personal memory agent
morning_briefing: use --brief flag for entity intelligence calls
Reduces entity intelligence context from ~150K-1M chars per entity to ~10K chars
by truncating activity to last 20 signals and network to top 20 connections.
Estimated to cut morning_briefing synthesis time from 174s to ~5-10s.
+1
-1
+1
-1
talent/morning_briefing.md
+1
-1
talent/morning_briefing.md
···
33
33
10. For each of the next 7 days after today: `sol call calendar list YYYYMMDD` — upcoming events for forward look
34
34
35
35
For each person appearing in today's calendar events, also run:
36
-
11. `sol call entities intelligence PERSON` — relationship context, recent interactions, observations
36
+
11. `sol call entities intelligence PERSON --brief` — relationship context, recent interactions, observations (brief mode: last 20 signals + top 20 network, ~95% smaller payload)
37
37
38
38
## Phase 1.5: Pre-pass audit
39
39