> For the complete documentation index, see [llms.txt](https://docs.tabiya.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tabiya.org/ethiopia/roadmap.md).

# Roadmap

### *Where things currently stand*

The skills-based matching approach Tabiya developed with government partners in South Africa and Kenya now runs on the E-LMIS team's own infrastructure. The team has deployed the matching service locally, generating skill embeddings with an open-weight model on their own servers, using a localised Ethiopian taxonomy (refinement in progress) of roughly 14,000 ESCO-aligned skills.

Tabiya serves as the ministry's main technology and technical-assistance partner for the E-LMIS, co-leading the digitalisation workstreams. The two teams have localised the base taxonomy — around 80% complete, with human review  continuing on the remainder and it is already in use in the matching pilot. Tabiya has also helped the E-LMIS team define key performance indicators and validate the metrics being built into their analytics platform. A taxonomy management application, which would make the taxonomy a maintained living resource rather than a static dataset, is being scoped.

***Piloting**: The collaboration positions the 18 model Job Centers as a demonstration site for how open-source digital public goods and AI-enabled tools can strengthen government-led employment services. A guiding principle is that these tools support rather than replace human-delivered services: their outputs are decision-support for counselors, not automated determinations of eligibility, benefits, or employment outcomes.*&#x20;

### *What's next?*

MoLS and the E-LMIS team have scoped around nine priorities for the modernisation of Ethiopia's public employment system. Tabiya is an active delivery partner on four of them - the living Ethiopian taxonomy, skills extraction and vacancy structuring, skills-based matching, and labor intelligence layer, and provides continued advisory and technical guidance across the rest.

These four form a single chain. The **taxonomy** gives every occupation and skill a shared name. **Extraction** turns unstructured vacancy text into structured skills expressed in that vocabulary. **Matching** compares supply and demand once both sides are anchored in it. An **analytics and intelligence layer** opens the system's growing supply- and demand-side data to non-technical decision-makers through plain-language querying, and enrich it with signals from elsewhere in government.

**Inclusive and bias-aware career guidance** is an upcoming priority. It determines whether a jobseeker's skills including those built in informal, unpaid and household work — enter the system accurately in the first place. Eliciting someone's skills and helping them think about their working future are the same conversation from the jobseeker's side, and the E-LMIS  team's plans for its My Career and MyFuture portals overlap directly with Tabiya's Compass, deployed in Argentina, Kenya, South Africa and Zambia.

Across the remaining priorities, Tabiya's role is advisory: helping scope what is feasible, and where its open-source components could contribute. Each depends on funding, data access, and decisions that sit with the ministry. These include a National Recruitment Platform, verifiable credentials built on Ethiopia's Fayda digital ID, the packaging of E-LMIS components as digital  public goods, and a national skill bank and skill libraries. Each depends on funding, data access, and decisions that sit with the ministry.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.tabiya.org/ethiopia/roadmap.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
