IF you’re trying to manage tenants/users/org settings (MSP/admin tasks)
​THEN you should be using admin.hatz.ai (admin portal).
​

IF you’re an end user chatting/using tools in your org (NOT an MSP)
​THEN you should be using your org’s subdomain (your unique Hatz URL), not admin.hatz.ai.
Source: “Access Restricted” note in the error guide + login troubleshooting context.

IF the app won’t load (chat history/workflows not loading) and your internet is fine
​THEN whitelist Hatz domains on your network/security stack:

Source:

IF you see “Access Restricted”
​THEN confirm you’re logging into the correct place:

Source:

Start by identifying the user type:

IF an ACTIVE Admin user needs a password reset
​THEN in admin.hatz.ai go to Settings → Users and Roles → (…) → Reset Password.

IF an INACTIVE Admin user didn’t get the invite / invite expired
​THEN in admin.hatz.ai go to Settings → Users and Roles → (…) → Resend Invite.

IF an ACTIVE Customer user needs help logging in
​THEN in admin.hatz.ai go to Tenants → select tenant → (…) → Resend Invite (sends reset/setup instructions).

IF a PENDING Customer user didn’t receive the invite / it expired
​THEN in admin.hatz.ai go to Tenants → select tenant → (…) and choose either:

Source (all of the above):

IF chat is taking too long to respond
​THEN

Source:

(Helpful context on model selection UI/attributes:)

IF an old/long-running chat stops giving good outputs
​THEN assume you’re hitting the model’s context window limits; move to a fresh chat (or reduce what you’re asking it to consider).

Source (context window note):

IF you’re using an OpenAI model in Hatz but results differ from ChatGPT on openai.com
​THEN check these common causes:

Source:

IF a file won’t upload even though it’s under 50MB
​THEN it may still exceed the token limit for the specific LLM you selected; try a different model (or reduce the document size/scope).

IF a file won’t upload even though it’s under 50MB
​THEN it might not be an accepted file type. We can evaluate these issues on a case by case basis.

Source:

IF web search, Auto-Tool, or an integration is not doing what you expect
​THEN

Sources:

IF users can’t find a model they expected (or you want to standardize model choice)
​THEN check org-level settings:

Source:

IF the issue is “credits, quotas, or usage limits”
​THEN use the official credit usage FAQ (most accurate source, updated policy):

(Background explainer in docs collection:)

IF you need a reusable prompt with user inputs and a single response
​THEN build an App. Apps are best when you do not need tool or integration access.
​

IF you need tools, integrations, multiple steps, multiple outputs, or run history
​THEN build a Workflow. A one-step workflow is the closest replacement for an app that needs tools.
​

IF you need a reusable conversational assistant with saved instructions, sources, and tools every time you chat
​THEN build an Agent and select it from Chat or use it from Workshop.
Source: https://docs.hatz.ai/en/articles/12281902-workshop-faq

IF a later workflow step cannot see or insert a previous step's output
​THEN confirm the steps are connected. Previous step outputs appear in the builder only when the steps are connected.
​THEN explicitly insert the earlier step's Output into the later step prompt and tell that step how to use it. Treat each step like a distinct automation; a later step will not automatically infer every detail from an earlier step unless you pass the needed output into its prompt.
Source: https://docs.hatz.ai/en/articles/11328145-workflows

IF Step 2 runs but behaves like it did not get Step 1 context
​THEN edit Step 2 and insert Step 1's Output from the Outputs list. Add plain-language instructions such as: Use the Step 1 output as the source material for this step.
Source: https://docs.hatz.ai/en/articles/11328145-workflows

IF you expected the workflow’s Web Scraper Step to click links / crawl the domain
​THEN note it only scrapes the single page URL you provide (it does not crawl the whole site).
​THEN either (a) provide the exact URL you need, or (b) redesign steps so earlier outputs produce the right URL for the scraper step to use.
Source: https://docs.hatz.ai/en/articles/11328145-workflows-beta

IF you need to debug cost, latency, or model choice inside a workflow
​THEN use Workflow Run History to inspect:

IF you want to share outputs as documents
​THEN export any workflow step to PDF or Word.
​

IF you want branded/structured Word docs
​THEN use a Document Processing Step with a .docx template and map placeholders (e.g., {{client_name}}) to workflow data.
​

IF you need to fill an existing PDF form
​THEN upload a fillable PDF and map workflow values to its form fields.
Source: https://docs.hatz.ai/en/articles/12332454-ai-document-processing-steps-and-exports-in-workflows

IF you can’t find where to build/manage workflows
​THEN go to the Workshop and look under Automations (Workflows are inside Workshop).
Source: https://docs.hatz.ai/en/articles/11328145-workflows-beta
(Workshop navigation/context): https://docs.hatz.ai/en/articles/12572765-the-hatz-workshop

IF an agent cannot use tools, integrations, or connected files
​THEN verify all of the following:

Source: https://docs.hatz.ai/en/articles/12602274-agents

IF you hit a limit adding tools
​THEN note agents can manually select up to three tools.
​THEN either enable Auto Tool Selection, swap tools, or create multiple specialized agents and switch agents when needed.
Source: https://docs.hatz.ai/en/articles/12602274-agents

IF the agent's behavior is inconsistent
​THEN first confirm the right agent is selected. Then tighten the agent's System Prompt (Instructions): define role, context, tasks, constraints, and output format in direct language.
​THEN test with a short request that clearly exercises one instruction. If tools or sources are involved, verify the expected tool/source is configured for the agent and review the inline tool call details.
Source: https://docs.hatz.ai/en/articles/12602274-agents

IF others can’t access your agent
​THEN check sharing settings—agents default to Private; enable Share with Organization to make it available org-wide.
Source: https://docs.hatz.ai/en/articles/12602274-agents

IF you created an agent but can’t figure out how to talk to it in Chat
​THEN use the agent selector in Chat (robot icon) and select your agent from the list. When an agent is selected, the chat tool selector shows the agent's configured tools and connection status, but the agent's tools are changed from the agent configuration page.
Source: https://docs.hatz.ai/en/articles/12602274-agents

IF an agent should only use a specific OneDrive folder or file
​THEN edit the agent, open its Tools settings, enable Microsoft 365, and use Browse under Limit OneDrive access to specific folders or files to select the allowed folders or files. Leave the scope empty only if the agent should use all OneDrive content available to the connected Microsoft account.
Source: https://docs.hatz.ai/en/articles/13947861-file-folder-scoping-for-agents

IF integrations aren’t appearing or you can’t connect them
​THEN check where you’re trying to connect from:

IF you need beta integration access and don’t see the integration
​THEN enable beta features for the right place:

IF results are stale or it didn’t search/scrape when it should have
​THEN either:

IF you’re debugging a workflow/agent/integration and want proof of what happened
​THEN use Inline Tool Calling to view:

IF you duplicated a community template but can’t find it / edit it
​THEN check My Items in Workshop (duplicating creates your editable copy; items start private).
Source: https://docs.hatz.ai/en/articles/12572765-the-hatz-workshop

IF you published something but the wrong people have access
​THEN re-check publishing/sharing scope (private vs org vs client tenants).
Source (apps publishing, relevant pattern for access scoping): https://docs.hatz.ai/en/articles/10716519-publishing-apps

IF you’ve followed the branch above and it still fails
​THEN contact Hatz support: [email protected] (listed in Hatz docs).
Source: