Operations | Monitoring | ITSM | DevOps | Cloud

What Separates a Serious AI Data Collection Company From One That Just Says It Is

Most AI projects don't fail at the model architecture stage. They don't fail at deployment. They fail earlier and more quietly - at the point where the data that was supposed to train the model turns out to be insufficient, inconsistent, or simply wrong for the task it was collected to serve. Choosing the right ai data collection companies is, in this sense, one of the highest-leverage decisions an organization makes when building AI capability - and one of the decisions most commonly made on the wrong criteria.

Monitoring AI Applications in 2026: What You Actually Need

Last updated: July 2026. Your AI feature works in development. It demos well. Then it hits production and you discover three problems your test suite did not catch: the LLM hallucinates product names that do not exist, the RAG retrieval step adds 4 seconds to every request, and your OpenAI bill is 3x what you budgeted because one prompt template is burning tokens on context that does not help the output. Traditional APM would have caught the latency.

AI Is Reshaping the Tech Industry in 2026: What Consumers and Businesses Need to Know

Artificial intelligence has evolved from an emerging technology into one of the biggest drivers of innovation across the global technology industry. In 2026, AI is influencing everything from smartphones and laptops to cybersecurity, cloud computing, enterprise software, and digital productivity tools. Companies worldwide are investing heavily in AI powered products that improve efficiency, automate repetitive tasks, and deliver more personalized user experiences.

The AI Software Engineering Revolution, feat. Anthropic | Big Tent S3E9

In this episode of Grafana's Big Tent, hosts Mat Ryer (Senior Director of AI, Grafana Labs) and Tom Wilkie (CTO, Grafana Labs) sit down with Eric Burns, Field Executive Architect at Anthropic, to talk about building trust between tech and business execs, why Anthropic bet early on running across every major cloud, and what it was like watching large language models go from "interesting" to "obviously the future" in real time.

Making agentic token costs visible in production

In some organizations, high token counts have become a proxy for productivity. Some engineering teams are being pushed to max out context windows and wire in sprawling tool sets. More tokens can mean better agent reasoning and richer context during development, but token costs compound in production. Tokens accumulate across sessions, users, and tool calls in ways that are easy to overlook. Datadog’s 2026 State of AI Engineering report quantifies the scale of this problem.

OpenSearch 3.6: Agentic Applications Meet Long-Term Support

TL;DR OpenSearch 3.6 makes agentic search production-ready, with the AI-powered Launchpad provisioning full search apps in minutes and faster default vector search, and it's the first LTS release, bringing 18+ months of guaranteed support, SBOMs, and an upstream-first commitment (every fix goes back to the main project) so teams get fast-moving open source and a stable, supported platform at once.

How to Use Your Knowledge Base to Increase AI Chatbot Deflection

Ticket deflection is the metric IT leaders point to when they talk about AI chatbot ROI, and the knowledge base is the part of the equation that determines whether that number moves. A chatbot can run natural language processing well and still deflect almost nothing if the content behind it is thin, outdated, or scattered across articles that don't match how people actually ask questions.

Why AI agents need a job description | The future of agentic AI in IT

An AI agent is only as useful as the job you can safely hand it. In this Zero Ticket Minute, Ian Coppock, Resolve Customer & Partner Marketing Manager, breaks down why enterprise AI is moving toward purpose-built agents with defined roles, scoped permissions, and real guardrails. That is the foundation for autonomous IT operations and Zero Ticket IT. Subscribe for weekly insights on AI, IT automation, and where enterprise operations are heading.

Why Cash Flow Still Matters in an AI-Driven Economy

Artificial intelligence is changing how businesses operate. Companies are using AI tools to automate customer service, generate content, analyze data, improve forecasting, and streamline everyday tasks. For many business owners, the promise is simple: work faster, reduce costs, and improve efficiency.

Building AI SRE Agents, Part 1: Start Local, Break Things, Learn Fast

The first stage of AI SRE maturity is a laptop, a throwaway cluster, and zero production access. Here’s how to set it up, and what to watch for. AI SRE (Site Reliability Engineering) agents are AI-powered systems that automate the most time-consuming parts of incident response: triaging alerts, correlating logs and metrics, generating root-cause hypotheses, and proposing remediation steps.

Rethinking Sprite Creation Costs for Indie Developers

The gap between game design ambition and art production has never been more visible. Over the past twelve months, a growing number of indie teams have discovered that the bottleneck isn't always code, mechanics, or level design-it's the sheer volume of sprite frames required to bring a single character to life. A walking cycle alone can consume an entire weekend. A complete character with idle, attack, and jump animations often stretches into weeks of pixel-by-pixel work.

The Future of Governing AI Agents in Enterprise Order Processing

Governing AI agents are rapidly reshaping how enterprises manage complex, high-volume order workflows, from automated validation to exception resolution and fulfillment routing. As AI models become more reliable and context-aware, organizations are shifting from human-heavy processes to autonomous systems that can handle end-to-end order lifecycle management with minimal manual intervention.

AI Detection in Your Content Pipeline: How to Reason About Detector Accuracy Before You Build a Gate Around It

Every ops team eventually inherits a check that nobody can fully explain. It runs on every release, it blocks the pipeline when it fires, and when you ask why the threshold is set where it is, the answer is some version of "it was like that when I got here." AI text detection is becoming that check for content operations. Teams are wiring detectors into publishing workflows, documentation pipelines, and vendor review steps, treating a probability score as a pass or fail gate. Then a genuinely human-written runbook gets flagged, a release stalls, and someone has to decide whether to trust the tool or override it.

How to Build Enterprise AI Agents with Natural Language | Agent Lab Demo, Guardrails & AI Skills

Most enterprise AI agents take weeks to build. This one takes minutes. Watch how Agent Lab creates purpose-built agents with natural language, adds reusable skills, and sets guardrails before anything ships. From idea to production-ready in a single sitting.

AI ROI: From Adoption to Business Proof

AI adoption is easy to report. Business impact is harder to prove. Engineering leaders are under pressure to show what AI is actually changing — not just who is using it, but whether it is improving delivery, quality, developer experience, and business outcomes. This discussion between 3 engineering leaders explores how to move beyond vanity metrics, build a practical measurement approach, and communicate AI’s value to executives and CFOs with more credibility and less hype.

AI-powered monitoring with Site24x7's Zia

In this video, you'll learn how to integrate Large Language Models (LLMs) with Site24x7 using Bring Your Own Key (BYOK), Zoho Key Services (ZKS), and Microsoft Azure OpenAI. Discover how Zia helps you analyze outages, understand performance issues, identify root causes, and get monitoring insights using simple natural-language queries. What you'll learn.

The future of governing AI agents

How to build governance into autonomous security agents from the architecture up The industry has moved fast on capabilities. Agents now triage alerts, investigate endpoints, create detection rules, and enrich indicators, and they are even capable of performing most actions we as security operators can perform. The architecture patterns are maturing, as are the models, but governance is not keeping pace.

The Aiven MCP in Practice: From Dev Environment to App Deploy

I spend a good amount of my time deploying Aiven services for demos and examples. Traditionally the tools I reach for are: If I’m writing a program, I may also look to the Aiven API, perhaps using curl at the command line or in a shell script, or perhaps with direct HTTP requests in a Python program. The API is how the console and the CLI tool talk to Aiven, but I generally find that too low level to be comfortable, and I always have to look up how to pass in the Aiven user token.

From Data Warehouses to AI: How Enterprise Data Quality Has Changed Over the Last 20 Years

An interview with Marcin Chudeusz, co-founder and CEO of digna Two decades ago, enterprise data quality looked very different. Organizations were building centralized data warehouses, business intelligence projects revolved around structured reporting, and most data quality initiatives relied on thousands of manually created validation rules. The objective was simple: ensure the data entering reports was accurate enough for decision-making.

Anthropic Warns Against AI While Building It Faster Than Anyone

On June 4, 2026, Anthropic published a document unlike anything a major AI lab had put in writing before. Titled "When AI builds itself," and co-authored by Jack Clark (Anthropic's co-founder and head of policy) and Marina Favaro, who runs the Anthropic Institute, the piece argues that frontier AI development may need to slow down - or even stop - before humans lose the ability to control what comes next.

The invisible visitor: Why the internet is no longer just for humans

"Every website was once designed for people. That assumption is beginning to change." For nearly three decades, the internet has worked in a predictable way. Whenever we wanted to know something, we searched for it, clicked through a few websites, compared information, and made a decision. Whether it was buying a new phone, planning a vacation, or researching software for work, businesses knew exactly how people behaved online.

How do you run AI when your data can't leave the network?

Highly classified environment. Strict compliance requirements. Data that can't leave the network. But still a real need for the competitive advantage AI delivers. Civo Director of Enterprise Cloud Solutions John Dietz addresses exactly that challenge and how Konstruct makes it possible to run Kubernetes, deploy your own models, and point Claude Code at your own internal private servers instead of public APIs.

Introducing the BigPanda AI Incident Assistant

AI incident assistant from BigPanda gives L2, L3, and SRE teams instant answers to resolve incidents faster without manual triage or tool-switching. IT teams lose critical minutes during incidents because context is scattered across Slack threads, bridge calls, monitoring tools, and historical tickets. The BigPanda AI Incident Assistant fixes that by surfacing relevant knowledge exactly when and where responders need it. It gives responders evidence-based resolution paths drawn from historical incidents and live system data, without leaving your workflows.

Introducing AI Incident Prevention from BigPanda

AI Incident Prevention from BigPanda stops change-related outages before they occur by leveraging risk scores, trend analysis, and guided remediation steps. Manual IT changes are still a leading cause of IT outages and disruptions. BigPanda AI Incident Prevention addresses this by automatically scoring change requests against historical data, flagging high-risk changes before they go live, and surfacing the recurring problems that cause service degradation.

Why Some IT Teams Adopt AI Faster (And How to Close The Gap)

Every IT leader is under pressure to show AI results. Budgets are approved, pilots are launched, and vendors promise transformation within a quarter. Some teams are already running AI agents in production, resolving tickets and answering employees without human intervention. Others are still stuck in proof-of-concept purgatory, six months into a rollout with nothing to show a board. The thing is, AI doesn't fix what's broken in an IT operation, it multiplies what's already there.

Called it (mostly): Checking in on 2026 predictions so far

On this episode of Masters of Data, we revisit the predictions Adam White, Zoe Hawkins, and David Girvin made at the end of last year, checking our own scorecard halfway through 2026. The hits: agents running amok and deleting databases, MCP becoming the backbone for tracking what agents actually do, growing security gaps around personal data, and a collective rejection of low-quality AI content. The misses: we underestimated how fast companies would cut staff for AI, then quietly start rehiring once the agents couldn't cover the work, and we're still arguing about whether token burn is a cost problem or a coming attack vector.

Deterministic vs Probabilistic AI Engineering Explained

Deterministic processes carry one guarantee: the same input will produce the same output. That guarantee built the entire observability stack. AI broke that contract by reasoning in terms of probability. The same input can now produce different outputs, whether from AI-generated code that carries assumptions invisible in staging, or from distributed systems where timing creates failures that no pre-captured telemetry can anticipate.

GitHub Copilot cost: what teams actually pay in 2026

The GitHub Copilot cost runs from $0 for the Free tier to $10/month for Pro, $39/month for Pro+, and $100/month for Max. Teams pay $19/user/month for Business and $39/user/month for Enterprise. The twist: on June 1, 2026 GitHub swapped fixed premium requests for usage-based AI Credits, so what those flat fees actually buy now depends on how hard you push the AI. The sticker price is the easy part. The part that ambushes finance is everything stacked on top of it.

How to Evaluate an Agentic Process Automation Platform in 2026

Agentic AI has moved quickly from experimentation to enterprise planning. IT leaders are no longer asking whether AI agents can summarize tickets; they’re asking a more important question: Can agentic AI actually complete work consistently and measurably? That is where agentic process automation becomes critical.

How to Automate Unstructured Data Using AI Agents (Clear & highly searchable)

Let’s be honest: traditional automation breaks the second it hits a scanned PDF, a messy email thread, or an architectural drawing. Rules-based RPA simply lacks the cognition required to decode unstructured data. In this episode of, Project Manager Swetha K J breaks down exactly how we conquered this massive roadblock on our automation journey. By embedding advanced AI models directly into automation workflows, we’ve built a context-aware architecture that transitions systems from static execution to dynamic intelligence.

Why individual AI adoption is breaking team-level throughput

There is a question a lot of engineering leaders are quietly sitting with right now: we have rolled out AI tools across the team, the developers seem faster, so why isn't more software actually shipping? It is a reasonable thing to consider. Pull requests are opening faster. Lines of code per sprint are up. The boilerplate that used to take full afternoons now takes minutes. By every local measure, the investment is paying off.

Why prompt injection gets worse with AI agents?

When AI could only answer questions, a bad prompt just meant a bad answer. But now AI agents read your documents, browse websites, and actually do things on your behalf. So when someone sneaks a malicious instruction into a file or a webpage, the agent doesn't just say something wrong. It does something wrong!

MCP vs CLI: Does it even make a difference? | Live Laugh Logs ep. 3

MCP vs CLI: does it even make a difference? Here’s everything you need to know. Welcome to Episode 3 of Live Laugh Logs, the podcast from the Coralogix Developer Relations team. This week Andre has made the move to the US, so Annie and Lewis are joined by George Pickers, Head of Solution Engineering for EMEA & APAC at Coralogix.

GPT-4 API cost 2026: pricing breakdown and how to estimate it

GPT-4 API pricing spans $0.10 to $30.00 per million input tokens across the model family. GPT-4.1 is the current recommended production model at $2.00 input / $8.00 output per million tokens. Legacy GPT-4 still runs at $30.00/$60.00 per million tokens -- 15x more expensive for no meaningful quality gain. For finance and engineering leaders accountable for AI spend, choosing the right GPT-4 variant is the single biggest cost lever on your bill.

How to Set Up Claude Code with CircleCI MCP Server (Full Demo)

AI agents write code fast, but without a validation layer, fast just means faster bugs. In this video, we connect Claude Code to the CircleCI MCP server so Claude can trigger pipelines, pull build failures into context, and iterate until everything is green. No context switching. No copy-pasting logs.

Kafka MCP: Manage Apache Kafka From Your AI Assistant

The Aiven MCP connects Claude, Cursor, and VS Code to Apache Kafka. Inspect topics, track consumer lag, stream a database in with CDC, and manage your cluster. AIVEN DATA PLATFORM The Aiven Platform is more than a collection of open source services for streaming, storing and analyzing data. The platform ensures that all services run reliably and securely in the clouds of your choice, are observable, and can easily be integrated with each other and with external 3rd party tools.

Kafka MCP: Manage Apache Kafka From Your AI Assistant

You're building with Claude or Cursor, and you need to know what's actually happening on your Kafka cluster. Your AI assistant knows Apache Kafka in the abstract, but not your topics, your retention, or that a consumer group has been slipping since this morning. So you leave the editor and go digging through logs, a CLI, and a few dashboards, correlating by hand to answer questions like: The Aiven MCP (EA) turns each of those into a sentence you type where you already work.

Observability for LLM Apps and Agents: OpenLIT SDK + VictoriaMetrics observability stack

Many “LLM observability with OpenTelemetry” tutorials stop at a single chat.completions span. That works for a demo, but it leaves gaps once an agent fans out into 30 tool calls, two vector-DB queries, three handoffs, and a 90-second tail latency you need to attribute. This post wires the OpenLIT SDK (50+ instrumentations, OTel GenAI semantic conventions, one line of code) into the full VictoriaMetrics observability stack and shows query examples that turn agent telemetry into decisions.

Six AI agent SDKs for enterprise Kubernetes, compared

There’s a question we hear constantly from platform and engineering leaders right now, “which agent SDK should we standardize on for our Kubernetes clusters?” The honest answer is that the question is slightly wrong, and the rest of this post explains why. But it’s a fair question, so let’s compare the contenders first.

AI on AI Challenges

Building AI agents is easy until they launch into production and start behaving unpredictably. In this presentation, João Freitas, Chief AI Officer at PagerDuty, dives into the messy reality of scaling non-deterministic systems and shares how PagerDuty manages multi-agent complexities. Speaker: João Freitas, Chief AI Officer, PagerDuty Recorded during GenAI Community x Google Developer Group Lisbon at PagerDuty Portugal offices, July 2026.

How to Measure AI ROI in IT Service Management

A service desk manager launches a virtual agent in January. By March, chat conversations are climbing, ticket volume hasn't changed much, and the monthly report doesn't explain whether the investment is delivering value. AI rarely produces a single number that proves its return. The gains accumulate across thousands of support interactions, making measurement just as important as deployment.

Introducing AI Analytics Reports in InvGate Service Management

Most teams can confirm their AI features are turned on. Measuring how often employees use them, which requests get resolved without agent intervention, and where AI is helping support teams work more efficiently is a different question. In InvGate Service Management, those capabilities live in AI Hub, a set of built-in AI features that includes the Virtual Service Agent, AI-assisted ticket resolution for agents, automated knowledge generation, and more.

Why Faster Recovery Beats Faster Shipping in the AI Era

A year ago, AI coding tools worked alongside developers—suggesting the next line, completing a function, accelerating work that a human was already doing. Today, they’re writing entire modules and services independently, producing code that no human has reviewed line by line, built from components that no single person has fully mapped. And adoption is only accelerating: According to our recent AI Resilience Survey, 84% of organizations are now using AI to write, review, or suggest code.

Right Size Your Model Usage with Valkey and Semantic Routing

Benchmarks keep showing that picking the right LLM is hard. The easy answer is "just use the most powerful one." That works, but it is pricey. A small, cheap, or local model can handle many simple requests just as well as a frontier model, for a fraction of the cost. That is what semantic routing is for. Use middleware that looks at an incoming request and decides which model should answer it.

OpenAI API cost calculator: estimate your GPT spend before it estimates you

This OpenAI API cost calculator (also an AI inference calculator for o3/o4-mini thinking tokens) estimates your monthly OpenAI API pricing bill from three inputs: model, request volume, and average tokens per request. Toggle between standard, batch, and cached pricing and get your number in seconds. It also shows what the same workload costs on Claude and Gemini. For the full per-model rate card, see CloudZero's OpenAI API pricing guide.

AI Summary Agent in Turbo360

Handed over an Azure integration environment you've never seen before? Turbo360's AI Resource Summary agent gives any support operator or engineer an instant plain-English overview of what a resource is, how it behaves, and what to watch out for - without needing to ask the developers. In this demo: Great for: IT operations teams, MSP NOCs, cloud support engineers, and anyone responsible for running integration workloads they didn't build.

Prepare for the EU AI Act with Harness AI Security | Harness Blog

Harness AI Security provides a unified control plane for AI discovery, risk visibility, and runtime protection, helping organizations operationalize key requirements of the EU AI Act. Instead of relying on manual audits or fragmented tooling, teams get continuous insight into how AI systems are built, exposed, and used, along with the evidence needed to demonstrate compliance.

ACP vs MCP: What's the difference for agentic coding?

An AI coding agent holds many conversations at once. Not only is the user prompting it, the agent also talks to the IDE, showing diffs and asking before it touches a file. At the same time it talks to tools, pulling a failing build or querying a database. Two open protocols standardize those conversations. This guide compares ACP vs MCP in practical terms: what each protocol does and when each applies. ACP (Agent Client Protocol) connects a code editor to an AI coding agent.

Why Most AI Pilots Never Reach Production

Most AI initiatives never make it out of the pilot stage. Gartner has forecast that 30% of generative AI projects will be abandoned after proof of concept by the end of 2025, undone by poor data quality, weak controls, unclear business value, and escalating cost. The problem predates the current wave of generative tools. RAND's study of experienced practitioners found that more than 80% of AI projects fail, roughly twice the rate of IT projects that carry no AI component.

How Agentic AI speeds up troubleshooting application issues

One night, Daniel Rizzy was the only person awake on Zylker’s IT team, and the clock was already running. He was also the only thing standing between a P1 outage and 10,000 customers. Rizzy works nights for ZylkerXchange, Zylker’s foreign currency exchange app. He lives on the city’s outskirts, where the air is clean and quiet, and the night shift suited that life. Most nights, nothing happened. Some nights, everything did.

The Future of Digital Experience in Companies: What Changes with DEX, AI, and the Employee at the Center

For decades, companies measured IT efficiency through technical indicators: servers up, systems online, equipment working. But does that actually mean a good experience for the people doing the work?

AI Agents Write Broken Code 49% of the Time #speedscale #AI #Coding #Tech #DevOps

AI agents write broken code nearly 50% of the time. By adding a traffic-based deterministic evaluation, Speedscale boosted unsupervised bug-fixing quality from 51% to 77% in just 5 minutes. This helped slash token costs and eliminate rework without human intervention. Learn more: speedscale.com.

LogicMonitor and Edwin AI: Autonomous IT for Hybrid IT Environments

Autonomous IT starts now with LogicMonitor and Edwin AI, built to help IT teams monitor complex hybrid IT environments, discover root cause faster, reduce downtime, and prevent incidents before they impact revenue or brand reputation. See how LogicMonitor brings AI-powered IT operations, observability, and incident prevention together for modern infrastructure teams.

How AI Agents Are Changing Each Agile SDLC Phase

The Agile software development lifecycle was designed to surface problems early, with short sprints, iterative testing, and continuous integration built on the premise that faster feedback loops produce better software. AI coding tools have changed the velocity equation across every phase of that loop, but the phases designed to catch failures are struggling to keep up because build speed and validation capacity have not accelerated at the same rate, and the gap between them is widening with every sprint.

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.

PagerDuty agent app in GitHub

PagerDuty's agent app shows live incident state, incident history and change correlations inside GitHub so you can get context right within your PR without interrupting your flow. Automatically correlate incident data with recent commits and deployments to identify root causes, then generate fix PRs with proper incident linking.#IncidentResponse.

PagerDuty agent app in GitHub: incident context where you already work

This blog post is part of PagerDuty’s ongoing series on how we’re helping customers navigate their journey toward autonomous operations. Read on to learn about the PagerDuty agent app in GitHub (Early Access) and how it builds toward this vision. How many tabs do you have open right now? And how many more do you open the moment an incident hits? Context switching during incident response is one of the most persistent sources of toil in engineering.

AI Orchestrations: Your easy button for proactive operations

This blog post is part of PagerDuty’s ongoing series on how we’re helping customers navigate their journey towards autonomous operations. Read on to learn about how AI Orchestrations builds towards this vision. “We should automate this.” Sound familiar? For many operations teams, that sentence never becomes action. Building event orchestration rules demands deep platform expertise, time no one has, and the ability to spot which patterns in your data actually matter.

The Next Enterprise AI Challenge: The Multi-Model Workplace

For the last two years, enterprise AI strategy has largely focused on one thing: adoption. Organizations encouraged employees to experiment with ChatGPT, Claude, Copilot, Gemini, and dozens of emerging AI tools in the hope that productivity gains would naturally follow. CIOs approved pilots, departments launched AI task forces, and leaders pushed teams to integrate AI into everyday work as quickly as possible. But the enterprise AI conversation is beginning to change.

How Datadog uses AI to build internal software delivery tools and improve system performance

At Datadog, we want our developers to become better at using AI tools with the end goal of building quality software, faster, that generates real value. This includes not only the products and features that our customers use, but also the internal tools that help keep our workflows running smoothly behind the scenes.

Accelerate investigations with AI in Datadog Incident Response

Engineering teams spend much of their incident response time investigating the problem and coordinating the response. Both tasks become harder when telemetry data lives in one place, deployment history is stored in another, and conversations unfold across chat channels and incident bridges. Responders often spend the first part of an incident rebuilding context before they can begin testing hypotheses and working toward resolution.

Don't 'control' your AI spend. Understand it and be intentional.

There’s a good interview making the rounds. BizTech sat down with IBM’s James Stevenson to talk about how financial institutions can get a handle on cloud and AI costs. The advice is solid: get visibility, kill idle resources, tighten governance, tag everything. And pull finance and engineering into the same room. I don’t disagree with it. But I read the whole piece and noticed where the gravity pulls: control costs, reduce waste, bring down spend. The headline says it (‘Q&A.

Shipped: Turn your Bifrost gateway into an AI spend meter

If you route model traffic through Bifrost, you already have the hard part: one place every AI call passes through, where the model, the tokens, and the cost are visible on the way past. It’s the cheapest spot in your stack to measure AI spend. What’s missing is everything downstream – today that usage only becomes “spend” weeks later, when the provider invoice lands as a lump sum you can’t break apart.

AI Tool Sprawl Is Killing Enterprise ROI | Why Orchestration Matters More Than AI Features

Enterprise AI adoption is accelerating, but are organizations actually solving business problems or just adding more tools? In this episode of Agents of IT, Fran Fernandez (Chief Product Officer at Resolve) and Zach Austin (Director of Product Marketing) explore one of the biggest challenges facing enterprise IT in 2026: AI tool sprawl. They discuss why many organizations struggle to demonstrate ROI from AI investments, how disconnected AI assistants create operational complexity, and why orchestration, automation, and context have become the real differentiators for enterprise AI success.

Reading the agent traces is how you make the call your eval can't

Remember being excited (or dreading, depending on the stage of your career and the company you worked at) about writing unit tests? Or sweating all the details in your end-to-end and integration tests you were sure covered all the use cases your users would hit? These days a lot of UIs are slowly being replaced by a single input field and an agent that promises to deliver the same value a UI would, but with the elegance and pun-ness of a “Jarvis”.

Harness Agents

Today, we're launching Autonomous Worker Agents, AI agents that run as governed pipeline steps inside Harness. They inherit OPA policies, RBAC, audit trails, and scoped credentials from the first run. And because they live inside your Harness pipelines, they reason using the Harness Knowledge Graph: your services, deployments, incidents, and policies.

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.