AI Advisor (Digital Chief of Staff) CEO / Admin
Intelligent advisor powered by Claude, covering all 27 Kaltiv modules. 44 AI tools in 4 layers, tenant-specific knowledge base, proactive recommendations, conversational memory and scheduled reports.
Access
Sidebar → Agriculture → AI Assistant (chatbot)
Knowledge base management: Settings → Advisor Knowledge
Or directly via: /settings/advisor-knowledge
The 6 Tabs
The Advisor Knowledge page consolidates all management features in 6 tabs:
| Tab | Icon | Description |
|---|---|---|
| Documents | File | Upload documents (PDF, DOCX, XLSX), track embedding status, delete |
| Facts | Lightbulb | Add, edit, delete manually taught facts |
| Recommendations | Star | View proactive recommendations generated by AI |
| Memory | Brain | Visualise the assistant's long-term conversational memory |
| Scheduler | Clock | Configure automatic reports (daily, weekly, custom) |
| Sources | Link | Connect external sources (Google Drive, RSS feeds) |
Document Management
Tab: Documents
The assistant uses your internal documents to enrich its responses. The processing pipeline is fully automated.
Processing Pipeline
Upload (PDF/DOCX/XLSX)
→ Text extraction
→ Chunking
→ Vector embedding generation
→ Tenant-isolated storage
Available Actions
| Action | Description |
|---|---|
| Upload | Drag and drop or select a file (PDF, DOCX, XLSX) |
| Status | Track processing: pending → extraction → embedding → ready |
| Search | The assistant automatically queries your documents via vector search |
| Delete | Remove a document and its associated embeddings |
Start with your strategic documents: business plan, standard operating procedures (SOPs), annual objectives, audit reports. The richer the knowledge base, the more relevant the recommendations.
Teaching Mode (Facts)
Tab: Facts
Teaching mode lets you inject business knowledge directly into the assistant's memory without uploading documents.
Two Methods
- In conversation: say "Remember that..." and the assistant records the fact automatically
- Example: "Remember that our palm yield target is 18 tonnes/hectare for 2026."
- Via the interface: Settings → Advisor Knowledge → Facts tab → Add a Fact button
Fact Management
| Action | Description |
|---|---|
| Add | Enter a fact with a category (objective, process, policy, contact, etc.) |
| Edit | Update an existing fact when information changes |
| Delete | Remove an outdated fact |
| Search | Facts are automatically queried in the triple-source RAG pipeline |
Facts are integrated into the hybrid triple RAG search: shared base + tenant documents + taught facts.
Proactive Recommendations
Tab: Recommendations
The assistant generates recommendations based on cross-module data analysis. Recommendations are powered by 6 machine learning models deployed in production.
Trigger Types
| Trigger | Example |
|---|---|
| Financial anomaly | Abnormally high spending on a budget line |
| Yield drop | Production below expected threshold (ML yield model) |
| HR risk | Rising absenteeism, potential departures (ML turnover model) |
| Commercial opportunity | Favourable price trend, underutilised stock |
| Lean gap | Blocked PDCA cases, declining 5S score, SPC violations |
| ML prediction | Yield, quality, price forecasts (oil/nuts/papaya), demand |
| Preventive maintenance | Equipment at risk of failure (ML maintenance model) |
Recommendation Lifecycle
Automatic detection (cross-module analysis)
→ Recommendation generated
→ Notification (sidebar badge)
→ View (Recommendations tab)
→ Action or archive
Recommendations also appear via a notification badge in the sidebar.
Personalised Memory
Tab: Memory
The assistant learns from each conversation to personalise its responses over time.
What the Assistant Memorises
| Element | Description |
|---|---|
| User preferences | Preferred report format, modules of interest, response language |
| Accumulated context | Recurring topics, past decisions, usage patterns |
| Confidence decay | Older memories gradually lose weight — recent information takes priority |
Actions
- View: see the full conversational memory
- Purge: delete outdated or incorrect memory entries
Memory is isolated by tenant and by user. No sharing between tenants.
Scheduled Reports
Tab: Scheduler
Configure automatic reports generated by the AI assistant on a defined schedule. Reports are executed via Vercel Cron and stored in Supabase Storage.
Report Types
| Type | Frequency | Content |
|---|---|---|
| Daily briefing | Every morning | KPI summary, active alerts, pending tasks |
| Weekly review | Every Monday | Week's performance, trends, recommendations |
| Custom tracking | Configurable | Report on a specific topic at chosen intervals |
Configuration
- Go to Settings → Advisor Knowledge → Scheduler tab
- Click New Scheduled Report
- Define: subject, frequency (daily, weekly, monthly, custom), format
- The report is generated automatically and accessible in the history
Technical Infrastructure
Scheduled reports use the Vercel Cron endpoint /api/cron/advisor-schedules, which queries the advisor_schedules table and triggers generation via the Claude API.
External Connectors
Tab: Sources
Connect external data sources to automatically feed the knowledge base.
Google Drive
| Step | Action |
|---|---|
| 1 | Go to the Sources tab |
| 2 | Select type Google Drive |
| 3 | Configure the folder ID to sync |
| 4 | Synchronisation runs automatically at regular intervals |
| 5 | New files are automatically indexed and embedded |
RSS Feeds
| Step | Action |
|---|---|
| 1 | Go to the Sources tab |
| 2 | Select type RSS |
| 3 | Enter the RSS feed URL (sector news, market prices, etc.) |
| 4 | Articles are automatically fetched and integrated into the knowledge base |
You can configure multiple sources simultaneously. Each source is synced independently and content is isolated by tenant.
AI Chatbot — 44 Tools
The chatbot is accessible via Agriculture → AI Assistant in the sidebar. It responds in natural language and queries data in real time.
Overview of the 4 Layers
| Layer | Tools | Scope |
|---|---|---|
| L1 — Core | 12 tools | HR, Payroll, Leave, Attendance, Daily work, Sales, Stock, CMMS, Accounting, Agriculture |
| L2 — Lean | 15 tools | PDCA, 8D, QRQC, Kanban, BSC, SPC, FMEA, 5S, Gemba, OPL, VSM, Takt Time, SMED, TPM, OKR |
| L3 — Knowledge | 7 tools | Tenant documents, embeddings, taught facts, hybrid triple RAG search, external connectors |
| L4 — Advisory | 10 tools | ML predictions, proactive recommendations, cross-module correlation, memory, scheduled reports |
Example Questions by Layer
L1 — Core:
- "How many active employees do we have?"
- "What was last month's revenue?"
- "Which leave requests are pending approval?"
- "What's the current carton stock level?"
L2 — Lean:
- "Which PDCA cases are overdue this week?"
- "Show the BSC score by perspective."
- "Are there any Nelson rule violations on the SPC charts?"
- "Summarise this month's Gemba observations."
L3 — Knowledge:
- "What do our SOPs say about the harvest procedure?"
- "Remember that supplier X raised prices by 12%."
- "What information do we have on OHADA standards?"
L4 — Advisory:
- "What is the yield forecast for plot A?"
- "Generate a briefing for the management committee."
- "What are your recommendations for this week?"
- "What is the palm oil price trend?"
Access Control (RBAC)
The assistant automatically checks RBAC permissions before each query. A user can only query the modules they have access to.
Use Cases
CEO Daily Briefing
The CEO opens the chatbot each morning and asks:
"Morning briefing."
The assistant responds with:
- Key KPIs (production, finance, HR)
- Active alerts (low stock, broken equipment, unvalidated leave)
- Proactive recommendations for the day
- Tasks pending approval
This briefing can be automated via the Scheduler to be generated every morning at 7am.
Agricultural Intelligence
The production director asks:
"What is the yield forecast for next quarter and what risk factors should I watch?"
The assistant combines:
- ML yield and quality prediction models
- Weather data and production history
- Uploaded technical documents (SOPs, agronomic guides)
- Taught facts (targets, field constraints)
Financial Alerts
The finance manager receives a proactive recommendation:
"Alert: fuel expenses are 35% above the 3-month average. Recommendation: check recent purchase orders and audit vehicle usage."
This recommendation is generated automatically by the cross-module correlation engine (L4).
Technical Architecture
Database (7 tables)
| Table | Purpose |
|---|---|
tenant_documents | Documents uploaded per tenant (PDF, DOCX, XLSX) |
tenant_embeddings | Embedding vectors per document chunk |
advisor_facts | Facts taught by users |
advisor_recommendations | Proactive recommendations generated by the AI engine |
advisor_memory | Long-term conversational memory |
advisor_schedules | Scheduled report configuration (Vercel Cron) |
tenant_sources | External connectors (Google Drive, RSS) |
All tables are isolated by tenant_id with RLS (Row Level Security).
Triple-Source RAG Pipeline
User question
→ Hybrid search:
1. Shared base (general Kaltiv embeddings)
2. Tenant documents (tenant embeddings)
3. Taught facts (tenant facts)
→ Enriched context passed to Claude
→ Response with citations and sources
Permissions
| Role | Access |
|---|---|
| CEO / Admin | All features: chat, documents, facts, recommendations, memory, sources, scheduled reports |
| HR Administrator | Chat (RBAC-authorised domains), view recommendations |
| Manager | Chat (RBAC-authorised domains) |
| Supervisor | Chat (Agriculture, Lean, Operations domains) |
| Employee | Chat (HR domain: profile, leave, payslips) |
Navigation
/agriculture/chatbot → AI Chatbot (conversation)
/settings/advisor-knowledge → Knowledge base (6 tabs)
The AI advisor is connected to all Kaltiv modules. Recommendations cross HR, production, finance, stock and Lean data for strategic insights. The 6 deployed ML models (yield, quality, price x3, demand) power real-time predictions.
Screenshots of this module will be added in a future documentation update.