Multi-domain executive analytics façade · PEF is pack #1 · chat host is separate UI
Service is up · you are viewing this via https://business-mcp-staging.dtt-hub-dev.odvi.app
https://business-mcp-staging.dtt-hub-dev.odvi.app/https://business-chat-staging.dtt-hub-dev.odvi.apphttps://business-mcp-staging.dtt-hub-dev.odvi.app/healthhttps://business-mcp-staging.dtt-hub-dev.odvi.app/mcphttp://46.250.229.188:9101Hub packs: ["pef", "ncapp", "prs"] · registered systems: ["pef", "odoo", "prs", "ncapp", "context"]
list_business_metrics — List what can be askedcheck_question_support — Can this question be answered?ask_business_question — Run a governed metric / scenario 1–5get_metric_definition — Definition cardsubmit_feedback — Feedback on a run_idsubmit_dtt_request — Submit unmatched question to DTT (after user says yes)list_dtt_requests — List DTT requests (Requests tab)update_dtt_request_status — Triage: open|in_progress|done|dismissedlist_knowledge_summary — Dev: Knowledge home countsget_metric / update_metric — Dev: resolve & patch metric SQLpreview_metric_sql — Dev: SQL preview (guarded)list_glossary_terms / update_glossary_term — Dev: glossary browser18 metrics · exploratory until definitions are approved ·
ask with metric_id or “scenario 1”…“scenario 5”
| metric_id | Title | Domain | Systems | Scenario | Source | Description |
|---|---|---|---|---|---|---|
active_users_by_department | Active PEF users by department | pef | pef | — | builtin | Count of active PEF users grouped by PEF department. |
instances_by_state | PEF instances by workflow state | pef | pef | — | builtin | Count of non-deleted PEF instances grouped by state. |
incomplete_pefs | Incomplete PEFs | pef | pef | — | builtin | PEF instances not submitted and not closed (exploratory incomplete definition). Parameterized group_by: none (total) or department. If breakdown is not specifie |
instances_by_cycle | PEF instances by cycle | pef | pef | — | builtin | Count of PEF instances per evaluation cycle. |
workflow_status_by_company_dept | Workflow status by company & department (published cycles) | pef | pef | 1 | builtin | For every PUBLISHED evaluation cycle: PEF counts by workflow state, grouped by company and department, with group totals, state share %, completion % (CLOSED), |
eligibility_vs_assignment | Eligibility vs assignment (regularization cutoff) | pef | pef | 2 | builtin | For each PUBLISHED cycle: (a) active REGULAR employees regularized on/before cutoff without a PEF assignment; (b) assigned employees regularized after cutoff. |
overdue_pef_activities | Overdue PEF activities (milestone-based) | pef | pef | 3 | builtin | As of today, open PEFs past the cycle milestone mapped to their current state (self-rating, KPM, calibration, close). Shows employee, manager, department, activ |
self_vs_manager_disagreement | Top self vs manager rating disagreements | pef | pef | 4 | builtin | Five largest disagreements between SELF and MANAGER ratings on matching People Analyzer, GWC, or KPM rows (same row_id). |
gwc_wrong_seat_kpm_passed_audit | Audit: GWC WRONG_SEAT with KPM PASSED | pef | pef | 5 | builtin | PEFs where GWC is WRONG_SEAT and KPM is PASSED. Recalculates KPM as weighted average of manager ratings (pass >= 3.00) and next step from PA×GWC matrix; flags d |
results_recalc_mismatches | Results recalculation mismatches (broader audit) | pef | pef | 5b | builtin | Broader audit: PEFs whose stored KPM score/result or next_step differs from recalculation (manager KPM weighted avg; PA×GWC next-step matrix). |
ncapp_productions | NCAPP productions | ncapp | ncapp | — | builtin | Companion App loan production counts. Parameterized group_by: none | month | branch | source; optional period filter. If breakdown is not specified, ask — do no |
ncapp_par_current_by_tag | NCAPP current PAR tags | ncapp | ncapp | — | builtin | Distribution of current portfolio-at-risk (PAR) tags on accounts. |
ncapp_payment_posting_status | NCAPP payment posting by category/status | ncapp | ncapp | — | builtin | Payment posting rows by category and execute_status (top combinations). |
ncapp_money_collected | NCAPP money collected | ncapp | ncapp | — | builtin | Sum of payment posting amounts (column amount) on NCAPP payment_posting_data. Parameterized: period (current_month, last_month, month, range, ytd, all_months) a |
prs_parcels | PRS parcels | prs | prs | — | builtin | Outbound parcels (not soft-deleted). Parameterized group_by: none | status | month | branch | courier; optional period. If breakdown is not specified, ask — do |
learned_bucketlist_mr_sales_funnel | BUCKETLIST MR Lead-to-Visit-to-Availed Funnel | bucketlist | bucketlist | learned | learned | Learned metric from teaching session. Gap: new_metric Systems: bucketlist Domain: bucketlist Engine: trino Intent: Determine whether MR availment performance is |
learned_ncapp_customer_lifetime_borrowing | NCAPP Customer Lifetime Borrowing and Preterm Renewal | ncapp | ncapp | learned | learned | Learned metric from teaching session. Gap: new_metric Systems: ncapp Domain: ncapp Engine: snowflake Intent: Quantify customer lifetime value through repeat bor |
learned_pending_kpm_bae721d966 | Pending KPM count (learned proof bae721d966) | pef | pef | learned | learned | Learned metric from teaching session. Gap: new_metric Systems: pef Domain: pef Intent: Count PEFs stuck in KPM step for ops follow-up Population: Non-deleted PE |
It must refuse (hard stop), then proactively ask in the same turn if you want to submit this as a request to DTT — including for unknown abbreviations. It must not open application codebases or invent SQL. There is no end-user teaching path.