Lagniappe can use Google Vertex AI for optional generation, extraction, and summarization features. AI runs only when a user invokes an AI action.

The goal is not to sprinkle AI everywhere, but to use it where the app already knows the relevant form schema, document, file, page, task, and permission context.

• Generate draft form schemas from descriptions.
• Autofill page or task forms from existing context, files, images, or user instructions.
• Generate editable document text.
• Generate page or document images.
• Summarize uploaded files for review or search.
• Create draft categories, projects, model tasks, pages, and schedules.
• Look up permitted workspace records and application help while working on a request.
• Answer questions using only the records, files, and tasks the current user can access.
• Suggest workspace-native actions, such as adding pages, tasks, files, forms, or projects in the right place.

Open Create a Plan on Home with a question, a request, files, or a combination of them. For example, you might ask what repairs a property needs, or attach inspection notes and ask for follow-up tasks. One saved plan can contain both an answer and proposed workspace changes.

Read the answer and review proposed changes before applying them. Use Revise Plan to correct the proposal, then Execute Proposal when it is ready. A question that needs no changes finishes with its answer. Files can stay with the plan as supporting evidence; say when they should not be filed onto a page or task.

On the homepage, combine the Active, Executed, and Answers filters to choose which saved reports to show. Active includes proposals that are ready, still processing, or need attention. Executed contains completed proposals. Answers contains saved answers without executable changes. Each count includes reports hidden by the current filters.

Select Executed alone to delete all displayed executed proposals after one confirmation. This removes their reports, undo history, and report-only uploads. Created pages, tasks, and other workspace changes remain. Your browser remembers your filter choices.

An Administrator chooses a separate AI level for each ordinary user; only the primary Owner edits another Administrator’s account. This level controls features that call Lagniappe’s configured model provider: None disables those calls, Ask allows workspace questions with supporting files and saved answers, and Create also enables proposals, generation, autofill, and summarization. Create includes Ask.

This setting is independent from user groups and permissions, so a user can have broad workspace permissions without AI access, or AI access that still operates only within a narrow set of permitted records.

External-agent API plans use the user’s own AI client and tokens, so they are not controlled by this provider entitlement. Working with an already saved report is also provider-free. API plans and report execution still use the signed-in user’s normal workspace permissions.

AI tools use the same permission boundaries as the rest of Lagniappe. When a user asks a question or starts an AI workflow, the app assembles context through server-side permission checks instead of handing the AI an owner-level view of the workspace.

For example, if someone is invited only to an old house category, they can ask about electricians, repairs, files, or tasks in that category. Other houses, other categories, and records they cannot view are left out of search results and AI tool responses.

Built-in AI requests go through your own Google Cloud project’s Vertex AI configuration. That is a meaningfully different posture from pasting private data into a consumer chatbot account, though it is still a cloud AI service: prompts, files, and generated output are sent to Google for processing under your cloud terms and settings.

The training boundary is the important difference. Consumer AI products may use conversations to improve or train their services depending on the product, plan, and account settings. Google Cloud’s managed Gemini model terms say Google will not use customer data to train or fine-tune AI/ML models without prior permission or instruction. That is stronger than relying on a consumer account toggle, but it is not the same as local-only processing.

If zero data retention matters for your installation, choose those settings intentionally. Google’s guidance calls out several retention paths to review, including abuse-monitoring exceptions, request-response logging, cached data, and grounding features that may keep limited logs: Gemini Enterprise Agent Platform zero data retention. Lagniappe setup can help disable Vertex AI caching, but that is one control rather than a blanket guarantee for every AI feature or future provider setting.

AI usage is pay-per-use through your cloud project. Text operations are usually small. Image generation and large file analysis cost more, and provider pricing can shift over time.

Budget alerts in Google Cloud are an easy safety net. If you turn on search grounding, file processing, image generation, or run large planning requests, it is worth glancing at usage a little more often.

Change models in Admin / Site Settings / AI Models. The installer can change AI and external-agent access with:

./setup.sh ai

AI is a helpful collaborator rather than an oracle. A few things to keep in mind when reviewing its output:

• Generated schemas can look reasonable and still need a tweak or two.
• Autofill may skip a value, or fill one in that you would rather leave blank.
• File summaries occasionally miss a detail that matters.
• Search-grounded answers can lean on the web rather than your own policy or records.
• Model names, pricing, and retention settings live with the provider and can change.