AI Agents
How autonomous AI systems actually behave when deployed, coordinated, and left to run — what works and what breaks silently.
14 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
Context Window Management for Long-Running AI Agents: 4 Patterns That Work
Context window management for long-running AI agents isn't compression. Four patterns from years of long agent runs, one embarrassing mistake of mine, and what the long-context benchmarks actually say.
All Stories
When Not to Use an AI Agent: The Architecture Decision Nobody Talks About
Gartner says 40% of agentic AI projects die by 2027. When not to use an AI agent, how an AI agent differs from a workflow, and why 'just add an agent' is usually backwards.
Why LLM Agents Fail Silently in Production (And How to Detect It)
A silent agent failure doesn't crash. It reports success. Here's the uncomfortable economic reason most teams never find out.
Every Agentic Loop Needs a Circuit Breaker. Mine Took 3.5 Days to Get One.
My bot detected its own ban and then kept working for three and a half more days. Agent safety isn't really about what the agent decides. It's about how long it keeps deciding.
The Hidden State Problem in Agentic Systems That Nobody Warns You About
My Twitter bot kept drafting replies for 3.5 days after the account was suspended. It had already detected the suspension. Memory was never the problem.
Do Reasoning Models Actually Make Developers Faster? What the METR Study Found
METR's 2025 randomized trial found experienced developers were 19% slower with AI while believing they were 20% faster. Here's what that means for reasoning models, code review, and how I build.
Semantic Routing: How I Cut LLM Costs 70% in Production
Semantic routing cut my LLM costs 70% without hurting quality. Most teams still send every request to the expensive model. Here is what actually breaks.
RAG Hallucination Rate: Why Retrieval Still Fails in 2026
RAG hallucination rate is still 17-33% on production legal tools. Retrieval did not fix this. Long context just moves the same failure into the prompt.
LLM Hallucination Rates in Production: What the Data Actually Shows
LLM hallucination rates in production run from under 1% on grounded summarization to 58–82% on open legal questions. Here's what the data shows — and why adding a human reviewer doesn't fix it.
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.
LLM Function Calling in Production: Reliability, Failure Modes, and Design Patterns
Honeycomb shipped LLM function calling to production before the API existed. What they found — plus τ-bench and BFCL numbers, real failure modes, and the validation layer nobody ships until it burns them.
Why Multi-Agent AI Systems Fail in Production (And Which Patterns Hold)
Multi-agent AI systems fail at the handoff, not the model. What cascading trust costs, whether more agents reduce errors, and the schema and step-ceiling configs that hold under load.
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.