving an expense, processing a leave request or resetting a password, generating forms, calendars and approval cards as needed. The new Home is available now, and business administrators choose when to turn it on and whether to make it the default.
Bears on: Workflow orchestration
View sourceWorkday announced the general availability of Workday Learning powered by Sana, integrating Sana's AI learning technology with Workday's Human Capital Management platform. The launch introduces a personal AI tutor that coaches learners through concepts in real time, alongside AI authoring tools that convert static files like PDFs and presentations into interactive courses. This Sana-powered version is now the default learning offering for new Workday customers.
Bears on: Integrations
View sourcePricing
Free tier; paid plans not published
per user / month
Sales call required
Mixed (some tiers require a call)
Free / trial
Free tier: up to 5 members, 10 meetings and 20 chat messages per user a month
Lowest paid plan
Not published
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Abacum — FP&A platform for growing companies whose AI Modeler builds, edits…
- Adopt AI — Finance agents that categorize, reconcile and close the books inside…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
Alternatives to Sana
The closest documented capability profiles to Sana among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Kinaxis10.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- Uniphore9.5 / 14Adds documented Testing, Debugging & Optimization
- Eightfold AI9.0 / 14Adds documented Memory & State Persistence
- Ema11.0 / 14Adds documented Memory & State Persistence and Testing, Debugging & Optimization
- Findem7.0 / 14A lighter documented profile than Sana
- FurtherAI8.0 / 14Fuller documented coverage on Human Oversight & Guardrails
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded