Dennis Pilarinos

Founder & CEO of Unblocked

Dennis Pilarinos is the founder and CEO of Unblocked, the context engine for engineering teams. He previously founded Buddybuild, the mobile CI/CD service Apple acquired in 2018 and relaunched as Xcode Cloud, and built developer platforms at Amazon (AWS) and Microsoft (Azure). He holds multiple patents and writes here about how AI agents get, and lose, organizational context.

Dennis Pilarinos

Articles

Anthropic's Agent Memory Research: What Memory From Sessions Can't See

Agentic Engineering: What Agents Need Besides the Model

Unblocked ranked the highest performing code review tool

Context for Background Coding Agents: What an Unattended Agent Needs Before It Starts

How Enterprise AI Agents Get Company Context: Access Is Not Understanding

Why Was This Built This Way? The Second Codebase Your AI Agents Can't Read

How to Organize Context for AI Agents When It Lives Everywhere

Context for Support and Ops Agents: One Source for Every Agent You Run

Source of Truth for AI Agents: Who Decides What Is True?

Stop AI Slop From Contaminating Your Team's Knowledge Base

Best AI Documentation Tools for Engineering Teams (2026)

Does Sandboxing MCP Output Fix the Agent Context Problem?

How to Give AI Agents Your Slack, Jira, and Confluence Knowledge (Tools Compared)

Agent Skills vs Rules Files vs Retrieved Context: What Goes Where in 2026

Best Knowledge Base for AI Agents (2026)

One Instructions File to Rule Your Agent: What AGENTS.md and CLAUDE.md Can and Can't Fix

What 194 Engineering Teams Told Us About Their Homegrown Context Stacks

Why Wouldn't Claude Code Handle Your Org Context Itself?

The Snowflake Copilot Autofix Incident: An AI Approved Removing a Guardrail Nobody Told It About

CLAUDE.md vs AGENTS.md vs .cursorrules: Which File Should You Write?

What We Learned Moving Our Agent Loops from Anthropic to GLM

Why Claude Code Invents Functions Your Codebase Doesn't Have

What Is Context Rot? Why AI Agents Degrade Mid-Session

Claude Code vs Codex CLI: The Enterprise Comparison (2026)

Which Source of Truth Does Your Coding Agent Believe?

Inside the Unblocked context engine: how we decide what your agent needs to know

Cursor vs Claude Code for Teams: Which Fits Your Engineering Org in 2026?

Codex Context Management: Auto-Compact Threshold and /context

Context Infrastructure for Fleet-Scale Coding Agents

Keeping CLAUDE.md, AGENTS.md, and .cursorrules in Sync

A Pile of MCP Connectors Is Not a Context Engine

AI Agent Orchestration Platforms Compared (2026)

Connect PagerDuty and GitHub to Claude Code for Incident Debugging

Slack MCP: Feed Slack History to Your AI Coding Agent

Linear MCP: Sync Linear Tickets to Your AI Coding Agent

Notion MCP: Connect Notion to Claude Code and Cursor

Unblocked vs Onyx for AI Coding Agent Context

Best Context Retrieval Tools for AI Coding Agents

Why Cursor Hallucinates Your Architecture and Forgets Context (and How to Fix It)

Best MCP Servers for Engineering Teams (2026 Compared)

Context Infrastructure for Autonomous Coding Agents: What They Need Before You Can Trust Them

What Is an AI Software Factory? (And How Agentic Engineering Actually Works)

Knowledge Graph Tools for Engineering Teams: What to Use in 2026

Best Engineering Knowledge Platforms for AI Coding Agents in 2026

"Context" grew up at the World's Fair

Codex Context Window: Size, the 1M Setting, and How to Check Usage (2026)

Confluence MCP Server: Connect Claude Code, Cursor, and VS Code in 2 Minutes (2026)

Permission-Aware Context Retrieval: How Unblocked, Glean, Augment Code, and Sourcegraph Compare

Best AI Tools for Engineering Teams in 2026

How to Refactor Legacy Code with AI Agents (2026)

AI-Powered Legacy Code Modernization: The Complete Guide (2026)

Claude Code Context Window: 200K vs 1M, and How to Check What Is Using It (2026)

Jira MCP Server: Connect Claude Code, Cursor, and VS Code in 2 Minutes (2026)

AI Coding Anti-Patterns: How Teams Waste the Three Levers

How Much Autonomy Should You Give Your AI Coding Agents?

Your agents lack context. Here's how to fix "You're absolutely right."

Why AI Agents Burn Tokens: The Four Runtime Waste Mechanisms

FinOps for AI Coding: Who Owns the Budget When Agents Spend It

The Auto-Loop Tax: Why Self-Running AI Agents Burn More Tokens, Not Fewer

Model Routing for Coding Agents: When Cheaper Models Save Money (and When They Cost More)

AI Tokenomics: How to Measure and Control What AI Coding Tools Actually Cost

How to Measure the ROI of AI Coding Tools (When Fewer Than 1 in 5 Teams Do)

DORA Metrics in the AI Era: Necessary but No Longer Sufficient

Context-Adjusted Productivity: Measuring What AI Actually Ships in Large Codebases

The AI Productivity Paradox: Why Your Devs Feel Faster but Ship the Same

How to Measure AI Productivity: The 2026 Framework for Engineering Leaders

How to Scale from One Agent to Parallel Agents Without Losing Quality

How to Build a Context Layer for Your Engineering Org

The Context Infrastructure Stack: A CTO's Guide

How Many MCP Servers Is Too Many? The Tool Overload Problem

Unblocked vs Glean vs Augment: Which Is Right for Your Engineering Team?

The 55,000-Token Problem With the GitHub MCP Server (and 4 Fixes)

The Context Layer: What It Is and Why Every AI Agent Needs One

Why Your AI Coding Agent Keeps Forgetting Your Codebase

Where Your MCP Token Budget Actually Goes: A 2026 Autopsy

Why Claude Code Keeps Reinventing Your Team's Rejected Approaches

Claude Code Context Rot: Why Accuracy Drops at 200K Tokens

Three Hard Lessons from Building Context at Scale