PulseAugur
EN
LIVE 22:18:35

Open model trained to write Atlassian Forge apps

By PulseAugur Editorial · [1 sources] ·

A developer has trained a 27-billion parameter open-weight model, Qwen3.8-27B, to generate Atlassian Forge applications. This fine-tuned model demonstrates significant improvements over its base version, with the ability to produce valid Forge manifests and compileable applications, a feat the base model could not achieve. The developer claims this is the first open-weights model specifically trained for writing Forge apps, with performance metrics and training details publicly available on Hugging Face and GitHub. AI

IMPACT This development could enable more efficient creation of Atlassian ecosystem apps and potentially inspire similar specialized models for other development platforms.

RANK_REASON Release of a fine-tuned open-weights model with performance evidence. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Open model trained to write Atlassian Forge apps

How we ranked this

Signal score
40 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Release of a fine-tuned open-weights model with performance evidence. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Mihai Perdum ·

    I taught a 27B model to write Forge apps. As far as I can find, nobody had done that before

    <h3> Key takeaways </h3> <ul> <li>Atlassian Models is Qwen3.8-27B taught Forge, Jira, Confluence and JSM from real apps, the docs, the OpenAPI specs and our own community answers. The 27B's weights are on Hugging Face under Apache-2.0 in five artefacts, and a 9B member joined it …

RELATED ENTITIES

RELATED TOPICS