| SERIES | AI in OSINT · Field report |
| ID | AIO-010 |
| PROMPT | Longitudinal alias profiling prompt |
| TESTED ON | Claude (Anthropic), 15 November 2026 |
An alias that has been active across a decade leaves a structured record. The signals do not all point the same direction. The question is not what the alias looks like now. It is what the progression tells you about the person behind it.
THE PROBLEM
Long-running aliases present a specific analytical challenge. A handle that has been active since 2014 has accumulated signals across multiple platforms, in multiple contexts, and through multiple behavioural phases. The earliest posts may reflect a different register, a different location, or a different set of preoccupations than the most recent ones. The signals are internally inconsistent not because they belong to different people but because the same person has changed over a decade.
The manual approach to longitudinal alias analysis is chronological review: start at the earliest archived post, work forward, note the shifts. That is methodologically sound but extremely time-consuming when the signal set spans hundreds of posts across multiple platforms and years. The analyst ends up with a timeline but without a structured assessment of which signals are stable across the decade (and therefore high-confidence indicators of underlying identity) and which are variable (phase-specific and therefore less reliable as identity anchors).
The problem is compounded by the nature of identity signals over time. An alias might use consistent spelling and grammar across ten years (a stable signal), switch platforms twice (variable, platform-specific), post from three different apparent time zones (variable, may reflect travel or VPN use), and maintain a consistent technical vocabulary in their area of expertise (stable, strongly correlated with underlying identity). Distinguishing stable from variable signals across a large longitudinal dataset is exactly the kind of structured pattern extraction that benefits from AI assistance.
What the AI contributes to longitudinal alias analysis is temporal signal stratification. Given a chronologically organised set of posts or activity records, the model can identify which signals remain consistent across the full time period (and are therefore reliable identity anchors), which signals show phased change (and may reflect life events, location changes, or deliberate alias management), and which signals are point-in-time (appearing in a specific window and not before or after).
The rest of this prompt is for Signal subscribers.
What remains: the full prompt, the output schema, the discriminating checks, and the conditions under which the model's answer should not be trusted.
Join SignalAlready a subscriber? Sign in
A Signal subscription gives you:
- Full OSINT Reference Card library, 21 domains
- Methods, every tradecraft tutorial in full
- AI in OSINT, every tutorial and field report
- OSINT Hub community access

