ONDA Overview
ONDA: Observer-Native Dialog Architecture
Section titled “ONDA: Observer-Native Dialog Architecture”ONDA is the core paradigm behind Plugy. It treats the chatbot not as a stateless request-response system but as a coherent observer that reads context, reasons, retrieves knowledge, responds, and then learns from the outcome.
Philosophy
Section titled “Philosophy”Traditional chatbots are “thermometers” — they measure and forget. ONDA builds “thermostats” — systems that measure, act, observe the result, and modify themselves.
The 4-Tact Cognitive Cycle
Section titled “The 4-Tact Cognitive Cycle”Every incoming message passes through four tacts:
| Tact | Name | Mode | What Happens |
|---|---|---|---|
| 1 | SCAN | Expansion | Load memory (recent + summary + profile), extract session facts |
| 2 | THINK | Compression | Fast model analyzes emotion, intent, tone, topic |
| 3 | RETRIEVE | Expansion | Semantic search retrieves relevant knowledge base entries |
| 4 | RESPOND | Compression | Primary model generates the response using enriched context |
After the response is sent, asynchronous tasks update memory and compute B-scores.
B-Score: The Coherence Metric
Section titled “B-Score: The Coherence Metric”B-score measures the quality of each bot response as a weighted geometric mean of four components:
| Component | Symbol | Measures |
|---|---|---|
| Focus | F | Relevance of the answer to the user’s question |
| Empathy | E | Alignment with instructions, emotional attunement |
| Consistency | 1-sigma | Non-contradiction with prior answers and knowledge base |
| Experience | Lambda | Use of conversation history and feedback |
Weak-link rule: If any single component is zero, the entire B-score collapses to zero.
Activation Operator
Section titled “Activation Operator”Before generating a response, the RESPOND tact applies four verification checks:
[A_F]— Is my response focused on the client’s actual need?[A_E]— Does my tone match the recommended tone from THINK analysis?[A_sigma]— Does my response contradict any known facts from client context?[A_Lambda]— Am I using relevant past resolution patterns from the knowledge base?
Three-Level Learning
Section titled “Three-Level Learning”| Level | Scope | Mechanism |
|---|---|---|
| Client | Single conversation | Recent message history, session facts |
| Project | One bot instance | Conversation summaries, persona optimization, knowledge rules |
| Global | Cross-project | Client profiles, cross-project knowledge sharing |
The Strange Loop
Section titled “The Strange Loop”The self-learning system forms a feedback loop: the bot generates responses, the ONDA system observes those responses, measures B-scores, proposes improvements, and feeds improved configurations back into the bot. The observer observes itself observing.
See Self-Learning for how ONDA improves your bot over time.