# Iron Gorilla Help Center Customer and administrator help for setting up, operating, and troubleshooting Iron Gorilla. ## Categories ### Getting Started Core concepts and first steps for new Iron Gorilla workspaces. - [What Iron Gorilla does](https://help.irongorilla.ai/articles/what-iron-gorilla-does) - A plain-language overview of runtime governance and the parts of the platform. - [Choose Business or Studio mode](https://help.irongorilla.ai/articles/choose-business-or-studio-mode) - Pick the level of agent detail that fits the work you are doing. - [Understand plan limits and upgrades](https://help.irongorilla.ai/articles/understand-plan-limits-and-upgrades) - See why an action is limited and who can change the organization plan. ### Organization And Users Workspace setup, users, roles, and access boundaries. - [Set up your organization](https://help.irongorilla.ai/articles/set-up-your-organization) - Configure the organization foundation before inviting teams and deploying agents. - [Invite users and assign roles](https://help.irongorilla.ai/articles/invite-users-and-assign-roles) - Bring teammates into Iron Gorilla with appropriate access for their responsibilities. - [Manage access by department](https://help.irongorilla.ai/articles/manage-department-access) - Give people and Access Groups the right role in the right part of your organization. ### Agent Builder Create, review, validate, and deploy governed agents. - [Create your first agent](https://help.irongorilla.ai/articles/create-your-first-agent) - Use Agent Builder to turn a business request into a reviewable governed agent. - [Review an agent before deploy](https://help.irongorilla.ai/articles/review-an-agent-before-deploy) - Check source, tools, policies, validation, and owner context before an agent goes live. - [Improve an agent with feedback](https://help.irongorilla.ai/articles/improve-an-agent-with-feedback) - Rate agent work and review suggested improvements before anything changes. - [Use voice chat with an agent](https://help.irongorilla.ai/articles/use-voice-chat-with-an-agent) - Start and control a governed voice conversation from agent chat. - [Use agent memory and autonomous work](https://help.irongorilla.ai/articles/use-agent-memory-and-autonomous-work) - Give an agent approved context and bounded multi-step work without opening its scope. ### Trust Profiles Understand agent trust scores, drift signals, and human review. - [Understand agent trust scores](https://help.irongorilla.ai/articles/understand-agent-trust-scores) - Read trust score signals and use them to decide how much autonomy an agent should have. - [Handle an agent trust drop](https://help.irongorilla.ai/articles/handle-an-agent-trust-drop) - Respond when an agent drifts, loses trust, or starts requiring human review. ### Connectors And MCP Connect tools and MCP servers without handing agents open-ended access. - [Add a connector or MCP server](https://help.irongorilla.ai/articles/add-a-connector-or-mcp-server) - Find hosted tools or connect a custom MCP server while preserving scoped access. - [Review connector health](https://help.irongorilla.ai/articles/review-connector-health) - Use connector status, tool registration, and diagnostics to keep agent tools reliable. ### LLM Proxy Route model calls through a governed path with cost, trace, and policy context. - [Configure model routing in LLM Proxy](https://help.irongorilla.ai/articles/configure-model-routing-in-llm-proxy) - Send model calls through a controlled path with provider, fallback, and policy context. - [Read an LLM trace](https://help.irongorilla.ai/articles/read-an-llm-trace) - Understand provider, token, latency, cost, policy, and refusal details for a model call. ### Policy Builder Turn business boundaries into controls that run where agents act. - [Create a policy from plain language](https://help.irongorilla.ai/articles/create-a-policy-from-plain-language) - Start with a business boundary and turn it into a control the runtime can enforce. - [Simulate a policy before launch](https://help.irongorilla.ai/articles/simulate-a-policy-before-launch) - Use sample actions to see exactly how a policy will behave before it affects live work. ### Operations Command Center Manage approvals, blocked actions, exceptions, and audit context. - [Pause and review agent work](https://help.irongorilla.ai/articles/pause-and-review-agent-work) - Stop AI work, compare a safe recovery, and review the evidence before resuming. - [Review pending approvals](https://help.irongorilla.ai/articles/review-pending-approvals) - Decide held actions with the agent, policy, trust, and evidence in view. - [Use the operations dashboard](https://help.irongorilla.ai/articles/use-the-operations-dashboard) - Find current risk, waiting approvals, blocked actions, and agent activity in one view. - [Investigate blocked actions](https://help.irongorilla.ai/articles/investigate-blocked-actions) - Review why an action was stopped and decide whether policy, access, or agent behavior should change. ### Reporting Preview, save, schedule, and export governance evidence. - [Build an ad-hoc report](https://help.irongorilla.ai/articles/build-an-ad-hoc-report) - Preview a governance report for a scope, agent, template, and time window. - [Schedule recurring reports](https://help.irongorilla.ai/articles/schedule-recurring-reports) - Create a cadence for governance reports that should arrive without manual work. - [Export evidence as PDF, Markdown, or JSON](https://help.irongorilla.ai/articles/export-evidence-as-pdf-markdown-or-json) - Choose the right export format for people, AI workflows, or downstream systems. ### Troubleshooting Common access, verification, and browser issues. - [Troubleshoot login, Turnstile, and common access issues](https://help.irongorilla.ai/articles/troubleshoot-login-turnstile-and-common-access-issues) - Resolve common sign-in, verification, invite, and browser problems. ## Support - Changelog: https://help.irongorilla.ai/changelog - Submit a ticket: https://help.irongorilla.ai/contact - Main website: https://irongorilla.ai ## Changelog Customer-facing product updates for signed-in Iron Gorilla users, grouped by date. We keep this page focused on what changed and link to help articles when more detail is useful. URL: https://help.irongorilla.ai/changelog ## July 19, 2026 ### Manage access by department and group - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-19-department-access-control Administrators can give people and Access Groups the right role at the organization, department, or Functional Group level, then use Access Inspector to understand why someone has access. Related help: - [Manage access by department](https://help.irongorilla.ai/articles/manage-department-access) ### Dashboards and reports feel faster - Category: Improved - Link: https://help.irongorilla.ai/changelog#2026-07-19-faster-dashboard-navigation Common dashboard and reporting views now reuse data more efficiently, preload pages as you navigate, and avoid unnecessary refreshes while keeping workspace information current. Related help: - [Use the operations dashboard](https://help.irongorilla.ai/articles/use-the-operations-dashboard) ### A smoother path to your first agent - Category: Improved - Link: https://help.irongorilla.ai/changelog#2026-07-19-smoother-first-agent-setup Website consultation, account setup, email verification, agent creation, validation, and deployment now provide clearer progress and a more continuous guided experience. Related help: - [Create your first agent](https://help.irongorilla.ai/articles/create-your-first-agent) - [Review an agent before deploy](https://help.irongorilla.ai/articles/review-an-agent-before-deploy) ### More reliable live updates and agent editing - Category: Fixed - Link: https://help.irongorilla.ai/changelog#2026-07-19-reliable-live-updates-and-editor Live status stays connected more consistently as you move between pages, and agent source opens as readable code without stale or incorrectly encoded editor content. Related help: - [Review an agent before deploy](https://help.irongorilla.ai/articles/review-an-agent-before-deploy) ### Bug fixes - Category: Fixed - Link: https://help.irongorilla.ai/changelog#2026-07-19-account-audit-and-pricing-fixes We fixed issues that affected account setup, plan price displays, audit time filters, page responsiveness, and several slow or stale loading states. Related help: - [Understand plan limits and upgrades](https://help.irongorilla.ai/articles/understand-plan-limits-and-upgrades) - [Build an ad-hoc report](https://help.irongorilla.ai/articles/build-an-ad-hoc-report) ## July 15, 2026 ### A simpler way to work with agents - Category: Improved - Link: https://help.irongorilla.ai/changelog#2026-07-15-business-first-agent-experience New accounts start in Business mode with clearer agent names, statuses, and pages. Studio mode remains available when you need source and runtime detail. Related help: - [Choose Business or Studio mode](https://help.irongorilla.ai/articles/choose-business-or-studio-mode) ### More tools in the connector catalog - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-hosted-connector-catalog Browse hosted connectors by category, choose between a provider’s available servers, and connect another instance without leaving the catalog. Related help: - [Add a connector or MCP server](https://help.irongorilla.ai/articles/add-a-connector-or-mcp-server) ### Feedback now turns into agent recommendations - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-agent-feedback-recommendations Rate completed runs and chat replies, explain what went wrong, and review suggested improvements before sending a change to Agent Builder. Related help: - [Improve an agent with feedback](https://help.irongorilla.ai/articles/improve-an-agent-with-feedback) ### Help is available inside the app - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-in-app-help Open Help from anywhere in Iron Gorilla to find relevant articles or send a support request with useful page and diagnostic context. Related help: - [Contact support](https://help.irongorilla.ai/contact) ### Plan limits and upgrade paths are clearer - Category: Improved - Link: https://help.irongorilla.ai/changelog#2026-07-15-plan-limits-upgrades Agent, audit, routing, environment, and identity limits now explain the available plan and whether you can upgrade or need an administrator. Related help: - [Understand plan limits and upgrades](https://help.irongorilla.ai/articles/understand-plan-limits-and-upgrades) ### Authorized administrators can pause AI work - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-ai-emergency-controls Preview the impact of a pause, stop AI work for an organization, department, group, or agent, and resume it when the issue is resolved. Related help: - [Pause and review agent work](https://help.irongorilla.ai/articles/pause-and-review-agent-work) ### Voice conversations with agents - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-governed-voice-chat Agents configured for voice can hold governed web conversations with consent, mute, restart, transcript, approval, and fallback controls. Related help: - [Use voice chat with an agent](https://help.irongorilla.ai/articles/use-voice-chat-with-an-agent) ### Agents can use scoped memory and autonomous work - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-agent-memory-autonomous-work Where enabled, agents can recall approved context within their assigned scope and work through bounded multi-step tasks with governed tools. Related help: - [Use agent memory and autonomous work](https://help.irongorilla.ai/articles/use-agent-memory-and-autonomous-work) ### Review risky changes with replays and narratives - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-risk-replay-narratives Where enabled, reviewers can compare a proposed recovery in simulation and approve a cited governance summary before it is exported or shared. Related help: - [Pause and review agent work](https://help.irongorilla.ai/articles/pause-and-review-agent-work) ### Grok 4.5 model routing - Category: New - Link: https://help.irongorilla.ai/changelog#2026-07-15-grok-model-routing Organizations with xAI enabled can select Grok 4.5 as a preferred or fallback model and review its context, pricing, and trace details. Related help: - [Configure model routing](https://help.irongorilla.ai/articles/configure-model-routing-in-llm-proxy)