%term

Building reliable dashboard agents with Datadog LLM Observability

Jan 16, 2026 By Harmit Minhas In Datadog

This article is part of our series on how Datadog’s engineering teams use LLM Observability to iterate, evaluate, and ship AI-powered agents. In this first story, the Graphing AI team shares how they instrumented their widget- and dashboard-generation agents with LLM Observability to detect regressions and debug failures faster. Visibility into how large language model (LLM) applications behave in real time is essential for building reliable AI-driven systems at Datadog.

Read Post

Datadog

Read more about Building reliable dashboard agents with Datadog LLM Observability

Why agentic AI is the future of IT change management

Jan 16, 2026 By Rachel Pearson In BigPanda

Every enterprise depends on continuous changes to its IT environment. New code releases, infrastructure updates, configuration changes, and security patches are all crucial to support continuous innovation. These same changes are also a leading source of operational risk and one of the most common causes of failures at the network, infrastructure, and software layers, resulting in outages.

Read Post

BigPanda

Read more about Why agentic AI is the future of IT change management

How AI OCR Is Reshaping Automated Data Extraction in Large-Scale Business Operations

Jan 16, 2026 By OpsMatters In OpsMatters

Businesses handle massive amounts of data every day. Such data is obtained from invoices, bills, contracts, applications, and many other documents. Most of these documents are distributed in the form of scanned copies and images. As a result, whenever organizations resort to manual data entry in processing such data, the process turns out to be slow and filled with errors. However, to avoid these issues, organizations are now turning to AI-OCR solutions for better data extraction and increased operational efficiency.

Read Post

OpsMatters

Read more about How AI OCR Is Reshaping Automated Data Extraction in Large-Scale Business Operations

AI in Contact Centers: Capabilities, Limits, and the Missing Decision Layer

Jan 16, 2026 By OpsMatters In OpsMatters

AI in contact centers refers to the use of artificial intelligence technologies to automate customer interactions, support agents in real time, analyze conversations, and improve operational efficiency. In practice, this includes chatbots, virtual agents, intelligent routing, agent assist tools, sentiment analysis, and automated quality assurance systems designed to increase speed, consistency, and scale.

Read Post

OpsMatters

Read more about AI in Contact Centers: Capabilities, Limits, and the Missing Decision Layer

Lightrun MCP: AI agents now validate your code with live Runtime Context

Jan 15, 2026 By Lightrun In Lightrun

Lightrun R&D Team Lead Or Galon and Engineer Roy Chen demo how you the new Lightrun MCP allows AI coding assistants to access Runtime Context, and validate how software will behave in production.

View Video

Lightrun

Read more about Lightrun MCP: AI agents now validate your code with live Runtime Context

Agentless First, Agents When Needed: A Hybrid Approach to Security Telemetry

Jan 15, 2026 By VirtualMetric In VirtualMetric

Security data collection has become a first-class architectural concern for modern SOCs. Once collection is treated as a dedicated layer, separate from analytics and detection, the next question becomes practical: how should telemetry be collected in a way that aligns with this architecture? In the previous article, we examined why this shift occurred. Here, we focus on how different collection models (agent-based, agentless, and hybrid) fit into modern security data collection architectures.

Read Post

VirtualMetric

Read more about Agentless First, Agents When Needed: A Hybrid Approach to Security Telemetry

The Problem With AI Code Nobody's Talking About

Jan 15, 2026 By GitKraken In GitKraken

GitKraken's Product Director Justin Roberts explains why we're focused on managing AI-generated code aftermath, not creating another code generator. Learn about Commit Composer, AI conflict resolution, GitKraken MCP, and our agent-driven workflow vision.

View Video

GitKraken

Read more about The Problem With AI Code Nobody's Talking About

What is Runtime Context? A Practical Definition for the AI Era

Jan 15, 2026 By Roy Chen In Lightrun

TLDR: Runtime Context is live, execution-level access to a running production system. It lets engineers and AI agents ask precise questions of running code and get answers immediately, without redeploying or interrupting users. This is the new baseline for reliability.

Read Post

Lightrun

Read more about What is Runtime Context? A Practical Definition for the AI Era

Dossinth AI - where we're at

Jan 15, 2026 By Lucian Daniliuc In Monitive

The AI sidekick called Dossinth I'm building is starting to take shape. So far, it became a moderately useful CRM, with a nice dashboard, and event log, daily briefing (which I am also receiving by email), account management and knowledge base. It's less AI and more CRM. For now. Here's a quick tour...

Read Post

Monitive

Read more about Dossinth AI - where we're at

The Operational Cost of Shadow AI: Securing Data Integrity in Modern Workflows

Jan 15, 2026 By OpsMatters In OpsMatters

In the current hyper-accelerated digital landscape, operational efficiency is the bedrock of corporate scaling. However, a silent threat-the "Authenticity Gap"-is quietly eroding the reliability of enterprise data as unvetted Generative AI permeates modern workflows. For operations managers, this is a Level 1 silent risk that compounds into significant wealth erosion and project delays if left unmanaged.

Read Post