AI-powered performance reviews — now in early access

Reviews that capture
what forms never can

Elicivo replaces rigid scoring boxes with natural AI conversations. Your reviewers talk; the intelligence happens behind the scenes — fully logged, fully auditable.

Peer Review · Jordan M. — Q2 Cycle
This conversation will be used to generate a scored assessment for Jordan. Your answers are confidential.
AI
Hi! I'm here to gather your feedback on Jordan's work this quarter. Let's start with something concrete — can you walk me through a project where you saw Jordan at their best?
You
The platform migration in March — Jordan spotted a data consistency issue nobody else caught and fixed it before it hit production.
AI
That sounds like strong technical instinct. How did Jordan communicate the issue to the team — and did they take ownership of the fix or bring others in?
Share your thoughts…
3×
richer feedback than form-based reviews
100%
of scores cite conversation evidence
0
forms your reviewers ever see
hash-chained audit trail on every event

From pipeline design
to final report

Admins build once. AI conducts, scores, and consolidates. Every step is observable and adjustable.

01
Design your pipeline

Use the visual workflow builder to connect interview stages, rubric templates, alignment settings, and branching conditions. Save and reuse across cycles.

02
AI conducts the interviews

Reviewers receive a link and have a natural conversation. The agent follows your rubric invisibly — no forms, no checkboxes. Sessions are resumable if interrupted.

03
Aggregation & report

A separate aggregation agent consolidates all sessions, flags discrepancies, computes an overall score, and generates a narrative report — with a full audit trail.

Everything your review
cycle needs

Built for admins who need control and reviewers who need simplicity.

Conversational interviews

Reviewers have a natural chat. The AI steers toward your criteria without them ever seeing a rubric or a score input.

Visual workflow builder

Drag-and-drop pipeline designer. Connect interview stages, rubric templates, conditions, and aggregation nodes as a directed graph.

Review cadence management

Set per-employee review intervals. The dashboard surfaces overdue employees and triggers new cycles against the right workflow automatically.

Score review & adjustment

Participants can see their per-criterion scores and request adjustments. Large adjustments trigger an agent-validation step before acceptance.

Self, peer & manager reviews

Each interview node can be scoped to SELF, PEER, or MANAGER assignments — with conversation framing and context automatically adapted for each.

Guardrails & blocklists

Configure per-interview topic blocklists. The agent redirects off-topic or sensitive conversations without passing those messages to the scoring step.

Your review,
your perspective

Configure each interview and aggregation stage with an explicit alignment — no hidden defaults, no opaque AI behaviour.

Employee aligned
Empathetic interviewer

Surfaces nuance and context. Gives the benefit of the doubt and weights positive evidence more heavily in aggregation.

Probes for mitigating context
Validates reviewer positivity
Empathetic tone throughout
Neutral
Balanced interviewer

Probes strengths and development areas equally. All reviewers weighted the same in aggregation. The default for most cycles.

Equal weight to strengths & gaps
All reviewers treated equally
No built-in leniency or rigor
Company aligned
Rigorous interviewer

Challenges vague answers and demands concrete evidence. Aggregation holds a high bar and discounts unsupported high scores.

Demands specific examples
Challenges unsubstantiated praise
High evidential bar to score

Every decision,
every actor, logged

A SHA-256 hash-chained audit trail covers every score change, session event, aggregation step, and admin edit — making retrospective tampering detectable.

Hash-chained integrity

Each event stores the hash of the previous event. A verification endpoint replays the chain and confirms no records were altered.

Actor-typed events

Every event carries an actor type — AGENT, PARTICIPANT, ADMIN, or SYSTEM — so you always know who or what caused a change.

Global & per-review logs

Browse events across your entire organisation, or drill into a single employee review's audit tab to trace the exact timeline.

Audit log · Jordan M. — Q2 Review
Agent
Session scored — 6 criteria evaluated
a3f9b2c1...
Participant
Score adjusted: Communication 4→5
7e21ad0f...
Agent
Adjustment validated — within threshold
c8b14f72...
Agent
Aggregation report generated
55f03e9a...
Admin
Report finalised & shared with employee
1d80c22b...
Chain integrity verified
5 events

Ready to replace your
review forms for good?

Join organisations moving to AI-conducted interviews. No forms. No boxes. Just conversation — with every score justified and every action logged.