Real Atlassian solutions to real problems — no fluff, no SEO spam.
I ran DeepSeek V4.1 Flash twice through Forge 2.0, our Atlassian Forge app-upgrade benchmark. It scored 0.2893 and 0.3790, a median of 0.3342 against 0.6745 for Claude Opus 5.5 and 0.5283 for MiMo V2.6 Flash. Then I read the code behind its biggest penalty, and I don't think our scorer got that one right.
Mihai Perdum14 min read
A Jira project status report has one job: tell the sponsor whether the date will hold. LeanZero Management answers that from the plan, says Can't tell yet when too little work is dated, and drafts a sponsor report whose verdict you can't edit.
Gabriela Perdum9 min read
Claude Haiku 5.5 and GPT-6 Luna both list at $0.10 in and $0.50 out per million tokens. In our agent runs Haiku billed 3.6 times as much, mostly because 64 of its 111 calls crossed the 100k-token line where its price goes up five times, and part of that was a bug in our own agent. It also built the better apps: 0.9661 to 0.395 on an Atlassian Forge app, 0.661 to 0.4797 on a payments app. The checks that decided both, the call-by-call bill, and how to keep Haiku under the step.
Mihai Perdum22 min read
A CogniRunner AI agent set up from one paragraph, then given a plan I tightened by hand, counted 32 Atlassian products on 17 sites. A second agent took one Confluence license away only after a person approved. Plus a workflow validator that stopped Claude Code twice, a Forge app deployed through Bitbucket Pipelines, the safety design and the token bill.
Mihai Perdum17 min read
Atlassian Team '26 Europe on demand: six keynotes are already on Atlassian's YouTube channel, the library opens on 12 October (11 October in the FAQ), and these are the sessions I'd watch as a Forge builder or Jira admin.
Mihai Perdum7 min read
Our Atlassian Team '26 Europe recap: the highlights in one list with Atlassian's own status labels, what we learned at RAI Amsterdam, what we know about the Closing Keynote, and what to check next week as a Jira or Confluence admin.
Gabriela Perdum7 min read
The Team '26 Europe Founder Keynote as I saw it from the hall in Amsterdam on Wednesday 7 October: agent sessions from Cursor, Codex and Claude Code on a Jira board, AMP, a lot of Rovo, a power cut, and a day showing our Forge apps to Atlassian's people.
Mihai Perdum8 min read
Qwen3.8 Flash beat Qwen3.8 Max Prime on an Atlassian Forge app built with no internet, 0.7961 to 0.6953, and lost to it on a payments web app, 0.6846 to 0.8364. Every check behind both results, the one manifest line that decided Forge, a probe in which neither model showed it knew the rule until it was handed the docs sentence, and what fine-tuning our own 27B taught us about forgetting.
Mihai Perdum38 min read