Tutorials Prompt Engineering Tutorial
AI Analytics Dashboard — PromptVerse Project
AI Analytics Dashboard — PromptVerse Project: free step-by-step lesson with examples, common mistakes, and interview tips — part of Prompt Engineering Tutorial on Toolliyo Academy.
On this page
Prompt Engineering Tutorial · Lesson 97 of 100
AI Analytics Dashboard
Prompts ✓ → Apps
Apps · 2 — RAG & agents · ~10 min · Module 10: Real-World AI Projects
What is this?
PromptVerse Analytics Dashboard turns NL questions into approved metric cards — SQL template + narrative + chart spec.
Why should you care?
Execs ask questions in Slack; bot returns consistent metric definitions not ad-hoc SQL hallucinations.
See it live — copy this example
Copy the prompt into ChatGPT, Claude, or your LLM API playground and compare outputs.
SYSTEM: Analytics Bot. Use METRIC_CATALOG only. SQL from template id. Narrative: describe numbers only, no causal claims.
USER: QUESTION: (nl) METRIC_CATALOG: (approved list)
EXPECTED: { metric_id, sql_params: object, narrative: string, chart: { type, x, y }, refresh_at: iso8601 }What happened?
- metric_id ties to vetted SQL template.
- chart spec lets UI render without second LLM call.
Practice next
- Define 3 metrics in catalog.
- Ask NL question matching one.
- Validate sql_params keys.
- Add comparison period param.
- refresh_at from warehouse sync time.
Remember
Catalog-backed metrics. Template SQL only. Chart spec for UI.
Slack metric bot
CEO asks MRR trend.
Outcome: Card renders line chart + 2-sentence narrative.
Interview prep for this lesson
Practice these questions aloud after reading—each links to a full structured answer.
Sign in to ask a question or upvote helpful answers.
No questions yet — be the first to ask!
