Moveworks

What it does

Writes code

PartlyIt writes throwaway Python inside a sandbox to compute answers over plugin data, not application source code, and only a subset of Python is available.The Code Interpreter Plugin can write code to analyze data related to a user's request and provide accurate & verifiable calculation.docs.moveworks.com/ai-assistant/capabil… ↗

Debugs and fixes

PartlyIt diagnoses misconfigurations in the agents you build in Agent Studio, not failures in your own codebase.Agent Architect helps you review your builds, resolve misconfigurations and performance gaps, and iterate until every agent is reliable, compliant,…moveworks.com/us/en/platform/ai-agent-b… ↗

Reviews code

PartlyIt reviews agent builds it helped assemble, not a diff written by another engineer.Validate your agents end-to-end and catch issues before they reach production.moveworks.com/us/en/platform/ai-agent-b… ↗

Ships it

PartlyIt deploys the AI agents built in Agent Studio, including promotion between instances; it ships no application code.A purpose-built, low-code workspace to create, configure, and deploy proactive and responsive AI agents at the speed of business, complete with…moveworks.com/us/en/platform/ai-agent-b… ↗

Done-for-you service

PartlyYou run the software yourself, but Moveworks sells Forward Deployed Engineer engagements that do the implementation and custom builds for you under a statement of work.Engage our PS team of Forward Deployed Engineers (FDE) and Engagement Managers when you need technical resources for complex deployments, or…docs.moveworks.com/ai-assistant/getting… ↗

How much it does unattended

Runs autonomously

YesAmbient agents run in the background on webhook or schedule triggers, monitoring and acting without anyone prompting them first.Deploy ambient agents that run in the background — monitoring, triaging, and acting without a prompt.moveworks.com/us/en/platform/ai-agent-b… ↗

Multi-agent

YesThe reasoning engine selects and chains multiple plugins in one conversation, and ambient agents can hand work to conversational agents on the same platform.These agentic frameworks are interoperable on the Moveworks platform, so you can build experiences that span multiple patterns.docs.moveworks.com/agent-studio/overview ↗

Agent permissions

YesPolicy validators enforce rules deterministically before an action runs, and a native approvals engine can require sequential, parallel or conditional human sign-off.Enforces rules deterministically, not through prompts. Validates policy compliance before any action executes.moveworks.com/us/en/developers ↗

Which models it runs on

Claude

NoThe published LLM Action model reference lists only OpenAI GPT models on OpenAI Direct and Azure OpenAI; no Anthropic model appears in any environment column.In Azure Government IL4 and IL5 environments, LLM Actions support only these models: gpt-4.1, gpt-4.1-mini, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-lunadocs.moveworks.com/agent-studio/actions… ↗

GPT

YesGPT models are the foundation models behind reasoning and are the only family selectable in LLM Actions, with gpt-5.4-mini as the default.Specifies the LLM model to use. Choose a model from the Model Reference for your environment. Outside IL4/IL5, the default is gpt-5.4-mini.docs.moveworks.com/agent-studio/actions… ↗

Open models

NoNo open-weight model is selectable: every model in the Model Reference is a proprietary OpenAI model served through OpenAI Direct or Azure OpenAI.Specifies the LLM model to use. See the Model Reference for available options. Defaults to gpt-5.4-minidocs.moveworks.com/agent-studio/actions… ↗

Model choice

PartlyBuilders may name a model per LLM Action from a fixed list, but the assistant's core routing is Moveworks' own gateway choosing the model, and org provider settings can narrow the list.we have built an LLM Gateway, a single egress point that dynamically routes requests from other internal Moveworks services to the best machine…docs.moveworks.com/agent-studio/agentic… ↗

Where you use it

In your editor

NoThe vendor's supported-surface list covers chat platforms and an embedded web widget only; Agent Studio's low-code IDE is a browser workspace, not an editor extension.The following surfaces / chat platforms are supported for deploying the Moveworks AI Assistant: 1. Slack 2. Microsoft Teams 3. Google Chat 4. Webex…docs.moveworks.com/ai-assistant/chat-pl… ↗

On the command line

NoNo terminal client appears in the supported surface inventory or the developer hub; building and running happens in the browser and in chat.The following surfaces / chat platforms are supported for deploying the Moveworks AI Assistant: 1. Slack 2. Microsoft Teams 3. Google Chat 4. Webex…docs.moveworks.com/ai-assistant/chat-pl… ↗

In your pipeline

PartlyIt reacts to external systems through webhook and scheduled triggers, including a documented GitHub webhook, but it does not act on pull requests as a CI participant.Webhooks Triggersdocs.moveworks.com/agent-studio/system-… ↗

In a browser

YesThere is a hosted web assistant plus an embeddable widget for intranets, ServiceNow portals, SharePoint and Google Sites.AI that works where employees do — chat, browsers, intranets, service portals, etc. and speaks their language fluently.moveworks.com ↗

Whose machine it runs on

Self-hosted

NoThe platform runs only in Moveworks' AWS tenancy; the On-Prem Agent is a connectivity component for reaching internal systems, not a self-hosted deployment of the product.AWS is Moveworks' cloud hosting provider. All customer data remains in its region and is never transferred elsewhere.moveworks.com/us/en/platform/security ↗

Open source

NoNothing in the vendor's developer material offers source code; the platform is a hosted commercial product with docs, marketplace templates and sample configurations only.AWS is Moveworks' cloud hosting provider. All customer data remains in its region and is never transferred elsewhere.moveworks.com/us/en/platform/security ↗

What it costs to run

How it meters

PartlyThe one published figure meters per user per year on a 12-month contract; moveworks.com names no unit at all and routes buyers to a custom quote.1,000-2,500 users | Price per user per year | $150.00aws.amazon.com/marketplace/pp/prodview-… ↗

Free tier

NoThere is no free plan or self-serve sign-up: every route on the site leads to a demo request or a sales conversation for a custom quote.Connect with a Moveworks expert to request a custom quote and discuss:moveworks.com/us/en/pricing ↗

API access

YesDocumented REST APIs cover events, conversations and analytics data, authenticated with bearer tokens against a per-data-centre base URL.Moveworks provides REST APIs to integrate AI-powered automation into your applications and workflows.docs.moveworks.com/api-reference/overvi… ↗

MCP server

PartlyMCP Workspace lets admins connect remote MCP servers so the assistant can call their tools, but it is limited-availability, server-level only, and local servers are unsupported.MCP Workspace is available to a limited set of customers. Moveworks is validating the experience and gathering feedback, so capabilities and limits…docs.moveworks.com/agent-studio/mcp-wor… ↗

Bring your own key

PartlyYou cannot bring your own inference for the reasoning engine, but a plugin can call an external LLM API with your own credentials held in a connector.Set up an HTTP action to call the external agent's API. Here's an example using the Anthropic API:docs.moveworks.com/agent-studio/cookboo… ↗

Buying it for a team

A company can buy it

YesIt is sold only to organisations: enterprise-wide deployment, a sales-led quote, and customer references at Fortune 500 scale.Scalable packages and pricing options for all stages of business growthmoveworks.com/us/en/pricing ↗

Seat model

PartlyThe published dimension is per user per year with a 1,000-user floor and a 2,500-user ceiling; above that band pricing reverts to a quote.1,000-2,500 users | Price per user per year | $150.00aws.amazon.com/marketplace/pp/prodview-… ↗

Admin controls

YesAdmins constrain agents with launch permissions, role-based access on each asset, connectors closed by default, and policy validators that gate every action.Provide users with defined access to specific tools and data, ensuring control, and preventing unauthorized or accidental changes.moveworks.com/us/en/platform/ai-agent-b… ↗

Audit log

YesA JSON SIEM export over SFTP records authentication, permission changes, config changes and Agent Studio actions, refreshed every three hours.Moveworks provides a JSON-based SIEM log export (via SFTP) that captures API calls, authentication events, permission changes, config changes, and…docs.moveworks.com/agent-studio/core-pl… ↗

Single sign-on

YesBoth SAML and OIDC are documented for the embedded web assistant, with named guides for Okta, Azure, OneLogin and ADFS plus a multi-SSO setup.Covers how the auth_key is leveraged in Moveworks Setup to properly identify the correct SSO configuration for a given Embedded AI Assistant…docs.moveworks.com/ai-assistant/llms.txt ↗

Not established: Pooled budget

What happens to your code

Opt out of training

YesThe vendor states customer data is never used to train its global generative models, so there is nothing for a buyer to opt out of.No customer data is used to train global generative models.moveworks.com/us/en/platform/security ↗

Data residency

YesSeven named AWS regions including EU, UK, Japan, Canada, Australia and US GovCloud, with per-data-centre API hosts that confirm the separation.Moveworks is hosted in the following AWS regions: US Commercial, EU Commercial, US GovCloud, Canada, Australia, UK, Japanmoveworks.com/us/en/platform/security ↗

Getting out

PartlyInteraction and analytics data can be pulled out through the Data API and SIEM SFTP export, but no contractual exit, deletion or unused-balance term is published.Customers can export these logs from SFTP into their internal storage systems or forward them using a SIEM/log forwarder.docs.moveworks.com/agent-studio/core-pl… ↗

Certifications

YesA long certification wall covering SOC 2 Type 2, the ISO 27001 family, ISO 42001, CSA STAR Level 2, GDPR, CCPA and FedRAMP authorisation.Deployed globally across manufacturing, healthcare, financial services, and government entities with FedRAMP® authorization.moveworks.com/us/en/platform/security ↗