Ask AI App Overview

Ask AI

1. What it is

Ask AI is the platform’s conversational assistant. Employees type or speak a question, and Ask AI routes it to whichever specialist agent owns the answer — scheduling for shift questions, leave management for PTO balances, service desk for ticket status, and so on. Each agent works with that app’s live data, so answers reflect the current state of a schedule or queue, not just what a policy document says.

• Enablement: Ask AI requires a licence and the Standard platform tier or above. An admin enables it from Admin → App Marketplace → Ask AI, and can restrict access to specific groups or roles.
• What it is not: Ask AI is not the place to pause or resume the AI across the organisation — those kill switches live in Admin → AI Operations.

2. Standing it up

1. Go to Admin → App Marketplace, find Ask AI, and enable it. Confirm the organisation is on the Standard platform tier or above — Ask AI will not load on Lite.
2. Open Apps → Ask AI → Admin → Settings and review the defaults. The key decisions at this stage:
   • Enable Action Execution (on by default) — whether the assistant can carry out actions such as filing tickets or creating shifts. Every action pauses for the employee’s confirmation before executing.
   • Enable Voice Mode (on by default) — whether employees can speak to Ask AI. The default daily limit is 30 minutes per user.
   • Conversation retention (default 24 months) — how long transcripts are kept before the nightly sweep permanently deletes them.
3. Open Apps → Ask AI → Admin → Agent Guidelines → AI Features and confirm the toggles suit your rollout. Key defaults:
   • Multi-agent routing is on — a question that spans two apps is handed between agents automatically.
   • Shared knowledge search is on — agents draw on the Knowledge Base, HR Policies, SOPs, Sites, Wikis, and Drive when answering.
4. To restrict Ask AI to a pilot group before a wider rollout, go to the app’s Audience settings in the App Marketplace and assign the group. Only members of that group will see the Ask AI entry point; others are redirected.
5. Confirm it works: open Apps → Ask AI → Chat and type a question. The response should stream in. If the organisation has other apps enabled (Shifts, Leave Management, Service Desk), try a question in each domain to verify agent routing.

3. How it fits together

Agents and routing — Ask AI is a dispatcher, not a single model. Each enabled app registers its own specialist agent. When a message arrives, Ask AI classifies the intent and routes it to the matching agent. If a request spans two areas, the first agent can hand the remainder to another mid-conversation, so the employee never restates the question. Agents are gated by the same licence and audience rules that govern their parent app: if an employee cannot reach the Compensation app, the Compensation agent will not answer their question either.

Shared knowledge — In addition to each agent’s live data, Ask AI searches a shared corpus of company knowledge. The six sources — Knowledge Base, HR Policies, SOPs, Sites, Wikis, and Drive — can each be toggled on or off from the AI Features tab. Within the Knowledge Base source, individual areas can be individually disabled.

Verified Knowledge — When Ask AI gives a wrong or incomplete answer in a News Feed thread, a user can submit a correction. These corrections land in the Verified Knowledge queue (pending review). An admin approves, edits, or rejects each one. Approved entries become part of the retrieval corpus and directly influence future answers.

Personal Memory — The assistant remembers facts about each employee across conversations (preferences, role context, prior requests). Every user can review and erase these facts from the Personal Memory tab; the underlying memory feature is governed by the Muscle Memory app.

Journeys — Multi-step goals the assistant tracks for an individual employee. An employee can have up to 3 active journeys at a time, each with up to 12 steps. The assistant updates progress during conversation, and the employee can override any step from the My Journeys tab. Journeys are gated by the Journeys toggle on the AI Features tab.

4. Running it

Reviewing Agent Guidelines

Agent Guidelines shape how every agent thinks, communicates, and acts. Go to Apps → Ask AI → Admin → Agent Guidelines. The five tabs are:

1. Context & Rules — Business context, custom instructions, universal guardrails, and a glossary. These are concatenated into every agent’s system prompt.
2. Communication — Tone, response style, greeting, apology, and escalation messages.
3. Autonomous Actions — Action-level guardrails, notification rules, and whether reasoning is shown in chat.
4. Overrides — Per-agent customisations that override the global settings.
5. AI Features — The org-level toggles for multi-agent routing, shared knowledge, journeys, and other capabilities.

Context, Communication, and Autonomous Actions use a draft / publish workflow: changes are staged as a draft until you click Publish, at which point they apply to all agents immediately. Overrides and AI Features apply on save.

Managing Verified Knowledge

Go to Apps → Ask AI → Admin → Verified Knowledge. The queue shows three tabs: Pending, Active, and Retired. Pending entries are submitted corrections awaiting review. Active entries are live and influence answers. Retired entries are archived.

For each pending entry, you can approve (optionally editing the answer), reject, or leave it. An approved entry immediately becomes part of the retrieval corpus.

Using the Knowledge Map

Apps → Ask AI → Admin → Knowledge Map shows the graph of content linked to skills and roles. This makes retrieval skill-aware: an answer about welding safety is prioritised for employees whose role requires welding skills. You can add manual links between content (Knowledge Base articles, HR Policies, SOPs) and skills, or filter the graph by skill or role type.

Running the Test Suite

Apps → Ask AI → Admin → Test Suite (accessible to admins and managers) lets you send example questions to the live agent pipeline and see which agent handled them, the response, and the routing match. Tests run against the published Agent Guidelines configuration.

Processing Data Requests

Apps → Ask AI → Admin → Data Requests supports GDPR Articles 15/17/20. Select an employee and either export their full Ask AI record as JSON, redact the content (keeping the metadata skeleton), or erase all Ask AI data for that person. Erasure is irreversible. Only admins (not app admins) can access this surface.

Reviewing Analytics

Apps → Ask AI → Admin → Analytics shows this tenant’s Ask AI usage: adoption trends, volume, per-user and per-day breakdowns, with CSV export.

Managing the Prompt Library

Apps → Ask AI → Prompt Library shows a gallery of reusable prompt templates. The gallery combines system-wide curated prompts with the tenant’s own org-private prompts. Any employee can browse and click Use in Ask AI to deep-link into the chat with the prompt prefilled. Admins can create, edit, and delete tenant-private prompts. Prompts are organised into categories: Productivity, Communication, Workflow, Analytics, and Operations.

5. Settings

Settings are split across two surfaces: the Settings page (the app’s configure page) and the AI Features tab within Agent Guidelines.

Settings page

Setting	Default	What it changes
Enable General Questions	On	Whether Ask AI answers open-ended questions beyond schedule and app-specific queries
Enable Schedule Queries	On	Whether Ask AI answers shift and schedule questions
Enable Action Execution	On	Whether agents can carry out actions (every action still requires the employee’s confirmation)
Enable Voice Mode	On	Whether employees can use voice conversations with Ask AI
Voice Daily Limit	30 minutes per user	Per-user daily cap on voice usage; 0 means unlimited
AI Voice	Marin	The voice used for spoken responses
Voice Response Style	Concise	How verbose voice answers are
Voice Speech Pace	Normal	Speed of spoken responses
Include Platform Help Articles in Answers	Off	Whether the assistant’s answers draw on platform help-centre articles in addition to company knowledge
Keep conversation history for	24 months	How long transcripts are retained before permanent deletion by the nightly sweep
Allow users to clear their conversation	On	Whether employees see the “Clear conversation” and “Reset AI completely” controls

AI Features tab (Agent Guidelines → AI Features)

Setting	Default	What it changes
Multi-agent routing	On	Whether a question that spans two apps is handed between specialist agents automatically
Shared knowledge search	On	Whether agents search the company knowledge corpus (Knowledge Base, HR Policies, SOPs, Sites, Wikis, Drive)
App help articles	On	Whether agents draw on each app’s built-in help articles when answering
Session mining	Off	Whether the platform analyses completed conversations to surface unanswered question patterns
Journeys	On	Whether the assistant tracks multi-step goals for employees
Journey inference	On	Whether the assistant infers journey progress from conversation context
Reasoning loop	On	Whether agents use an extended reasoning loop for complex questions
Tool signal boost	On	Whether the assistant strengthens signals to select the right tool for a request
Planner	Off	Whether the assistant creates multi-step plans for complex tasks

6. More help

• Ask AI FAQ — specific setup and operating questions, including limits, thresholds, and troubleshooting
• Ask AI — What It Can Do and How to Govern It — the platform-level governance article covering AI operations, moderation, and cross-app controls
• Ask AI — the assistant answers questions about Ask AI from these articles