GitLab 19.5: MCP Server GA Lets Outside Agents In, With Limits
GitLab 19.5 makes its MCP server generally available, governs Claude Code and Cursor sessions, and adds rate limits. What platform teams should configure first.
GitHub Secret Scanning: Why a Small Model Beat the LLM Pipeline
GitHub secret scanning swapped an LLM for a fine-tuned ModernBERT classifier: 86% faster scans, 98% lower cost, fewer false alarms. How it works for teams.
GitLab AI Credit Caps: Three Levers for Controlling Agent Spend
GitLab AI credit caps, open-weight models and Orbit target agent spend. What each lever controls, GitLab's benchmarks, and the order to use them.
CircleCI's Intent-Driven Development: A Six-Step Framework for Steering AI Agents from Idea to Ship
CircleCI's intent-driven development gives AI coding agents explicit constraints and success criteria via intent documents. A six-step framework.
JFrog: AI Coding Tools Are Generating Vulnerabilities 10 Times Faster Than They're Being Fixed
JFrog's 2026 report: AI coding tools add about 35 CVEs a month as disclosures rose 92% in 2025, and CISA now advises against severity-only vulnerability triage.
CircleCI's Framework for Testing AI Agents in CI: Contract Tests and Agent Evals
CircleCI's two-layer agent testing in CI: deterministic contract tests as hard gates, plus statistical agent evals against baselines at a slower cadence.
Coding Agents Are Pulling Packages Your Security Team Can't See
AI coding agents like Cursor and Claude Code bypass traditional package governance by pulling dependencies directly from public registries. JFrog's agent package resolution closes that gap before the next supply chain incident.
JFrog Fly Graduates: What an Agentic Repository Actually Means for Enterprise CI/CD
JFrog Fly's agentic repository capabilities are now part of the main JFrog Platform. The experiment is over. The question now is what enterprise teams do with it.
MCP vs API: CircleCI's Practical Guide to When Each Makes Sense
CircleCI's engineering blog clarifies the actual distinction between APIs and MCP — and why the answer for most agentic systems is 'both, for different purposes.'
AGENTS.md vs. Skills: How to Actually Steer a Coding Agent
CircleCI's breakdown of when to use AGENTS.md versus modular skills for coding agents — and why the real problem isn't the format, it's measuring whether steering works at all.
The Practical Guide to AI Sandboxes for Developers
AI coding agents have deleted home directories and a production database. What an AI sandbox is, how isolation levels differ, and where it fits.
Model Routing Promises 85% Savings. One Switch Can Erase All of It.
JFrog's research shows model routing cuts AI agent costs by 40-85% — but a single mid-session model switch can cost more than the savings it was meant to create.
AI Coding Speed Is Outrunning Secrets Security
Nearly 30 million secrets leaked on GitHub in 2025 (up 34% YoY). AI-assisted code leaks at nearly 2x the rate. What DevOps security teams should do now.
Atlassian's Jira Gets a Coding Agent: What the Teamwork Graph Actually Changes
Jira Coding Agent is now live on all paid plans. Atlassian's Teamwork Graph provides project context to connected AI coding tools — here's what that means for platform teams managing AI-assisted development at scale.
JFrog Boost: The Free CLI That Cuts AI Coding Token Bills Before You Hit the Limit
JFrog Boost enters public preview with 80% payload reduction in CI scenarios—addressing the token-cost problem quietly becoming every platform team's biggest AI line item.
Datadog Agent Observability Brings AI App Debugging Into Your Coding Agent
Teams spend 60–80% of AI development time on evaluation and error analysis. Datadog's new Agent Observability workflow surfaces production trace data directly into coding agents to cut that cycle.
Datadog Acquires Adaptive ML: Production-Trained AI Agents for Observability
Datadog acquired Adaptive ML to embed specialized model training into its observability platform — shifting AI agents from generic APIs to systems trained on real production signals.
How Datadog Used AI to Turn a 45-Minute Query Into a 1-Second One
Datadog migrated its Stream Router — the control plane handling 100+ trillion events daily — from FoundationDB to PostgreSQL using AI-assisted refactoring. The approach cut 45-minute operations to 1 second and reduced database costs by 90%.
HashiCorp Launches tfctl: A Dedicated CLI for HCP Terraform and Terraform Enterprise
HashiCorp's new tfctl gives platform engineers full API coverage of HCP Terraform and TFE from the command line — with dry-run mode, schema discovery, and built-in guardrails for destructive operations.
JFrog Brings Xray Security Data Into Amazon Kiro With a New Open-Source Power
JFrog Power for Kiro adds artifact search, repository management, and live CVE data from JFrog Xray directly into Kiro's MCP-native IDE — closing the gap between AI-assisted coding and security validation.
Datadog DASH 2026: When Your Monitoring Platform Became an Agentic Operating System
Bits AI agents now detect, remediate, validate, and write code inside Datadog. DASH 2026 marks the shift from observability tool to autonomous engineering platform.
JFrog's Claude Code Plugin Puts Supply Chain Security Where AI Decisions Happen
JFrog embeds dependency validation, MCP server governance, and Artifactory access directly into Claude Code—shifting supply chain security left into the agentic development loop.
Microsoft Made the Agent Runtime Free—and That's Exactly the Point
Microsoft's Agent Framework—built on open-source OpenClaw—is now free. Scout ships on top of it. The pattern matches how mobile platforms evolved: free runtime at the base, managed services and compliance tooling as the revenue layer.
Replit's Shopify Integration Reveals the Real Play: Owning the Vibe Coder's Full Financial Stack
Replit added Shopify storefront generation to its monetization suite—joining RevenueCat subscriptions and Visa agentic payments to assemble a turn-key financial layer for apps built without traditional engineering teams.
Patterns of Validation: How to Keep AI Agents from Wrecking Your Codebase
CircleCI's layered validation framework — feedforward instructions, mechanical hooks, and post-deploy observability — addresses the core ways AI coding agents fail silently.
JFrog's MCP Integration: Ask Your Platform to Provision Itself
JFrog's new MCP server lets AI coding agents like Cursor and Claude Code provision Artifactory repos, run Xray security scans, and trace release bundles — in plain language, without navigating dozens of UI screens.
Datadog Cut Spark Compute Costs 44% with an AI Agent. Here's Exactly How.
Datadog's internal ServiceQueryEdge job ran 17+ hours daily and cost $1.5k/day. An AI agent using Claude and Jobs Monitoring found three Scala-level optimizations that cut duration by 60% and cost by 44% — approximately $250K in annual savings.
Snyk Evo: Continuous Pentesting to Match the Pace of AI Code
Traditional pentesting averages 15 days of coverage per year. Snyk Evo runs AI agents against your application stack continuously. Here's the architecture and the gap it closes.
Datadog AI Impact: Connecting AI Coding Tool Usage to Deployment Performance
Datadog AI Impact maps AI-assisted commits to lead time, change failure rate, and deployment frequency — measuring AI tool ROI against actual delivery performance.
Datadog Database Investigator: Root Cause Analysis Without a DBA
Datadog's agentic Database Investigator diagnoses latency spikes, connection pool exhaustion, and replication lag without requiring dedicated DBA expertise.
CircleCI Chunk: CI Validation Inside the Agent's Inner Loop in Under 60 Seconds
CircleCI Chunk sidecars bring CI feedback into the agent's inner loop — microVM environments that validate code locally in 60 seconds, no commit or push required.
JFrog Skills: Open-Source Toolkit for AI Agents That Understand Software Supply Chains
JFrog's open-source Platform Skills library lets AI agents query CVE data, verify artifact provenance, and enforce governance policies using natural language — with MCP support for Cursor and Claude Code.
CircleCI as a Codex Plugin: What Agentic CI/CD Actually Looks Like
CircleCI just shipped a native Codex plugin that lets AI agents inspect pipelines, debug failures, and optimize configs without a context switch. Here's what that unlocks.
Datadog Code Security MCP: Security Scanning Inside AI Code Generation
Datadog launched an MCP server that runs SAST, SCA, secrets detection, and IaC scanning during AI code generation — catching vulnerabilities before they reach a pull request.
Datadog Bits Assistant: Natural Language Across the Entire Observability Stack
Datadog's Bits Assistant brings conversational AI to dashboards, logs, traces, and incident response — making complex telemetry queries accessible without query syntax expertise.
Betterleaks: The Gitleaks Successor Built for Agentic Secrets Scanning
Gitleaks creator Zach Rice rebuilt the tool from scratch with 98.6% recall, CEL-based validation, and CLI design built for AI coding agents operating code pipelines.
Datadog Bits AI Dev Agent: Automated Vulnerability Remediation at Scale
Datadog's Bits AI Dev Agent opens GitHub PRs to fix SAST findings automatically — closing the security backlog that manual triage alone can't clear.