docs: add AI Chat Showcase — public technical writeup for GitHub

doc/29-AI-CHAT-SHOWCASE.md: comprehensive technical showcase covering
the AI-powered CV navigation feature for potential clients/employers.

9 technical decisions explained with code:
1. ADK Go 1.0 as agent framework
2. Single agent, single tool design
3. Cross-section search across all CV data
4. CV navigation links (GPS for the CV)
5. Dual-provider with auto-fallback (Gemini→Ollama)
6. Model warmup on chat open
7. HTMX + plain JS (no SPA framework)
8. Rate limiting (30 req/hour/IP)
9. Graceful degradation

Linked from README.md and doc index.
This commit is contained in:
juanatsap
2026-04-08 17:13:18 +01:00
parent c44e9e8c67
commit afa93be8fe
3 changed files with 253 additions and 1 deletions
+9 -1
View File
@@ -36,7 +36,7 @@ This documentation covers the core Go systems that power the CV site, with a foc
- Coverage gap explanations
- Best practices and CI/CD integration
5. **[AI Chat Agent — CV Assistant Mascot](28-AI-CHAT-AGENT.md)** (~500 lines)
5. **[AI Chat Agent — CV Assistant Mascot](28-AI-CHAT-AGENT.md)** (~544 lines)
- Complete mascot feature reference: architecture, components, intelligence
- ADK Go 1.0 integration with Gemini 2.5 Flash
- Agent definition with query_cv tool (11 section types, cross-section search)
@@ -47,6 +47,14 @@ This documentation covers the core Go systems that power the CV site, with a foc
- Design system integration (CSS tokens, dark theme, responsive)
- Graceful degradation, security, and testing (46 Playwright assertions)
6. **[AI Chat Showcase — Technical Writeup](29-AI-CHAT-SHOWCASE.md)** (~250 lines)
- Public-facing technical showcase of the AI chat feature
- Architecture diagram with dual-provider fallback
- 9 key technical decisions explained with code examples
- CV navigation links (GPS for the CV)
- Technology stack and file structure
- What this demonstrates for potential employers/clients
## Quick Navigation
### By Feature