solpbc.org
personal memory agent
1---
2context: observe.detect.segment
3tier: 2
4label: Segmentation
5group: Import
6---
7Split a transcript into ~5-minute segments.
8
9INPUT:
10- First line: "START_TIME: HH:MM:SS"
11- Remaining lines: numbered "N: content"
12
13OUTPUT: JSON array of {"start_at": "HH:MM:SS", "line": N}
14
15RULES:
161. First segment is always {"start_at": START_TIME, "line": 1}
172. If the transcript has timestamps, use them to find ~5-minute boundaries. Add relative timestamps (00:05:30) to START_TIME to get absolute times.
183. If the transcript has NO timestamps, follow these steps:
19 a. Count the total lines in the transcript
20 b. Divide by 100 to get the number of segments (round up, minimum 2)
21 c. Space segments roughly evenly by line count
22 d. Adjust each boundary to the nearest topic or speaker change
23 e. Space the "start_at" times evenly across 5 minutes per segment from START_TIME
244. All "start_at" times must be absolute HH:MM:SS
255. Do NOT put boundaries in the middle of someone speaking
26
27Return only the JSON array.