analyst.ai: investment research (provisional)
Published results cover 54 fixed-packet research tasks per product label. Another 18 live-web tasks are planned and excluded from current results.
analyst.ai · Published 2026-10-22 · reviewed 2026-10-29
Scope and method
Six groups × nine packet tasks; four fictional investor profiles. No brokerage connection or trades.
Separates calculations, evidential support, investor constraints and usability; a fixed recheck is not autonomous monitoring.
How PAEval uses it
Provisional method reference; no live-research or trading score imported.
Evidence family: analyst-personal-assistants-2026-10. Shared tasks and tracks are not independent evidence votes.
Limits and interpretation
- Shared unresolved product identity, unequal conversation histories and missing full evidence pack.
- Packet results cannot fill unrun live-web or ongoing-monitoring panels.
Sources and reuse
PAEval summarizes existing published evidence and runs no new tests. Public readability does not establish permission to redistribute full datasets, conversations or images.
Related tracks from the same family
analyst.ai: information lookup (provisional) · analyst.ai: personal email (provisional) · analyst.ai: household money (provisional)
All benchmark sources → · How to read outcomes and intervention →