Course Outline
Introduction to Conversational Analytics
- Understanding conversational analytics and its significance for product teams.
- Overview of WrenAI key capabilities and high-level architecture.
- Typical product team workflows facilitated by Wren AI.
Connecting Data Sources and Access
- Supported data sources and ingestion methods.
- Data access, permissions management, and multi-source joins.
- Best practices for sample datasets and sandbox environments.
Semantic Modeling and Metrics Standardization
- Designing a metrics layer and establishing canonical definitions.
- Creating reusable metrics and dimensions for product analytics.
- Versioning and governance of the semantic model.
Natural-Language to SQL Workflows
- Mechanism of WrenAI translating natural language queries to SQL and validation strategies.
- Prompting patterns and fallback options for product inquiries.
- Managing ambiguity, clarifying questions, and intent design.
Self-Service BI and Embedded Use Cases
- Designing conversational dashboards and templates for product teams.
- Embedding Wren AI into product workflows and internal tools.
- Measuring the adoption and impact of self-service analytics.
Quality, Evaluation, and Guardrails
- Testing NL-to-SQL accuracy and developing validation suites.
- Monitoring drift, data quality signals, and conducting query audits.
- Safety measures, access control, and business-rule guardrails.
Workshop: Build a Product Insights Flow
- Hands-on lab: modeling a product metric, creating conversational queries, and validating results.
- Assembling a self-service dashboard and user guidance.
- Presentations, feedback sessions, and next-step action plans.
Summary and Next Steps
Requirements
- Understanding of product metrics and Key Performance Indicators (KPIs).
- Experience with data analysis or Business Intelligence (BI) tools.
- Basic familiarity with SQL is advantageous.
Target Audience
- Product managers.
- Data analysts.
- Data champions within business units.
Testimonials (4)
Abhi has excellent knowledge of Alteryx and he explained things very clearly. He understood our goals and created bespoke demo datasets that were relevant to our organisation, which was very impressive. The training was well-structured and delivered at a good pace, with time for questions.
Samuel Taylor - Manchester Metropolitan University
Course - Alteryx for Data Analysis
Deepthi was super attuned to my needs, she could tell when to add layers of complexity and when to hold back and take a more structured approach. Deepthi truly worked at my pace and ensured I was able to use the new functions /tools myself by first showing then letting me recreate the items myself which really helped embed the training. I could not be happier with the results of this training and with the level of expertise of Deepthi!
Deepthi - Invest Northern Ireland
Course - IBM Cognos Analytics
he was well prepared - and he is very sympathetic
Oliver - Post CH AG
Course - Splunk Fundamentals
Used good examples, good pace of the training and covered most things
