Operations | Monitoring | ITSM | DevOps | Cloud

Fix flaky tests with AI, and track future test work in Jira

In January we launched Tests in Bitbucket Pipelines – a single place to track, organize, and understand your test health over time. In April we added automatic flaky test detection so unreliable tests get flagged before they slow your team down. But spotting a problem is only half the battle. Day to day, your team still needs to act on a test – track it as work, clean it up, or route it to the right person.

GLM-5.2 Review (2026): Zhipu AI's Open-Weight Coding Model, Honestly Assessed

Zhipu AI (now operating internationally as Z.ai) shipped GLM-5.2 in mid-June 2026, and the claim that grabbed attention was blunt: an open-weight model that beats GPT-5.5 on several long-horizon coding benchmarks for roughly one-sixth of the cost. It's an MoE model with 753 billion total parameters released under an unrestricted MIT license, which means you can self-host it or call it through a managed endpoint.

How One AI-Localized String Broke Our Build and Cost Me $6,000 (And What I Do Differently Now)

The string that broke our last release was four words long. It passed review, went green in the build, and shipped to our German locale with a corrupted placeholder that turned the checkout button into a runtime error. Customers there could not complete an order for most of a Saturday before a screenshot reached me. The broken button cost us roughly $6,000 in lost orders that weekend; the fix itself took ten minutes. What I do differently now started with understanding why it happened.

Making Testing Smarter: How AI in testing automation Supports Continuous Change

Selecting a freight forwarder in 2026 is no longer just about getting goods from point A to point B. You now need a partner that can handle customs clearance, protect delivery timelines, provide transparent shipment updates, and help you understand how sustainable your supply chain is. It matters when disruption to supplies, expectations of customers, and reporting on the environmental impact of operations all sit with one team managing operations.

The Three Pillars Were Built for Humans

It was 2am and I was paying for the privilege. Something was on fire in production, and I’d done the modern thing: I pointed an AI agent at it. It ingested the dashboards. It read the logs. It walked the traces. Then it handed me back a beautifully formatted paragraph that said, in effect, “latency is elevated on the checkout path.” I knew that. The page told me that.

The Journey to Achieving Hyperscale Availability with AI-Driven Prediction

At hyperscale, a regional cloud outage is not merely a technical disruption—for Samsung Account, which serves 2.1 billion users across three global regions, it is an immediate global service crisis. Fragmented, region-siloed monitoring creates blind spots that make early detection nearly impossible, leaving SRE teams perpetually reactive rather than predictive. The path to proactive reliability requires both a philosophical shift and a foundational change in how observability data is collected, unified, and reasoned over.

From a $28,000 AI Bill to $0.60 Per Ticket

Engineering teams are burning through AI budgets with nothing to show for it — $100M across 10,000 engineers and no cost per run, no cost per outcome, just a number that keeps climbing. When it runs dry, your infrastructure upgrade gets cut. Harness ties every AI token to the outcome it created: cost per run, cost per resolved ticket, and anomaly detection before the invoice hits. One customer went from a $28,000 black box bill to $0.60 per ticket.