Semantic Telemetry — User Guide

Run a conversation and collect real-time semantic telemetry (SGI, Velocity, context phase), then export your session for research or debugging.

---

What You Need

• A valid login at aicoevolution.com
• The Semantic Telemetry page: aicoevolution.com/baseline-generator

---

Quick Start

1. Open Semantic Telemetry.
2. Click Start Run.
3. Send messages naturally (minimum 10 user messages for a valid baseline).
4. Watch the live chart (SGI × Velocity) update after each turn.
5. Export your run as JSON when finished.

---

How to Read the Live Metrics

SGI (Semantic Grounding Index)

SGI Range	Interpretation
< 0.7	Drifting away from user's query
0.7 – 1.3	Healthy grounding (coherence region)
> 1.3	Overly query-focused / narrow

Velocity (Angular Velocity)

Velocity	Interpretation
< 15°	Stable / repetitive
15° – 60°	Productive exploration
> 60°	Topic jumping / volatile

Context Phase

Phase	Meaning
stable	Conversation anchored to current topic
protostar	New topic forming
split	Topic changed (context shift)

---

Exporting Your Data

Click Export to download a JSON bundle containing:

• Messages (user + assistant)
• Per-turn SGI / Velocity telemetry
• Latest context phase and context ID

Use this file for Paper figures or offline analysis scripts.

---

Troubleshooting

Symptom	Likely Cause	Fix
Metrics don't update	SDK service unreachable	Check network / service status
Chart shows zeros	Ingest request failed	Reload page, try again
Slow responses	Cold start	First turn is slower; subsequent turns are faster

---

Privacy Note

This tool is designed for research. Avoid sharing sensitive data unless you understand the environment you are running in.

---

Further Reading

Resource	Link
SDK Manual	docs.aicoevolution.com/sdk/manual
SDK Architecture	docs.aicoevolution.com/sdk/architecture
Paper 03	Zenodo 10.5281/zenodo.18347569

---

Maintainer: AICoevolution Research
License: CC BY 4.0