Agentic Index
Rippling vs Workday (2026)
Rippling last verified ·Workday last verified
Rippling and Workday both run enterprise HR with agents, a generation apart. That verdict is the Agentic Index coverage score, graded from each vendor's own published materials.
Rippling is the modern unified HR, IT, and payroll platform with agents that provision, pay, and secure, while Workday, the incumbent for enterprise HR and finance, now governs agents through its Agent System of Record and lets Sana coordinate them. Both are sales led at scale. Choose Rippling for unified modern operations at mid market to growth scale. Choose Workday for enterprise HR and finance depth with agent governance.
This comparison is published by Agentic Index, an independent agentic AI vendor research platform. Rippling and Workday are each graded against the same 14 capability Agentic Index taxonomy, from the vendor's own public materials under the Agentic Index verification standard, alongside 1,165 researched vendors. No vendor pays for placement and no vendor has reviewed this page. How this evidence is graded
Choose Rippling if
- Unified HR, IT, and payroll on one modern platform is the operating model you want.
- Mid market to growth stage speed beats enterprise process weight.
- Agents provisioning licenses and tracking security add IT value.
Choose Workday if
- You are an enterprise standardizing on Workday for HR and finance.
- An Agent System of Record governing agents across the estate matters to IT.
- The Sana powered agent platform inside Workday fits your roadmap.
| Feature | R Rippling |
W Workday |
|---|---|---|
| Action & orchestration | ||
|
Integrations & Tool Calling Ability to connect agents to real systems through native integrations, OAuth-authenticated actions, custom tools, APIs, webhooks, or MCP-compatible tools. |
||
|
RipplingIntegrations & Tool Calling Rippling AI connects to more than 60 outside apps as plugins over MCP, among them Google Workspace, Slack, Teams, Outlook, Atlassian and GitHub. It can ask questions of them, search and summarize what they hold and, where the app supports it, take targeted actions such as sending a message or creating an issue. Admins decide in the MCP Gateway which employees can use each plugin and which of its capabilities are on, so one group can have read only use while another can create, update or send. Inside its own estate, Rippling AI manages apps connected through Rippling's identity and access management, granting access to Zoom, checking who has access to Slack and reclaiming unused licenses, and it maps a spreadsheet of bonuses, flags issues, takes approval and pays in more than 185 countries. Workflow actions run inside Rippling or out in connected tools, and Rippling Data Cloud and Pipelines bring in data from systems such as HubSpot, Zendesk and Snowflake. Sourcerippling.com/platform/plug-ins, /platform/ai and /platform/workflowsread 2026-10-24 |
||
|
WorkdayIntegrations & Tool Calling The agents autonomously complete tasks and take action on behalf of employees and managers, handling everyday requests and multistep processes. Each agent carries multiple skills, some available out of the box and others customizable, managed at a granular level. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
Workflow Orchestration Ability to sequence, branch, retry, route, and combine deterministic workflow nodes with autonomous agent steps. |
||
|
RipplingWorkflow Orchestration Workflows are a named product. A customer describes a process in plain language, Rippling AI builds the trigger, conditions, routing and actions, and the customer can adjust anything through conversation. Those four elements are authored, not hard coded, and the flow is reviewed and published as a unit. Actions land inside Rippling or out in the tools the team already uses, so a single flow spans systems. Multi step work runs end to end on real sequences. Onboarding runs across devices, apps and employee data in one place, showing who is starting, what has shipped and what access they have. A bulk payroll action maps the data, flags issues, takes approval and executes across 185 countries. License reclamation finds unused seats and stages deprovisioning. Each has distinct stages, a branch on conditions and a terminal write. Several distinct parties take part. The admin authors and approves, the agent tier plans and executes, the employee self serves, and managers and other employee types can be granted access to the data the customer chooses and the ability to build their own workflows, so flows are authored at the edge under central permission. Rippling's engineering account describes a supervisor agent coordinating read, retrieval and action agents, the internal architecture behind the product. Sourcerippling.com/platform/workflows and /platform/airead 2026-09-12 |
||
|
WorkdayWorkflow Orchestration Sana, Workday's central agent experience layer, interprets user intent and coordinates multistep workflows across Workday native agents, orchestrating specialized agents behind the scenes, with actions routed through the Agent System of Record. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
Triggers & Channel Coverage How agents wake up and where they work: schedules, webhooks, message events, CRM events, inbox events, chat, email, voice, and collaboration tools. |
||
|
RipplingTriggers & Channel Coverage Workflows trigger on anything and run anywhere. Any data in Rippling or the customer's connected apps can start a workflow, including each employee's role, location, tenure, pay, device status and app access, and Rippling Data Cloud adds signals from systems such as HubSpot and Zendesk. AI automations run repeatable work on schedules, changes to employee data, events or webhooks, and a report Rippling AI builds can be scheduled to rerun, such as a monthly list of overdue trainings. A customer describes the process in plain language and Rippling AI builds the trigger, conditions, routing and actions. People reach Rippling AI in the Rippling app, in Slack by direct message, group message or a channel mention, and in Microsoft Teams, where they can inspect payroll changes, see outstanding timesheets and start approvals. Outside assistants reach it through the Rippling MCP, and employees self serve pay, benefits and policy questions. Sourcerippling.com/platform/ai, /platform/ai/rippling-mcp and /platform/workflows; rippling.com/platform/workflowsread 2026-10-24 |
||
|
WorkdayTriggers & Channel Coverage Sana is a conversational entry point where users state what they need, and Workday says some agents work ahead of a request, such as the Payroll Agent catching issues before payday. There is no event, schedule or monitoring configuration that starts an agent without a person asking, so that autonomy is claimed agent by agent rather than set up by the customer. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
| Knowledge & context | ||
|
Knowledge Grounding & RAG Ability to ground agent behavior in company data through document ingestion, retrieval, external knowledge APIs, semantic search, or RAG layers. |
||
|
RipplingKnowledge Grounding & RAG The corpus is a standing system of record, not context assembled per run. Rippling AI works with the customer's live Rippling data and Rippling help center content out of the box, two distinct corpora, one structured and one documentary, both kept current and both queried, not pasted in. Rippling's engineering writeup puts the data model at thousands of tables and hundreds of thousands of fields. The customer can extend it by uploading additional documents to share context and improve company-specific answers for employees, an ingestion path into a store the customer curates. Retrieval is grounded, and the grounding can be checked for each answer, since numbers and names come back as clickable links to the underlying records. Rippling says its AI is built natively on HR, finance and IT data and connects dots no other tool can. It answers across HR, payroll, benefits, policy, spend, device and app access data in one query, and employees self serve personalized pay, benefits and policy explanations from the same store. Retrieval respects the permission boundary at read time, so the corpus is scoped to each requesting user, not flattened. Sourcerippling.com/platform/ai product page and FAQread 2026-09-12 |
||
|
WorkdayKnowledge Grounding & RAG The HR agent answers routine questions from company policy and Workday data, and agents work on the customer's live HR, payroll and finance records. Answers change as the policy and data change, with no retraining. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
Memory & State Persistence Ability to persist context across a run, conversation, workflow, user, team, or longer-term memory layer. |
||
|
RipplingMemory & State Persistence Only state within a run exists. A REPL keeps a runtime variable store between agent steps, but there is no agent memory across sessions. A variable store that lets one agent hand a named reference to the next inside a single execution is an implementation detail of tool calling, not a memory layer, and it does not survive the run that created it. Nothing else in the product is agent memory either. The single live model of the customer's data across thousands of tables is a database, the corpus the agents query. The employee record itself (comp, role, device status, app access) is the customer's application data, however persistent it is. Uploaded context documents are a knowledge artifact the customer maintains. Agent Identity Management creates persistent agent records with owners and permissions alongside employees and service accounts, which is identity and entitlement configuration, durable but not state the agent accumulates. There is no named memory component, no retained preference or correction the agent reapplies to later requests, no decision trace carried between sessions, no stated scope or lifetime for anything the agent holds, and no customer surface to inspect, edit, export or purge agent state separately from employee records. Rippling commits that usage data will not be used to train AI models, which says where interactions do not go and names no store where they persist. Sourcerippling.com/platform/ai product page and FAQread 2026-09-12 |
||
|
WorkdayMemory & State Persistence Sana carries a user's request through a conversation and coordinates agents within it, keeping that state only for the session. Workday says its agents learn from experience, but that learning is not a memory the customer can review. The HR and finance records agents draw on are the business record itself. There is no agent memory with a stated lifetime, or one that can be reviewed, edited, deleted or scoped by user, team or workspace. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
| Control & trust | ||
|
Human Oversight & Guardrails Approval steps, consent checkpoints, escalation rules, structured guardrails, policy constraints, and pause/resume controls. |
||
|
RipplingHuman Oversight & Guardrails The approval gate is unconditional. Any action Rippling AI proposes requires explicit human confirmation before execution, and Rippling presents this as a pillar of the product, so critical tasks never go off course. There is no tier gate, no configuration required and no carve out for low risk actions, and the hold covers every action the agent proposes. The review and approve step sits at the point of the consequential act. On a bulk payroll run the agent maps the data, flags issues, gets approval and executes, and bulk data corrections run with simple prompts and the customer's confirmation. A second gate sits one layer up, on the workflow, not the action. Rippling shows exactly what triggers a workflow, what it does and who it affects before anything goes live, and the customer reviews the reasoning, confirms the output and publishes. Agent initiated changes also go through whatever approvals the company already requires, the same as if a person had made them, so that chain is the customer's own. Admins can also enable or disable AI features entirely. Sourcerippling.com/platform/ai product page and FAQ, with /platform/workflowsread 2026-09-12 |
||
|
WorkdayHuman Oversight & Guardrails Cases that need a human go from the HR agent to the right specialist, and Workday says its agents act with appropriate human oversight and visibility into their decisions. Requests can route into existing channels, and the HR agent handles the escalation itself, so the customer does not have to build it. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
Security, Identity & Governance RBAC, SSO, auditability, encryption, least-privilege tool access, compliance posture, and data handling policy. |
||
|
RipplingSecurity, Identity & Governance Rippling holds seven certifications, with scope stated for each. SOC 1 Type 2 covers eleven control areas from information security and operations to change management and payroll processing, audited annually. SOC 2 Type 2 covers Security, Confidentiality and Availability, audited annually. SOC 3 is published openly with a download link. CSA STAR Level 2 is independent third-party validation of its security controls against the Cloud Security Alliance Cloud Controls Matrix. The others are ISO 27001, ISO 27018 for personal information, and ISO 42001, which Rippling says shows its commitment to secured and governed AI management. All are stated as held, in the present tense, with no hedge, and a trust center at trust.rippling.com carries the same list. ISO 42001 stands apart as an AI management system certification, not a general infosec one, and it is uncommon. Customer facing controls sit on the AI surface itself. Rippling AI inherits the customer's existing Rippling permissions, so every response is scoped to what the requesting user is authorized to see and employees never see data they should not. Rippling contrasts this with trusting a model to filter or redact correctly, since the boundary is enforced by the permission system, not by the model. Admins can enable or disable AI features, manage Rippling AI admin permissions and configure data permissions at the platform level. Agent Identity Management extends the same model to the agents themselves, with agent records holding assigned owners and permissions alongside employees and service accounts, so agents are known, owned, permissioned, auditable and revocable from one system. Rippling is itself an IAM and MDM vendor, so the access surface is the product. Sourcerippling.com/trust/security and /platform/ai FAQread 2026-09-12 |
||
|
WorkdaySecurity, Identity & Governance Workday holds a consolidated ISO 27001, 27017, 27018 and 27701 certificate, an ISO 42001 certificate, a SOC 3 report for Workday Enterprise Products, FedRAMP Moderate, IRAP, HIPAA and the EU Cloud Code of Conduct. On the agent layer, the Agent System of Record applies precise identity permissioning and data security uniformly to every agent, including third party agents. Sourceworkday.com/en-us/why-workday/trust/compliance.htmlread 2026-09-18 |
||
|
Observability & Auditability Traces, logs, execution histories, metrics, audit events, and debugging detail for production agent behavior. |
||
|
RipplingObservability & Auditability Customers get three surfaces, and the third matters most. Every Rippling AI answer contains clickable links to the source record and data, so numbers and names can be traced to real records. Customers can also view the underlying logic and validate results. The third is an action log. In the agent's IT use case, Rippling resolves IT issues with audit trails and handles device and access issues with built-in approvals, permissions and logging. A citation answers why this answer, while an audit trail answers what the agent did, and Rippling puts logging and audit trails on the agent's action path, not only citations on its answers. Agent Identity Management adds visibility across the estate, with agents auditable and revocable from one system and visibility into what each does, though that governs the customer's agent fleet. Rippling's engineering writeup also describes a shared, queryable trace store over agent executions in production, which is Rippling's own engineers watching their own agents, not a customer facing surface. The audit trail phrase sits in a use case card, not on a page that sets out the log, and Rippling describes no retention period, export path, field list or operator view of agent actions. Sourcerippling.com/platform/ai product page and FAQread 2026-09-12 |
||
|
WorkdayObservability & Auditability Every interaction through the Workday Agent Gateway, the secure hub for any agent using Workday data including third party agents, is managed and measured, so a customer knows exactly how its agents are working together. The Agent System of Record applies comprehensive observability uniformly across agents. It measures the agents' own behavior at the level of each interaction. Sourceworkday.com/en-us/artificial-intelligence/agent-system-of-record.htmlread 2026-09-18 |
||
|
Deployment & Data Residency Deployment modes and options, including SaaS, dedicated cloud, VPC, on-prem, hybrid, local runtime, and self-hosting. |
||
|
RipplingDeployment & Data Residency All data is held in a single region, in physically secure, US-based AWS data centers across multiple availability zones. That is one geography for all data. Multiple availability zones are a resiliency property inside one region, not a residency choice. There is no region list, customer controlled or dedicated environment, or point at which a customer chooses where data sits. Two things can read as multi region and are not. Rippling runs market and language sites for Australia, Canada (in English and French), France, Germany, Ireland, the United Kingdom and the United States, and payroll runs in more than 185 countries. Neither is residency, since a company can sell and pay people in 185 countries while holding every byte in US AWS, and Rippling says it does. A customer in the EU with a data localization requirement has no option. Rippling's security controls also include penetration testing, WAF and SDLC controls alongside seven attestations. Sourcerippling.com/trust/securityread 2026-09-12 |
||
|
WorkdayDeployment & Data Residency Running Workday on AWS lets customers choose a deployment region and deploy applications in a specific geography outside Workday operated data centers to meet data residency requirements. Core data for EU headquartered customers resides in European hosting locations in Belgium, Germany and Ireland. Sourceworkday.com/content/dam/web/en-us/documents/solution-brief/workday-aws-cloud-solution-brief.pdfread 2026-09-18 |
||
| Solution readiness | ||
|
Prebuilt Agents, Templates & Packs Ready-made workflows, packaged employees, templates, blueprints, industry solutions, and role-specific agents that reduce time-to-value. |
||
|
RipplingPrebuilt Agents, Templates & Packs Capability ships ready to use. Rippling AI answers HR, payroll and policy questions, builds reports and dashboards on headcount, hiring and pay, explains why a number moved, maps bulk pay changes, reclaims licenses and resolves IT issues, with no setup or training required. These are uses of one assistant pointed at different data, not separate agents a customer installs, removes or pays for. What a customer adopts beyond that is either a prompt or a skill. Rippling publishes a library of more than 100 prebuilt prompts from HR, finance and IT leaders, covering jobs such as onboarding audits and payroll forecasts, and lists 20 actions Rippling AI can take. Teams can turn their own repeatable tasks into AI skills and share them with other employees by role, location or any other attribute, so the reusable pieces are written by the customer's own people. Sourcerippling.com/platform/ai and rippling.com/ai-prompt-libraryread 2026-10-24 |
||
|
WorkdayPrebuilt Agents, Templates & Packs A catalog of named Sana agents is browsable on Workday's site, among them an Accounting Agent, an Admin Agent, a Payroll Agent, an HR agent and a Developer Agent, with some capabilities available out of the box and others customizable. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
| Platform extensibility | ||
|
Model Flexibility & Routing Ability to work across multiple foundation models, route tasks to different models, or let buyers bring their own providers and keys. |
||
|
RipplingModel Flexibility & Routing No model or provider is named for Rippling's own agent, and there is no picker, admin setting, per agent assignment or bring your own key path for Rippling AI itself. Rippling commits that usage data will not be used to train AI models and still identifies no provider. Rippling's AI Gateway looks like model choice and is not. It is one governed path for LLM traffic between employees, apps, agents and model providers, where admins control access to models, set budgets, enforce spend limits and log usage, with OpenAI, Anthropic and Google named as providers employees and agents call directly. An admin choosing which models their own staff may use is governance over the customer's own model use. It says nothing about which model runs Rippling AI's own retrieval, reasoning or message generation. The ISO 42001 certification for governed AI management is an attestation about process, not a second model. Rippling does not describe routing across more than one model on its side, or customer or admin control of the model Rippling AI uses. Sourcerippling.com/platform/ai FAQ, with /blog/introducing-rippling-ai-governance read through the search index and counted only as a refusalread 2026-09-12 |
||
|
WorkdayModel Flexibility & Routing No model or provider is named for Sana agents and the Agent System of Record, and Workday does not say who chooses them. Its product documentation sits behind a customer login. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
APIs, SDKs & MCP Extensibility Composability layer: stable APIs, SDKs, MCP tool consumption/serving, custom tools, and integration into internal systems. |
||
|
RipplingAPIs, SDKs & MCP Extensibility Rippling now publishes the Rippling MCP, a governed connection that lets outside agents such as Claude, ChatGPT, Cursor and Gemini use Rippling data and tools under the employee's own identity and permissions. It runs on Code Mode, a single code tool where the agent writes a short program that runs in a sandbox, which Rippling says cuts token use by up to 98% and keeps cross domain queries from timing out. Agents can work across people and org data, time off, hiring and custom objects, limited by the user's permissions and an admin granted MCP access policy, and an ask_ai tool returns one grounded, read only answer from Rippling AI without exposing the underlying records. Rippling also has a public REST API on its own production and sandbox domains, with cursor pagination, header based versioning pinned to the API token, field expansion, OpenAPI specifications to download and OAuth or API token scopes in a resource read or write form. The developer platform adds App Studio, serverless Functions, Pipelines and an App Shop partner program. Some API details come from an engineering post that predates the rebuilt documentation site at developer.rippling.com. Sourcerippling.com/platform/ai/rippling-mcp and rippling.com/blog/enterprise-grade-apisread 2026-10-24 |
||
|
WorkdayAPIs, SDKs & MCP Extensibility Workday's Developer Agent brings Workday's data, APIs and more than 50 Build skills into the tools developers already use, so they build against Workday without switching context. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
|
Testing, Debugging & Optimization Testing, debugging, scoring, retries, fallbacks, quality gates, and optimization loops for improving agent workflows before and after deployment. |
||
|
RipplingTesting, Debugging & Optimization A mature internal program of production debugging and evaluation covers Rippling's own agents, with traces, layered evals and a semi automated self healing loop that catches regressions. That is Rippling's own quality process, and the customer receives the outcome, not the harness. Rippling offers no way for a customer to run an eval, define a test set or read a result. What the customer gets is a quality check with no readable result, on three surfaces separate from the action approval gate. First, impact analysis on a change before release shows exactly what triggers a workflow, what it does and who it affects before anything goes live. Second, a validation pass runs inside execution. On a bulk payroll action the agent maps the data, flags issues, gets approval and executes, and the issue flagging step is a check on the work, separate from the consent step that follows. Third, a customer can view the underlying logic and validate results. There is no test environment, sandbox, holdout, versioning, evaluator or scored verdict about agent behavior for the AI surface. A changed workflow is described, previewed and approved, not run against a known set and measured before it reaches employees, and there is no score, pass rate or judge verdict. A sandbox does exist, for a different job. A separate non production API environment runs on its own domain, rest.ripplingsandboxapis.com, and header based API versioning lets a customer pin a version and test a newer one by changing a header. Both are real pre deployment testing surfaces for the customer's own integration code against Rippling's API, not for anything the agent does. Rippling does not say that Rippling AI, its workflows or its agents run in the sandbox, so it tests the caller's change, not the agent's behavior. Plan versus actual reporting measures the customer's payroll operation, not the agent. Sourcerippling.com/platform/workflows and /platform/ai, with /blog/enterprise-grade-apis for the sandbox refusalread 2026-09-12 |
||
|
WorkdayTesting, Debugging & Optimization The Agent System of Record gives real time insight into how agents perform in the workforce so leaders can understand and optimize them. There is no way to test workflows with fixtures, mocks or datasets before production, and no pre release evaluation, scored test cases or controlled optimization loop. Sourceworkday.com/en-us/artificial-intelligence/agent-system-of-record.htmlread 2026-09-18 |
||
| Specialist automation | ||
|
Browser & Computer Use Browser, desktop, or remote/local computer control for workflows that cannot be handled through stable APIs alone. |
||
|
RipplingBrowser & Computer Use Rippling's AI acts through data and integrations, not through a screen. It operates on data and flows inside Rippling and, where it reaches outward, uses the features of the integration, and it cannot go beyond what the integration supports. That is an API mediated, non visual action path, so it does not depend on interface elements that can change. There is no hosted or local browser, desktop session, remote or local computer control, RPA or recorder. Device management comes closest. Rippling ships MDM. It provisions and manages employee devices, stages deprovisioning, reclaims licenses, and instantly disables departing employees' devices, apps and access rights with Rippling's IAM and MDM products. Remote control of endpoints can look like computer use, but MDM acts through a managed agent and administrative APIs, not by operating a visual interface, and it is device administration, not the AI agent driving a machine. Sourcerippling.com/platform/ai FAQ and /trust/securityread 2026-09-12 |
||
|
WorkdayBrowser & Computer Use The agents act on Workday's own HR, payroll and finance data through skills and Workday's APIs, and third party agents reach Workday through the Agent Gateway. No agent operates a browser or desktop interface. Sourceworkday.com/en-us/artificial-intelligence/ai-agents.htmlread 2026-09-18 |
||
Pricing snapshot
Sourced from the Index pricing dataset · open each vendor's profile for full detail.
| Pricing | R Rippling |
W Workday |
|---|---|---|
|
Entry price Lowest public entry point |
From $8 per employee a month, with a monthly base fee. Every other module is quoted. | Contact sales |
|
Pricing confidence How public the numbers are |
Public, partial | Contact only |
|
Billing Primary billing axis |
Per employee per month for most products, module by module, on top of the required core platform. Some products carry or include a monthly base fee. | A flat enterprise subscription. |
|
Variable cost Workload / overage exposure |
Medium variable cost | Medium variable cost |
|
Free tier / trial Try before you buy |
No free tier
|
No free tier
|
|
Buying motion Self-serve vs sales call |
Mixed | Sales call |
|
Pricing verified When this pricing was last checked |
Product updates
Newest first, each linked to its source.
Rippling
-
· Agent capability
Rippling relaunched Automated Compliance with multi framework support (SOC 2, ISO 27001 and HIPAA today), AI help setting up templated or custom frameworks or importing an existing program, and evidence collection from connected third party systems as well as Rippling's own HR and IT tools.
Source -
· Security / enterprise
Rippling launched a new AI governance product and MCP gateway to manage agentic tool access.
Source -
· Observability / auditability
Rippling launched the AI Spend Console, a new tool designed to help companies track and control artificial intelligence token costs.
Source
Workday
-
· MCP / tool calling / API
Workday made its Trusted Agent Platform headless, with Agent-Ready Tools, its Model Context Protocol tools, now generally available so any MCP capable agent can read Workday data and take actions under Workday's permissions, approvals and audit trails.
Source -
· Security / enterprise
Workday Adaptive Planning has achieved FedRAMP Authorization at the Moderate Impact Level.
Source
Workday bought Sana in September 2025.
More comparisons with Rippling or Workday
Other matchups in enterprise operations agents
Not the pairing you were after? These compare a different set of enterprise operations agents on the same 14 capabilities.