FN2 AI launches earnings call semantic search and scheduled briefings
Understand this story
FN2 AI launches fn2 skill, enabling Claude Code to perform semantic retrieval over 10,602,684 embedding vectors from 142,758 earnings calls; these embeddings are generated by Qwen3-Embedding-8B (4096d). This feature is available to logged-in Pro plan users and requires device token credentials. Users can set up scheduled email briefings: search results are sent to their email 30 minutes before the market open on each US stock trading day (Eastern Time).
AI overview based on source reports · Updated 3 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Connect Claude Code to 10.6M Earnings Call Embeddings with FN2 AI
A Show HN post demonstrates using the FN2 skill to run a semantic search over 10,602,684 embedded passages from 142,758 earnings calls, answering a question about NVDA management commentary on Blackwell supply with quoted and cited results. The example shows a run completing in 35s using Qwen3-Embedding-8B (4096d), then scheduling a recurring pre-market NVDA brief with email delivery that resolves "before market open" against the exchange calendar. The post also shows an `agents` listing of existing scheduled agents, including one with 53 runs and two possible duplicates.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 12 01:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.