AI Agents
How autonomous AI systems actually behave when deployed, coordinated, and left to run — what works and what breaks silently.
9 stories
An AI agent is not a chatbot that does more. It is a system that takes actions, not just outputs. That distinction changes everything about how you build with it, how you trust it, and how you find out when it has gone wrong.
What Makes Agent Systems Different
Most AI applications are stateless. You send a prompt, you get a response. The interaction ends there. Agent systems are different: they maintain state across steps, take actions that have consequences in the real world, and often operate faster than any human can monitor them.
This creates failure modes that language model benchmarks do not capture. A model that scores well on reasoning tasks can still fail systematically when embedded in a multi-step pipeline — not because its reasoning is bad, but because its reasoning is local. It optimizes for the step in front of it without understanding the broader context it is operating in.
The Coordination Problem
When multiple agents work together — each responsible for a different part of a pipeline — the question of who is responsible for correctness becomes complicated. Each agent passes output to the next. Each agent trusts the output it receives. If one agent produces something subtly wrong, the downstream agents typically do not catch it. They incorporate it. By the time the error is visible, it has been processed through several layers of confident-sounding output.
The essays in this chapter examine these failure modes directly: the structural reasons they occur, the conditions that make them more or less likely, and the approaches that actually help — not in theory but in deployed systems.
Economics and Trust
Using AI agents at scale is also an economic question. The cost per action, the latency per step, and the reliability threshold required before removing a human reviewer from the loop — these are not engineering parameters. They are business decisions that require understanding what autonomous systems are actually good at versus where human judgment remains necessary.
These essays look at where the lines are, based on what the current systems can and cannot do, and how those lines are likely to move.
Featured Article
What the New Reasoning Models Actually Changed About How I Build
The data says reasoning models make developers 19% slower. Here's what actually changed in my software development workflow once I stopped ignoring that.
All Stories
How Semantic Routing Cut My LLM Costs by 70% Without Touching Model Quality
Semantic routing cut my LLM costs 70% in production. Here's the unglamorous truth about why it works and why most teams still won't ship it.
RAG Is Not Enough: What Retrieval Still Gets Wrong in 2026
RAG retrieval problems didn't disappear with better vector search. They just moved somewhere harder to audit. Here's the data nobody wanted to publish.
Hallucination in Production Agents: The Real Risk Profile Nobody Discusses Honestly
The real production risk of LLM hallucination isn't the errors themselves. It's what avoiding them is quietly costing you. Here's the evidence.
AI-Assisted vs AI-Autonomous: Where the Line Actually Is and Why It Matters
95% of AI pilots fail. Here's what the data reveals about when autonomous actually works—and when it's just expensive.
42% of AI Projects Fail Within 6 Months: The Real Reason (It's Not Technical)
Your AI automation project goes live and works perfectly for 4 months. Then distribution drift kills it. Here's why 42% get abandoned and how to prevent it.
Tool Use in LLMs: What It Actually Means for Production Systems
Honeycomb shipped LLM function calling to production before the API existed. What they found changes how you should think about tool use.
Context Window Poisoning in Multi-Agent Pipelines: Why Agents Hallucinate Together
When one agent's hallucination spreads through a pipeline, no agent catches it. Here's why cascading trust causes silent failures — and how to stop it.
Human-in-the-Loop vs Autonomous AI Agents: A Cost Comparison
AI agent economics show autonomous pipelines beat human-in-the-loop on cost AND accuracy at scale — here's the threshold most teams are missing.