> This page is for Harness. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/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.