Operations | Monitoring | ITSM | DevOps | Cloud

Stop Guessing: Let AI Handle the Debt Conversation

Traditional debt collection tactics fail in today's fast-paced digital age. Generic letters and repeated calls no longer deliver results. AI has shifted that landscape. Reaching out at the right time is easier when you know customer habits and preferences. This helps make contact smarter. Personalized service, cost savings, and increased efficiency are all possible. The best part? No new hires are required. Consumers now expect digital-first tools and flexible communication. Collectors get better with AI. It handles timing, channels, message tone, and follow-up without effort.

Beyond Chatbots: Advanced Generative AI Use Cases to Supercharge Team Collaboration

Emails compose themselves. In 2023, Gmail introduced the "Magic Compose" feature and its "Help me write" button (later rebranded as Gmail's Gemini Assistant), enabling users to draft, reply to, or polish entire emails using a short prompt or by selecting an already typed phrase. At the same time, AIpowered meeting summaries became built into tools like Notion, where /meet now triggers fully automatic transcription, structured summaries, and tagged action items, eliminating scribbles and missing points. Meanwhile, calendars are no longer static deadlines in spreadsheets.

Elastic bandwidth and the future of AI-driven networks

In this employee spotlight blog, Shaheen Kalla, Presales Team Lead, explores what the future of AI in networking may hold and the possibilities it presents. So much has been written about AI in the context of software engineering, machine learning, and data manipulation - especially where large datasets are involved. However, very little has been explored when it comes to AI from a networking perspective.

End-to-end testing and deployment of a multi-agent AI system with Docker, LangGraph, and CircleCI

Multi-agent AI systems are transforming how intelligent applications are built. By orchestrating multiple specialized agents that collaborate to solve complex tasks, these systems enable more dynamic and efficient workflows. However, deploying such a system reliably and at scale requires a structured approach to testing, packaging, and automation.

Detect hallucinations in your RAG LLM applications with Datadog LLM Observability

Hallucinations occur when a large language model (LLM) confidently generates information that is false or unsupported. These responses can spread misinformation that jeopardizes safety, causes reputational damage, and erodes user trust. Augmented generation techniques, such as retrieval-augmented generation (RAG), aim to reduce hallucinations by providing LLMs with relevant context from verified sources and prompting the LLMs to cite these sources in their responses.

Why we vibe coded a marketing campaign for Anthropic

Let’s start with the obvious: we’d like to have Anthropic as a customer. We greatly admire the work they are doing at the intersection of frontier models + safety. We use lots of different AI tooling at incident.io. We’re all-in at AI at incident.io, both to improve the productivity of our internal team and, more importantly, to provide our customers with superpowers in the form of an AI incident responder.

MCP server: Automated test coverage

Learn about a new feature using CircleCI's MCP server that brings automated test coverage to AI-enabled applications. Using a simple React app, the MCP server scans for AI prompts, recommends tests, and writes them directly into your codebase. Watch how you can: Now you can test and ship with confidence—right from your IDE or CI pipeline.