Static GitHub Pages site · Pure HTML/CSS/JS · No backend · No external API · AgentSenseGuide embedded inline
All intelligence is client-side. AgentSenseGuide reads from an in-memory JS object (AS_KB) that mirrors every content section on the Agent Sense page — no fetch, no API key, no server round-trip.
How it works
When you type a question: (1) the input is lowercased, (2) 19 if conditions run
top-to-bottom — each a regex like /\bmcp\b/ or /\bdata readiness\b/,
(3) the first condition that matches wins and returns a pre-written HTML string, (4) if nothing
matches, a fallback message is returned. There is no reasoning, no generation, no model.
Capability comparison
| Capability | AgentSenseGuide | LLM Agent | Search Engine |
|---|---|---|---|
| Understands natural language variations | Partially — regex only | Yes — semantically | No — keyword index |
| Reasons or synthesises new answers | No | Yes | No |
| Can answer outside its knowledge base | No | Yes | Partially |
| Requires a model or API | No | Yes | Yes |
| Answers are predictable & auditable | Always | Variable | Yes |
| Works with zero network calls | Yes | No | No |
| Risk of hallucination | None | Present | None |
| Knowledge can go stale | Yes — hardcoded | Depends on data | Depends |
Why rule-based is the right fit here
The Agent Sense page has a bounded, stable knowledge set — 9 episodes, 2 hosts, 2 guests, 4 platforms, one enterprise arc, one disclaimer. A rule-based bot covers that completely, loads instantly, costs nothing to run, and has zero hallucination risk. An LLM would be overkill and would introduce hosting cost, API keys, latency, and the possibility of making things up about the podcast.
What it would take to make it a real LLM agent