Working notes from the frontier of agent deployment.

June 9, 2026 Field guide Decagon Alternatives in 2026: 7 Options Compared on Pricing, Deployment, and Ownership June 9, 2026 AI Safety Mythos/Fable 5 NLA: What Anthropic Found Inside June 9, 2026 Engineering Recursive Self-Improvement Needs a Testing Harness, Not Just a Smarter Agent June 8, 2026 Field guide AI Customer Service for Financial Services: Audit Trails, SOC 2, and What Regulators Will Actually Ask June 8, 2026 Engineering What Is AG-UI? The Protocol Layer Agentic Apps Were Missing June 7, 2026 Compare Agentforce vs Sierra vs Decagon vs OpenNash: AI Agent Fit Compared June 7, 2026 Services AI Agent Consulting Services: Build Production Agents You Own June 7, 2026 Pricing AI Agent Pricing 2026: Platforms, Retainers, and True Cost June 7, 2026 Field guide HIPAA-Compliant AI Customer Service: What Healthcare Buyers Actually Need to Verify June 5, 2026 Field guide Why You Need an AI Services Partner: AGI Ships, But It Does Not Self-Install June 3, 2026 Field guide Workflow Discovery for AI Automation: Map the Process Before You Build the Agent June 1, 2026 Field guide Decagon Alternatives in 2026: 7 Options Compared on Pricing, Deployment Time, and Ownership May 29, 2026 Field guide AI in Insurance: Where Deterministic Automation Saves Time First May 28, 2026 Field guide How to Eval AI Agents in 2026: From Pretty Demos to Production Evidence May 28, 2026 Engineering Macro Evals for Agentic Systems: Why One Failed Trace Is Not Enough May 28, 2026 Market Replacing Junior Jobs With AI Is a Bad Business Strategy May 28, 2026 Engineering Self-Improving AI Agents Are Not Magic: What OpenAI's Tax AI and Karpathy's Autoresearch Teach Builders May 28, 2026 Engineering What the Anthropic Cookbooks Reveal About Building Agents That Actually Work May 24, 2026 Field guide AI Agent Deployment Is Not the Finish Line: The Operating Model After Launch May 24, 2026 Market Open AI Strategy: Why Model Routing, Traces, and Memory Beat Vendor Lock-In May 24, 2026 Market Verifiable Outcomes: Why the Best AI Agents Start With Boring Proof May 15, 2026 Field guide Open Source Just Caught Up to Opus 4.5: Why the Moat Is the Harness, Not the Model May 13, 2026 Market AI Receptionist for Law Firms: Intake, Conflicts, Escalation, and Audit Trails May 11, 2026 Market Best AI Voice Agents for Customer Support: Retell, Bland, Synthflow, Sierra, and Custom Compared May 8, 2026 Market AI Customer Support Platform vs Custom AI Agent: Build, Buy, or Own in 2026 May 6, 2026 Market Zendesk AI Agent Pricing: Licenses, Setup, and Resolution Fees May 4, 2026 Market Sierra AI Pricing: What Outcome-Based Really Costs and When to Walk Away May 1, 2026 Market Agentforce vs. Sierra vs. Custom AI Agents: Which Customer AI Platform Actually Fits? April 30, 2026 Engineering AI Coding Harnesses: Stop Writing Code, Start Designing the System Around the Agent April 30, 2026 Engineering Notion AI Agent Architecture: 5 Rebuilds, 100+ Tools, and What Finally Worked April 29, 2026 Market Why You Need a Professional Services Partner to Deploy AI Agents (And What That Actually Looks Like) April 27, 2026 Market Build vs Buy AI Customer Support: The 3-Year Cost Sierra, Ada, and Salesforce Hope You Skip April 22, 2026 Market Intercom Fin Pricing Reality: When $0.99 Per Resolution Becomes a $1.2M Problem April 20, 2026 Market Ada AI Review 2026: Pricing Reality, Platform Limits, and When Custom Wins April 17, 2026 Market Salesforce Agentforce vs. Custom AI Agents: When the CRM Giant Isn't the Right Fit April 15, 2026 Market Why 'Configurable' Isn't 'Custom': What Businesses Actually Get from AI Agent Platforms vs. Purpose-Built Software April 8, 2026 Market AI Agent Audit Trails: What Regulated Industries Need Before Deploying Agents April 8, 2026 Engineering LLM Routing in Production: How to Pick the Right Model for Each Task April 7, 2026 Field guide Open-Source LLMs for Business Automation: When They Beat GPT-4 and When They Don't April 6, 2026 Engineering Agent Reliability Engineering: SRE Patterns That Keep AI Agents Running in Production March 27, 2026 Market AI Agent UX: How to Design Interfaces That Users Actually Trust March 25, 2026 Field guide Human-in-the-Loop Agent Design: 5 Patterns for When AI Should Ask Permission March 23, 2026 Market Your Team's First AI Agent: 5 High-ROI Starting Points That Are Not Chatbots March 20, 2026 Market Build vs. Buy AI Automation in 2026: A Decision Framework for Technical Leaders March 18, 2026 Engineering Agent Memory Beyond RAG: Short-Term, Long-Term, and Episodic Memory Patterns That Work March 16, 2026 Engineering Evaluation-Driven Development: How to Ship AI Features That Actually Improve Over Time March 13, 2026 Market AI Labor Market Impact 2026: What to Automate Now and What Still Needs Humans March 11, 2026 Engineering The 8 Levels of Agentic Engineering: How Teams Move from Copilot to Background Agents March 9, 2026 Field guide AI Automation, SaaS Stock Drops, and the Future of Apps: What Actually Gets Repriced March 6, 2026 Field guide Why AI Agents Fail in Production: 7 Failure Modes and How to Prevent Them March 4, 2026 Engineering 9 Agentic Workflow Patterns Ranked: Which Ones Actually Work in Production February 27, 2026 Market The $50-a-Day Agent: Cost Engineering for Production AI Workflows February 26, 2026 Market OpenClaw for Business: What It Is, How It Works, and When to Deploy It February 25, 2026 Podcast AI's Real Bottleneck Isn't Software. It's Materials. February 25, 2026 Market How to Pick an AI Agent Platform Without Getting Locked In February 22, 2026 Engineering 6 Agentic Knowledge Base Patterns: How AI Agents Are Replacing Static Wikis February 18, 2026 Market From Pilot to Production: The Enterprise AI Agent Readiness Checklist February 16, 2026 Engineering The Lethal Trifecta: Securing AI Agents Against Data Exfiltration (Enterprise Checklist) February 13, 2026 Market 5 AI Agent Use Cases That Work in 'Boring' Companies February 12, 2026 Market From Prototype to Production: The Agent Deployment Checklist February 4, 2026 Engineering LLM Evaluation Beyond ROUGE: Building Custom Evals for Enterprise Agents February 2, 2026 Field guide Agentic Workflows vs Traditional Automation: When to Choose Each (2026 Guide) February 2, 2026 Market The Lethal Trifecta: Why Your AI Agent Is a Data Leak Waiting to Happen January 26, 2026 Market AI Agent Evals for Non-Technical Leaders January 23, 2026 Resource CAISO Storage Daily Brief: Dispatch, Prices & Ancillaries (2026) January 23, 2026 Resource ERCOT Prices Today: Day-Ahead, Real-Time & Ancillary (2026) January 23, 2026 Market The Hidden Tax of Agents: Compound Error and Cost Explosions January 22, 2026 Resource Clinical Trial Sponsors List: Top 500 Recruiting (2026) January 22, 2026 Resource FDA 510(k) Cleared Companies: Complete List (2026) January 22, 2026 Resource Fortune 500 Full List (2026) January 22, 2026 Resource Y Combinator Companies: Full List (2026) January 21, 2026 Podcast Personal AI Infrastructure: How Scaffolding Changes Everything January 21, 2026 Engineering Five Production Agent Patterns from Anthropic's Playbook