---
title: 'Estonian Unemployment Insurance Fund: OTT employment-prospect decision support'
slug: estonia-ott-employment-triage
stable_id: 269fe23a18088810
company: Estonian Unemployment Insurance Fund
function_code: customer_service
pattern_codes:
  - autonomous_with_backstop
  - continuous_decisioning
evidence_strength: reported
publication_tier: showcase
freshness: current
reviewed_at: '2026-08-23'
updated_at: '2026-08-22'
source_quality_summary: 1 independent, 1 primary; publication outcomes are reported.
caveat_summary: OTT2 98% is prospective and is not counted as achieved.
collections: []
bundle_version: 1.0.0
bundle_fingerprint: sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93
canonical_url: https://brianletort.ai/transformations/estonia-ott-employment-triage
---

# Estonian Unemployment Insurance Fund: OTT employment-prospect decision support

Counselling intensity can be allocated from updated risk evidence instead of manual synthesis alone.

Function: Customer service. Patterns: Autonomous with a backstop; Continuous decisioning. Evidence: reported.

Freshness: current. Reviewed: 2026-08-23. Updated: 2026-08-22.


Source quality: 1 independent, 1 primary; publication outcomes are reported.

## Before

1. **Newly registered jobseeker** — Provides registration information to the Estonian Unemployment Insurance Fund. (control: OTT1 created one employment-prospect assessment at registration.)
2. **Employment counsellor** — Interprets the one-time score with the client record and allocates support. (control: Counsellor owns service choice; published sources do not report a pre-OTT manual cycle time.)

## After

1. **OTT2** — Combines registry events and client changes to refresh employment-prospect assessments regularly. (control: Model is periodically retrained, does not self-modify, and explains influential factors.)
2. **Employment counsellor** — Reviews the current assessment and focuses intensive support on higher-risk clients. (control: Human service decision; the >98% OTT2 target remains under 2026 pilot evaluation.)

## Decision rights

Counsellors own interventions; the model is periodically retrained and does not change autonomously.

## Exception path

Contradictory or changed circumstances receive counsellor review; OTT2 refreshes assessments.

## Outcomes

- **Prediction accuracy** (reported): Manual, laborious risk assessment → OTT1 achieved over 95% prediction accuracy; OTT2 above 98% remains a 2026 pilot target. OTT2 98% is prospective and is not counted as achieved.

## Executive lesson

Separate realized OTT1 evidence from OTT2 pilot expectations.

## Anti-pattern

Do not publish forecast OTT2 accuracy as achieved.

## Questions for leaders

- Where is the operating threshold set and who can override it?
- What measured result would trigger rollback or retraining?
- Which residual decisions must remain human-owned?

## Sources

- [OTT2: Dynamic Data-Driven Personalisation of Employment Services](https://oecd.ai/en/dashboards/policy-initiatives/ott2-dynamic-data-driven-personalisation-of-employment-services-and-counsellor-decision-support) — OECD.AI
- [AI to help serve the Estonian unemployed](https://e-estonia.com/ai-to-help-serve-the-estonian-unemployed/) — e-Estonia