> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/harness/agentic-reasoning-engine/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server. # Agentic Reasoning Engine ## Docs - [What Goes Into a Turn](https://docs.moveworks.com/harness/agentic-reasoning-engine/how-the-reasoning-engine-works.md): - [The Reasoning Loop](https://docs.moveworks.com/harness/agentic-reasoning-engine/reasoning-loops.md): - [Tool Selection](https://docs.moveworks.com/harness/agentic-reasoning-engine/reasoning-loops/tool-selection.md): - [Multi-Tool Responses](https://docs.moveworks.com/harness/agentic-reasoning-engine/reasoning-loops/multi-tool-responses.md): - [Processing Tool Responses](https://docs.moveworks.com/harness/agentic-reasoning-engine/processing-tool-responses.md): - [Models](https://docs.moveworks.com/harness/agentic-reasoning-engine/models.md): - [Multilingual Support](https://docs.moveworks.com/harness/agentic-reasoning-engine/multilingual-support-assistant.md): - [Configure Multilingual Support](https://docs.moveworks.com/harness/agentic-reasoning-engine/multilingual-support-assistant/multi-lingual-support.md): - [Multilingual Support Troubleshooting](https://docs.moveworks.com/harness/agentic-reasoning-engine/multilingual-support-assistant/multilingual-support-troubleshooting.md) - [Conversation History](https://docs.moveworks.com/harness/agentic-reasoning-engine/conversation-history.md): - [Personalization](https://docs.moveworks.com/harness/agentic-reasoning-engine/personalization.md) - [Domains](https://docs.moveworks.com/harness/agentic-reasoning-engine/domains.md): - [Entity Catalog](https://docs.moveworks.com/harness/agentic-reasoning-engine/entity-catalog.md): - [Configuring Entities in Moveworks Setup](https://docs.moveworks.com/harness/agentic-reasoning-engine/entity-catalog/configuring-custom-entities.md): - [How To Guide for Entity Catalog](https://docs.moveworks.com/harness/agentic-reasoning-engine/entity-catalog/how-to-guides-1.md): - [Guardrails](https://docs.moveworks.com/harness/agentic-reasoning-engine/conversational-safeguards-assistant.md): - [Configure Moveworks Toxicity Filter](https://docs.moveworks.com/harness/agentic-reasoning-engine/conversational-safeguards-assistant/configure-moveworks-toxcity-filter.md) - [Grounding and Hallucinations](https://docs.moveworks.com/harness/agentic-reasoning-engine/grounding-and-hallucinations.md): - [AI Disclaimers](https://docs.moveworks.com/harness/agentic-reasoning-engine/ai-disclaimers.md): - [Configure Disclaimers & Labels](https://docs.moveworks.com/harness/agentic-reasoning-engine/configure-disclaimers.md) - [Display Configurations](https://docs.moveworks.com/harness/agentic-reasoning-engine/display-configurations.md): - [Steerability tools](https://docs.moveworks.com/harness/agentic-reasoning-engine/steerability-tools.md): - [Approval Queue](https://docs.moveworks.com/harness/agentic-reasoning-engine/approval-queue.md): - [Brief Me on the Agentic Reasoning Engine](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant.md): - [Brief Me: Enabling on Chat Platforms](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-configuration.md): - [Brief Me: Use Cases & Scenarios](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-use-cases-scenarios.md): - [Brief Me: Use Cases by Team](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-use-cases-by-team.md): - [Brief Me: Analytics Overview](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-analytics-overview.md): - [Brief Me: Security Overview](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-security-overview.md): - [Brief Me: Technology Overview](https://docs.moveworks.com/harness/agentic-reasoning-engine/brief-me-assistant/brief-me-technology-overview.md): - [Code Interpreter](https://docs.moveworks.com/harness/agentic-reasoning-engine/code-interpreter.md): - [Email Composer](https://docs.moveworks.com/harness/agentic-reasoning-engine/email-composer.md): - [People & Places Lookups](https://docs.moveworks.com/harness/agentic-reasoning-engine/people-places-lookups-assistant.md): - [Configure People Lookups](https://docs.moveworks.com/harness/agentic-reasoning-engine/people-places-lookups-assistant/lookup-settings.md): - [Conference Room Settings](https://docs.moveworks.com/harness/agentic-reasoning-engine/people-places-lookups-assistant/conference-room-settings.md): - [How To Guides for People and Places Lookups](https://docs.moveworks.com/harness/agentic-reasoning-engine/people-places-lookups-assistant/how-to-guides-lookups.md): - [Quick GPT](https://docs.moveworks.com/harness/agentic-reasoning-engine/quick-gpt.md): - [Text Translator](https://docs.moveworks.com/harness/agentic-reasoning-engine/text-translator.md): - [Self Knowledge](https://docs.moveworks.com/harness/agentic-reasoning-engine/self-knowledge.md): - [Smart Handoff](https://docs.moveworks.com/harness/agentic-reasoning-engine/smart-handoff-assistant.md): - [Smart Handoff Configuration Overview](https://docs.moveworks.com/harness/agentic-reasoning-engine/smart-handoff-assistant/moveworks-setup-handoff-settings.md): - [How To Guides for Handoff Plugin](https://docs.moveworks.com/harness/agentic-reasoning-engine/smart-handoff-assistant/how-to-guides-for-handoff-plugin.md): - [World Knowledge App](https://docs.moveworks.com/harness/agentic-reasoning-engine/world-knowledge-app.md) > **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/harness/agentic-reasoning-engine/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server. # The Agentic Reasoning Engine The Agentic Reasoning Engine powers your Enterprise Assistant, the main Moveworks AI Assistant. A language model reasons over the user's request and calls tools in a loop: it plans the steps toward a goal, selects and runs the next action, looks at the result, and adjusts the plan. ![](https://files.readme.io/4499478d147ace5e577af3af2594ce3e90be9600dbd0bfe78ce72805a584f976-image.png) > **Info** > > New to LLMs? Start with [LLM Fundamentals](/harness/llm-fundamentals) for how language models handle context windows and attention. ## What it is built from * **The reasoning loop.** The engine plans the most useful course of action, runs the plan step by step, and shows the user its progress, asking for confirmation when it needs to. * **Tools.** Search, workflows, API calls, code, and summarization, built in or added through Tool Studio. * **Context.** On each turn the engine reads your organization's content and terminology, the tools available to the user, the user's attributes, and the current conversation. * **Models.** Large foundation models for reasoning and planning, and smaller task-specific models for jobs like language detection, toxicity checks, and translation. * **Guardrails and governance.** Safeguards that keep interactions safe and accurate, plus visibility into what employees ask for. ## Where you shape behavior * Tool descriptions, examples, and reasoning instructions in Tools. * AI disclaimers and toxicity filter instructions in Display Configurations in Moveworks Setup. * Which user attributes the assistant uses to tailor answers, in [Personalization](/harness/agentic-reasoning-engine/personalization). * How long conversation history lasts, in [Conversation History](/harness/agentic-reasoning-engine/conversation-history). * The model version, through the Frontier, Standard, or Basic track in the [Reasoning Engine Upgrade Program](/harness/reasoning-engine-upgrade-program). The [Agentic Orchestrator](/harness/agentic-orchestrator) is the upgrade to the Reasoning Engine and comes to your Enterprise Assistant in Q1 2027. ## How it works #### [What Goes Into a Turn](/harness/agentic-reasoning-engine/how-the-reasoning-engine-works) What the engine reads before each step, and a map of the loop with links to each stage. #### [The Reasoning Loop](/harness/agentic-reasoning-engine/reasoning-loops) How the engine plans, runs, and checks its work, including Tool Selection and Multi-Tool Responses. #### [Processing Tool Responses](/harness/agentic-reasoning-engine/processing-tool-responses) What happens to a tool's output before the engine reasons over it, including size limits and variable tracking. #### [Models](/harness/agentic-reasoning-engine/models) Which models the assistant uses, how Moveworks evaluates and improves them, and why chatting with the assistant does not retrain them. #### [The Golden Rule](/tool-studio/guides/best-practices/the-golden-rule) Why attention limits matter for your tools, and how to move logic out of the LLM into code. #### [Multilingual Support](/harness/agentic-reasoning-engine/multilingual-support-assistant) How the assistant detects and responds in the user's language. ## Context management #### [Conversation History](/harness/agentic-reasoning-engine/conversation-history) What carries over between messages, how long it lasts, and how to clear it. #### [Personalization](/harness/agentic-reasoning-engine/personalization) How user attributes such as location and department tailor answers from Enterprise Search. #### [Domains](/harness/agentic-reasoning-engine/domains) How the engine understands your organization's areas. #### [Entity Catalog](/harness/agentic-reasoning-engine/entity-catalog) How the engine understands your organization's terminology. ## Guardrails [Guardrails](/harness/agentic-reasoning-engine/conversational-safeguards-assistant) covers the toxicity filter and conversational safeguards. Related pages: * [Configure Moveworks Toxicity Filter](/harness/agentic-reasoning-engine/conversational-safeguards-assistant/configure-moveworks-toxcity-filter) * [Grounding and Hallucinations](/harness/agentic-reasoning-engine/grounding-and-hallucinations) * [AI Disclaimers](/harness/agentic-reasoning-engine/ai-disclaimers) * [Steerability Tools](/harness/agentic-reasoning-engine/steerability-tools) ## Built-in skills * [Approval Queue](/harness/agentic-reasoning-engine/approval-queue) * [Brief Me](/harness/agentic-reasoning-engine/brief-me-assistant) * [Code Interpreter](/harness/agentic-reasoning-engine/code-interpreter) * [Email Composer](/harness/agentic-reasoning-engine/email-composer) * [People & Places Lookups](/harness/agentic-reasoning-engine/people-places-lookups-assistant) * [Quick GPT](/harness/agentic-reasoning-engine/quick-gpt) * [Text Translator](/harness/agentic-reasoning-engine/text-translator) * [Self Knowledge](/harness/agentic-reasoning-engine/self-knowledge) * [Smart Handoff](/harness/agentic-reasoning-engine/smart-handoff-assistant) * [World Knowledge App](/harness/agentic-reasoning-engine/world-knowledge-app) ## Related * [Reasoning Engine Upgrade Program](/harness/reasoning-engine-upgrade-program): the three upgrade tracks and the behavior changelog for each model version.