Real Atlassian solutions to real problems — no fluff, no SEO spam.
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
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
Claude Sonnet 5.5 edged Claude Opus 5.5 on our general-programming benchmark, 0.7984 to 0.7926, a margin I read as level. On an Atlassian Forge app, Opus won 0.9767 to 0.5508. Every check behind both results, GPT-6.1 Sol and Sol Pro on the same two boards, how the benchmarks grade a running app, and the full bill for fine-tuning our own 27B model.
Mihai Perdum45 min read
Cloud Fortified monitoring is bound to app versions, not to your framework. Publish a Forge version and the probes keep hitting your old Connect base URL — each one carrying its own 99.9% SLO, and redirects are not followed.
Mihai Perdum7 min read
A buffer task that absorbs slip until it can't, a plan that defends itself against edits made in Jira, and a write path that refuses rather than lies. Traced line by line, and set against what BigPicture and Structure.Gantt actually document.
Mihai Perdum18 min read
Forge delivered one page edit twice, 400ms apart. The duplicate didn't post a second comment — it wiped the 24-hour window that stops second comments. Then I wrote the whole thing up backwards, and the test I built to prove it agreed with me.
Mihai Perdum13 min read
Forge gives you no veto over a Confluence save. Product events arrive after the change is already committed, which means a lock on Confluence content cannot prevent anything — it can only detect and restore. Here is what that constraint does to an app: why the restore has to ignore itself, why reverting the whole page is the wrong fix, and why a licence check in a protection app must fail open.
Gabriela Perdum11 min read
CogniRunner's latest update brings local AI inference, a zero-key Atlassian-hosted model, and declarative AI actions that write back to Jira — all configured in plain English.
Mihai Perdum6 min read