Real Atlassian solutions to real problems — no fluff, no SEO spam.
Clean up before you migrate is the most-repeated advice in the Atlassian world, and almost nobody takes it. Not because they're lazy — because every incentive in the room, mine included, is paid to move more, not less. Follow the money.
We built a harness that makes local coding agents produce real software, grades it by running it, and ran the same model as GGUF and MLX. Here's the harness, its modes and archetypes — and which build wins.
We forked Block's goose into a multi-agent swarm that decomposes a hard app spec into a task DAG, runs it across three small local models on LM Studio, and makes them verify their own work by actually running it. Over six days and 300-plus commits, the last real limit stopped being the swarm's coordination and became the small model's raw coding ability — and even that ceiling moved.
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.
Permissions, Assets data shape, and Assets scope — the three places where I keep watching migrations slip and budgets balloon. None of them are anyone's fault. All of them are dramatically cheaper to fix before migration than during.
After enough Data Center to Cloud migrations, you develop an instinct for when things are about to go sideways. It's never the core data — Jira issues, Confluence pages, user accounts — that breaks the project. It's the apps. Specifically, it's the moment you realize the vendor doesn't have an answer either, and your client's deadline doesn't care.
JSM's native portal is functional enough for agents — but for the people filing requests, it's a friction-first experience that drives tickets up, not down. Refined Sites fixes the part your requesters actually see. Here's what you gain, what stays broken, and when the investment earns its keep.
Every workflow validator on the Atlassian Marketplace requires scripting. Every AI app for Jira is an assistant that can’t block a transition. CogniRunner sits in the gap between those two worlds — plain-English prompts that evaluate Jira field content, including attachments, as a real-time workflow gate.
After 10+ Data Center to Cloud migrations, here's what nobody tells you: they're imperfect by necessity, not by design. Waiting for perfection is the single most expensive mistake an organization can make — and I've watched it happen in real time.
