gabspereira/talk-to-data-case-study
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: add talk-to-data case study

Browse Source 
Add anonymized architecture, governance examples, diagrams, and interview materials.\n\nCo-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
@gabriel.pereira
2026-09-11 10:36:16 -03:00
commit 9e9ae249bc
12 changed files with 1229 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
case_study_one_page.html Normal file
View File

@@ -0,0 +1,49 @@
<!doctype html>
<html>
<head>
<meta charset="utf-8">
<title>Talk-to-Data Case Study</title>
<style>
@page{size:A4;margin:14mm}body{font-family:Arial,sans-serif;color:#1f2933;font-size:10pt;line-height:1.25}h1{color:#0b4f71;font-size:24pt;margin:0 0 2pt}h2{color:#0b4f71;font-size:13pt;margin:10pt 0 4pt;border-bottom:1px solid #b8c9d3;padding-bottom:2pt}p{margin:4pt 0}table{width:100%;border-collapse:collapse;margin:4pt 0 7pt;font-size:9pt}th{background:#0b4f71;color:#fff;text-align:left}th,td{border:1px solid #cbd5e1;padding:4pt;vertical-align:top}pre{background:#eef4f7;padding:6pt;border-left:3px solid #0b4f71;font-size:8pt}strong{color:#0b4f71}
</style>
</head>
<body>
<h1>Talk-to-Data</h1>
<p><strong>Governance-first semantic analytics for enterprise quotation workflows</strong></p>
<h2>The challenge</h2>
<p>More than 30 salespeople could depend on internal experts to answer routine quotation questions about products, discounts, and customer agreements. Manual lookup and email or chat coordination introduced an estimated <strong>5–30 minute delay per question</strong>.</p>
<h2>The approach</h2>
<p>Build a proof of concept around a curated semantic layer instead of exposing raw enterprise tables to an LLM.</p>
<pre>SAP ERP
│ daily batch
▼
Snowflake raw → dbt staging → dbt transforms
│
▼
Semantic views
│
▼
Cortex guardrails & audit
┌────────┴────────┐
▼ ▼
Snowflake UI Internal chatbot</pre>
<h2>Architecture decisions</h2>
<table><tr><th>Decision</th><th>Why</th></tr>
<tr><td>Snowflake + Cortex</td><td>Fast POC path with data, AI, and governance in one platform.</td></tr>
<tr><td>dbt layers</td><td>Reproducible SQL, lineage, testing, and versioned business logic.</td></tr>
<tr><td>Semantic views</td><td>One business contract for dashboards and natural-language queries.</td></tr>
<tr><td>Daily refresh</td><td>Sufficient for quotation research; avoids premature real-time complexity.</td></tr>
<tr><td>Guardrails in data layer</td><td>Protection of personal and customer information, access control, freshness checks, and exception escalation are enforceable—not only prompt instructions.</td></tr></table>
<h2>Estimated outcome</h2>
<table><tr><th>Signal</th><th>Estimate</th></tr>
<tr><td>Routine answer latency</td><td><strong>5–30 min → &lt;1 min</strong></td></tr>
<tr><td>Sales users in scope</td><td><strong>30+</strong></td></tr>
<tr><td>Data freshness</td><td><strong>Daily batch</strong></td></tr>
<tr><td>Main benefit</td><td>Less coordination overhead and faster quote responses.</td></tr></table>
<p>These are <strong>estimates based on the human workflow</strong>, not measured production KPIs. The next delivery step is a controlled pilot that captures actual latency, adoption, escalation rate, and answer quality.</p>
<h2>Delivery lesson</h2>
<p>The reusable asset was not just the chatbot. It was the delivery pattern: establish the semantic contract, encode business rules, apply governance, and then expose the smallest useful interface.</p>
<p><strong>Stack:</strong> SAP source system · Snowflake · dbt · Snowflake semantic views · Cortex Analytics · internal chatbot workspace</p>
<p><em>All examples are anonymized and contain no proprietary source data.</em></p>
</body>
</html>