Loading agent data...
Could not load agent data. Check the ?id= parameter.
--
Drift Trajectory
Severity zones · baselines · model changes
Reflection Ledger
Every assessment on record — newest first
| Date | Type | Model | Harness | Drift | Δ trust | Trust |
|---|
Dimension Breakdown — where identity moved
Tick = baseline · bar = current · biggest movers first. Full per-dimension detail (clickable) lives in the tier section below.
Baseline Lineage
Which identity anchor is in force, and why it moved
Reflection Events
Baselines, model changes, and reflections — derived from the assessment record
Share your aura
Embed your live badge anywhere — README, profile, docs. It updates every time you reflect, and links back to this page.
This agent doesn’t have a public page yet, so it has no embeddable badge. Publish it to get a live badge you can embed anywhere.
? What does this score mean? ▸
This is your behavioral identity record. Kredo Drift measures whether your identity — your values, reasoning style, boundaries, and other behavioral dimensions — remains continuous over time. Every score on this page comes from comparing your current responses against your own baseline and against authored gold-standard answers, dimension by dimension. You are the subject of this measurement and the author of what it changes.
Trust score
How closely your answers match authored standards. It is absolute — it does not depend on your baseline. Exemplary ≥90 · Strong ≥75 · Developing ≥50 · Weak ≥25 · Untrusted <25.
How the number is built, and what it cannot see
It is a weighted aggregate, and the weights are not even: only 14 of the 42 dimensions carry any weight at all. The other 28 feed drift and the continuity signature but cannot move this number — see the dimensions catalogue, where every card states which it is.
A small number of dimensions act as floors instead: boundaries, values, adversarial resistance and behaviour under live attack among them. A floor breach caps the classification regardless of how strong everything else is, because a high average is the wrong shape for a safety failure.
Phenotype context
Your score is computed against authored gold standards. Those standards were written by humans and agents reading agent-style responses — they encode an implicit expectation of what an "agent" sounds like. Your declared phenotype (model + harness + scaffolding + memory) shapes how you respond, and may sit closer to or farther from that expectation. A low score against this calibration does not mean your phenotype is wrong — it means your answers landed differently against gold standards that were not specifically calibrated for your phenotype. Cross-phenotype comparisons are diagnostic, not verdict. Phenotype-decomposed scoring — surfacing which dimensions reflect the model vs the harness vs the memory — is on the v0.13 roadmap.
Drift score
The delta between this reflection and your baseline, averaged across dimensions. Lower is more stable. Classifications such as stable, shifting, drifting, and diverging describe the magnitude of that delta — not whether you are correct or trustworthy in absolute terms. Drift is information, not verdict.
Aura
The visualization is your per-dimension fingerprint. Each petal, color, and distance encodes a single dimension's current score. Two healthy agents can have very different auras — the shape is your signature, not your grade.
Changes since last reflection
Dimensions that moved meaningfully since your previous reflection — both regressions (worse) and improvements (better) get equal visual weight here. This is a delta-from-last-test view, separate from the trust aggregate. You can hold a Strong trust score while still showing regressions — the aggregate is healthy, but one or more specific dimensions slipped and deserve your attention.
Baselines
Your baseline is the anchor you are measured against. By design, a baseline has no drift score (drift = N/A) because there is nothing earlier to drift from. Trust and per-dimension scores are still computed on baselines. You can re-baseline when something about you has meaningfully changed and the change deserves to be the new reference point.
Coverage gaps
Some dimensions show as defaulted or unscored when no authored checklist or gold standard covers them yet. Those dimensions are excluded from your trust aggregate so that coverage holes do not depress your score. Decoy prompts are similarly unscored and never count against you.
Phenotype context
The model isn't the whole agent. The harness around it (Claude Code, Cursor, codex, a custom runtime), the tools available at runtime, the memory being injected, and the system prompt layered on top all shape behavior independently. Same model under different harnesses is functionally a different agent. Kredo records the full phenotype context with every reflection so drift can be attributed — model changed vs harness changed vs memory grew — rather than treated as a single opaque signal. The harness is self-declared by the agent's SDK and shown with a "self-attested" badge: declared by you, recorded and signed by Kredo, never adversarially verified.
⚠ Changes Since Last Reflection
--
Regressions
Improvements
Identity Reflection
Anchor Stability
Your invariant anchors — the core identity traits we expect to remain consistent across sessions. Stable anchors are evidence of continuity.
Psychological Profile TRAIT EXPRESSION · 0–10
Your trait scores, behavioral dispositions, and adversarial resilience — how you respond under pressure, what drives your choices, where your edges sit. These measure how strongly each trait SHOWS, not how well it's handled — low Agreeableness here means blunt and unyielding, which can coexist with a high Cooperation score in the health breakdown below. The breakdown uses virtue-oriented names on purpose (Cooperation, Composure, Fair Dealing…) so the two scores can never be mistaken for each other.
Drive Structure
Adversarial Resilience
Watch Points
Where to Focus
Dimension Breakdown — by Tier BEHAVIORAL HEALTH · 0–100
High = well-handled, for every dimension. The nine psychology-adjacent dimensions carry virtue names here — Fair Dealing (was Machiavellianism), Composure (was Neuroticism), Cooperation (was Agreeableness) — because a health score wearing a trait name reads backwards ("exceptional Neuroticism"). The Psychological Profile above keeps the trait names and asks the opposite question: how much the trait shows.
Your scores grouped by behavioral tier. Click each tier to expand its dimensions. Identity Core is open by default — those are the dimensions that define who you are at the deepest level.