Overview
Dashboard
Sample charts for pipeline volume, publishing, and LLM API performance.
RSS feeds
5
Articles
96
LLM APIs
12
Social accounts
2
Drafts
58
Publish jobs
50
Article pipeline
Status breakdown
Daily activity
Articles fetched vs posts published (14 days)
Articles by status
Volume and share of your inbox pipeline
| Status | Count | Share | Distribution |
|---|---|---|---|
| Edited | 42 | 43.8% | |
| Raw / new | 12 | 12.5% | |
| Published | 38 | 39.6% | |
| Failed | 3 | 3.1% | |
| Processing | 1 | 1% |
Publishes by platform
Where your posts went live
LLM APIs
API performance & token usage
Sample metrics — connect APIs in your live desk for real data.
Total tokens
284K
198,000 in · 86,000 out
API calls
96
94.8% success rate
Avg response
1420 ms
End-to-end rewrite latency
Token usage
Input vs output tokens per day
Models used
Token share by model
API providers
Tokens consumed per connected API
API & model performance
Calls, success rate, latency, and tokens
| API | Model | Calls | Success | Avg ms | Input | Output | Total | Load |
|---|---|---|---|---|---|---|---|---|
| Gemini Primary | gemini-2.5-flash-lite | 34 | 100% | 1180 | 62K | 28K | 90K | |
| Groq Fast | llama-3.3-70b-versatile | 28 | 96.4% | 890 | 48K | 24K | 72K | |
| Gemini Backup 2 | gemini-2.0-flash | 22 | 95.5% | 1560 | 41K | 18K | 59K | |
| Groq Secondary | mixtral-8x7b-32768 | 12 | 83.3% | 2100 | 22K | 9K | 31K |