Operations | Monitoring | ITSM | DevOps | Cloud

SDLC Phases and the Reliability Gap AI Can't Close

Decisions in each SDLC phase from planning to design, development, testing, deployment, and maintenance are made without sight of live production behavior. AI coding agents are widening that visibility gap faster, working faster than human engineers ever could. This piece maps exactly how this gap presents at each phase, and the harm that this brings.

I'll have my AI agent call your AI agent: Battle for your digital hub

On this episode of Masters of Data, we unpack what it actually means to expect AI to be the primary interface for everything we do. We dig into the pull toward centralizing work in a single hub like Claude versus staying spread across specialized tools like Slack, Asana and Zoom, and where the line sits between helpful automation and letting an agent speak on your behalf. We also get into the "chief of staff" agent workflow for daily roundups and why specialized, best-of-breed tools aren't going anywhere, even as hubs get smarter.

Actionable Intelligence, Not Artificial Intelligence: What AI in Data Center Management Actually Requires

“AI-powered” has become a marketing label applied to almost any data center software feature. A more useful and precise term is actionable intelligence — a four-level maturity model (descriptive, diagnostic, predictive/prescriptive, and cognitive) that shows whether a platform’s AI claims are backed by real data infrastructure or just a chatbot layered on top of an incomplete system.

Security at Scale: What Changes When Everyone Can Deploy using AI

In our first series post, The New Software Creator, we mapped out a structural shift in the industry: AI is turning non-technical team members into creators of software. In our second post, When Anyone Can Build Software, Deployment Governance Is What Keeps It Safe, we argued that deployment is the single control layer that can secure this explosion of output without choking innovation.

Your AI agents are lost: give them a graph

The biggest limitation facing enterprise AI agents may not be the model. It may be the context surrounding it. Anthony Alcaraz, Senior AI/ML Portfolio Growth Manager at AWS and co-author of O'Reilly's *Agentic GraphRAG*, joins Humans of Reliability to explain why reliable agents need more than a vector database and a large context window. They need structured knowledge they can navigate, memory they can prune, constraints they can follow, and feedback loops that help them improve.

Introducing AI Agent Deployment in Harness Continuous Delivery | Harness Blog

‍Teams building agents have converged on something that looks a lot like the software development lifecycle, but reshaped around a system whose output isn't deterministic: prototype an agent against a framework, evaluate it against a dataset of expected behavior, deploy it somewhere real, observe how it behaves against live traffic, and feed what you learn back into the next prototype. Call it the agent development lifecycle (Agent DLC).

Introducing Harness AgentTrace: An Observability and Guardrail Framework for AI Agents | Harness Blog

AI agents fail differently from the software we spent the last two decades learning to monitor. We hear some version of the same story from teams shipping agents to production: an agent starts producing wrong answers. Not obviously broken: confident, well-formatted, plausible wrong. The logs are clean, latency looks healthy, and error rates sit at zero. Nothing flags a problem. A user eventually does.

AI's Role in Enhancing Digital Commerce Operations

Artificial intelligence is quickly becoming a must-have for digital businesses, not just a nice-to-have. For companies looking to sharpen their operations, AI offers powerful ways to predict what's next, smooth out customer interactions, and keep transactions safe. It's not about replacing people, but giving them better tools. This lets teams focus on big-picture strategy while AI crunches data and automates tasks. This shift is changing what's possible in terms of how efficient a business can be, how happy its customers are, and how much it can grow.