A conversational analytics platform for last-mile operations: plain-language questions become audited, governed queries, live data, and root-cause diagnosis — for operators and managers, not just analysts.
Every operational metric lived in the data warehouse and in formal dashboards. But writing a correct query meant knowing the data model, the right filters, and the canonical denominators — get one wrong and the number is misleading. So a hub manager who wanted to know whether productivity dropped this week, and why, opened a ticket and waited. The bottleneck was never the data. It was access.
The reports needed model knowledge, correct filters, and specific calculation logic to avoid showing the wrong figure.
Tables run into hundreds of gigabytes in hourly partitions. A query written without the canonical rules quietly returns bad data.
Knowing productivity fell is only the start. Explaining why took hours of manual analysis — so it rarely happened.
The user asks an operational question. The platform resolves the scope, generates canonical SQL verified against a governed rules codex, runs it against the warehouse, and answers in chat with a clean table, week-over-week context, and only the glossary terms that appear.
If the question doesn't specify a facility, operation type, or period, it asks first. It maps the user to their area of responsibility so the answer is already in their scope.
The query is built with inline references to a governed business-rules codex, then audited against a set of rules: correct calculation mode, canonical denominators, valid time filters. If a rule fails, the query never runs.
A dry run estimates cost first. If it passes, it executes against the correct table for the level of detail requested — facility KPIs, individual drill-down, or adoption metrics.
A clean table in chat. Weekly questions always include the prior week as context and flag whether a change is structural or a one-off. A short glossary covers only the terms used.
The governed codex — canonical metrics and definitions kept as versioned documents, separate from the warehouse — defines what each KPI means and how it's calculated. The AI reads it before generating any query, so the platform's numbers match the official reports and dashboards. An AI without an anchored source of truth is a risk, not an advantage.
Resolving the number is half the job. When productivity drops on a dominant sub-process, a causal model takes over and explains the drivers in plain operational language.
A causal attribution model (XGBoost + OLS with SHAP) is trained on real operational history. It doesn't predict — it attributes. When there's a meaningful week-over-week drop and the facility has a reliable model, it surfaces the driver automatically: a heavier mix of large items in sorting, more staff assigned than volume justified, idle time. Outputs are always translated to operational language, never raw coefficients. If the model isn't confident for that facility, the platform shows only the observed numbers.
This is the kind of system I design and ship. Let's talk about your operation.
Get in touch