Plain-English Analytics
Business Intelligence SaaS · Analytics Chat / Natural-Language Data
Plain-English questions answered as tables and charts, within each organization's data
Small and mid-size businesses needed analytics without analysts. Datics built a business-intelligence platform whose AI chat turns a plain-English question into SQL over the organization's own database and answers with a table, a chart or a short summary, along with dashboards, organization management and access control.
- Status
- In production
- Engagement
- September 2024 to early 2026
Analytics Chat / Natural-Language Data
Dashboards
Where charts and summaries are generated and kept.
- Plain-English questions
- Multiple databases
- Dashboard agent
- Organizations and access
Multi-tenant SaaS with organization-scoped data.
The starting point
Business users had their operating data in their own databases, but every new question meant a report request or a spreadsheet.
What had to change
Small teams needed analytics without analysts: fast answers to new questions, in their own terms.
What couldn't break
Every answer had to stay inside the right organization's data and respect who is allowed to see what.
Why this was hard
Text-to-SQL has to be trained on each database's schema and vocabulary, connect to different database types, and return something a non-analyst can read.
What Datics changed
Datics built the chat with text-to-SQL, training and query generation, connectors for MySQL, PostgreSQL and ODBC sources, chart rendering in the conversation, a dashboard agent, organization profiles and summaries, and super-admin access control.
Delivered in milestones from 2024, starting with chat and dashboards, then multi-database support, a dashboard agent and a SaaS edition, with QA readiness passes and a knowledge transfer at handover.
Plain-English questions
Questions turned into SQL and answered as tables, charts or text.
Multiple databases
MySQL, PostgreSQL and ODBC connections per organization.
Dashboard agent
Dashboards and summaries generated from live data.
Organizations and access
Organization management and super-admin access control.
How it works
Connects to: Each organization's own databases.
- 1
Ask
Where users ask questions of their data.
- 2
Dashboards
Where charts and summaries are generated and kept.
- 3
Organizations & Access
Where organizations, users and connections are managed.
Runs within: Multi-tenant SaaS with organization-scoped data.
Engagement at a glance
Business users go from a question to a chart or table on their own data, without a report request.
- AI surface
- Text-to-SQL chat with charts
- Data sources
- MySQL, PostgreSQL and ODBC
- Delivery
- Milestones from 2024 to handover in 2026
Under the hood
- Datics role
- Product management, UI/UX, front-end, back-end, AI engineering, QA and DevOps.
- Integrations
- Each organization's own databases.
- Deployment
- Cloud-hosted SaaS.
- Production boundary
- Multi-tenant SaaS with organization-scoped data.
Technology
What this unlocked
The same text-to-SQL pattern powers Cohortly, which answers enrollment, completion and retention questions inside SIS, analytics and LMS products.
Related work
Learning-agency directory
EdTech · Directory / Marketplace
A vetted, subscription directory that helps education buyers find and compare learning agencies
A members-only directory of vetted education agencies with search, filters, shortlists, moderated comments and Stripe subscriptions, built end to end in six milestones.
Leadership-development practice app
EdTech · Learning App / Mobile & Desktop
A leadership-development practice app taken from the web to iOS, Android and desktop
A daily leadership practice built on seven inner archetypes, taken from a web app to native iOS, Android, Windows, macOS and Linux apps from one codebase.
Voice Roleplay Trainer
Insurance Sales Training · Skills Practice / Voice AI
AI voice roleplay that makes skills practice measurable
Agents pick a scenario, a prospect personality and a difficulty, hold a live voice call with an AI prospect, and get a scorecard, transcript and coaching against the firm's own method.
Have a product with the same kind of constraints?
Tell us what already exists and what you want it to do. We will tell you what it takes.