Writing / Tag / 39 of 66
AI Agents
Every essay tagged AI Agents, newest first.
This is the broadest tag on the site. An AI agent is a model in a loop with tools, memory and some authority to act, and nearly every essay here is about one specific way that loop breaks once real users are on the other end: the agent that keeps running after the user leaves, the one that forgets everything when the tab closes, the one that does whatever a web page tells it to.
I do not write much about frameworks. The failures I cover are architectural, and they show up whether you built the loop yourself or pulled one off a shelf. So the essays tend to name a symptom, trace it back to a design decision, and show the fix with code you can read in ten minutes.
For a first pass, read the orchestrator and worker essay on why one prompt doing six jobs is the root of a lot of later pain. Then prompt injection defense for the trust boundary every tool-using agent needs, and human-in-the-loop approval gates for the small set of actions an agent should never take alone.
October 2026
Your Long MCP Tool Call Dies at the Client Timeout
A tool that takes four minutes to run cannot answer inside a client request that gives up after sixty seconds.Your Agent Writes Code and Runs It Where Your Secrets Live
The feature that makes a code-writing agent useful, running code it generated a second ago, is also the widest hole in your stack.Your Agent Logs Everything and Can Prove Nothing
A trace with forty-seven agent steps shows an auditor that something happened.Your Agent Failed at Step 7. The Bug Was at Step 3.
When a multi-step agent produces a confidently wrong answer, the step that threw the error is almost never the step that caused it.Your Agent Retries Are Making the Failure Worse
When an agent step fails and you retry it in the same context, the failed attempt stays in the window and the model conditions its next try on its own mistake.Your Evals Are Green and the Product Is Getting Worse
A frozen eval suite stops describing your product within weeks.Your Agent's One Reliability Number Is Hiding the Failures That Matter
A single pass rate on a dashboard tells you an agent is "99% reliable" and tells you nothing about which 1% is on fire.When Every AI Provider Goes Down at the Same Time
Early this month three of the big model providers degraded within a few hours of each other, and a lot of AI features went dark with them.
September 2026
Your Agent Got the Right Answer the Wrong Way
Your eval checks the final answer and goes green.Your Agent Would Rather Guess Than Admit It Doesn't Know
Most agents never say "I don't know." They were trained on benchmarks that reward a confident guess over an honest abstention, so in production they invent a policy, a number, or a citation and say it with a straight face.Nobody Can Tell You How Many Agents You Are Running
A year of shipping agents leaves most teams with a fleet nobody can inventory: no owner, no declared budget, no record of which tools each one can reach.Your Agent's Memory Is Full and Most of It Is Junk
You gave your agent persistent memory and it worked.Your Agent Fetches the Same Row Ten Times a Session
A long-running agent calls the same read tool over and over inside a single session, paying full latency and quota for answers it already had a few turns ago.Your Agent Is Idle Most of the Time It's Working
A tool-using agent spends a surprising share of its wall clock doing nothing, just waiting for a network round trip while the model has already stalled.Your Subagents Are Hiding the Evidence
Spawning a subagent to keep the parent's context clean is the right instinct, and it is also where a lot of long-running agents quietly go wrong.Your Multi-Agent System Already Has a Blackboard
Wire a few agents together with direct handoffs and it works.Your Voice Agent's Dead Air Is an Architecture Problem
A voice agent that goes silent for two seconds after the caller stops talking feels broken, and no faster model fixes it, because the floor is retrieval plus generation plus speech.Your Easy Queries Are Paying for Thinking They Never Use
You turned on extended thinking because it lifted your quality numbers, and a quarter later the invoice had doubled.One Flaky Step Is Sinking Your Agent. Vote It Out.
You measured your agent and found one step that flips between right and wrong on the same input.Your Agent Scores 90% on Evals and Still Fails Customers
A 90% pass@1 eval score feels like a passing grade, and then production hands you a stream of complaints anyway.Content Filters Watch What Your Agent Says. Nothing Watches What It Does.
Your output guardrails inspect the words an agent produces.Your Agent Started Calling Other Agents. Who Verified Theirs?
A2A hit v1.0 this year and teams are wiring their agents to other teams' and vendors' agents.
August 2026
Your Model Started Showing Its Work. Now You Have to Handle It.
Reasoning traces are the feature everyone turned on this month and nobody planned for.Your Agent Called the Same Tool Seventy Times and Billed You for It
A ReAct-style agent calls the same search tool, gets the same unhelpful result, decides another identical call will help, and does it again.You Installed a Skill and Your Agent Will Run Whatever Is Inside
You pulled a skill off a registry, your agent read its instructions, and it is now ready to execute whatever code shipped in the folder.Your Agent Passes Every Eval and Still Fumbles Real Conversations
Your eval suite is green.A Customer Hit a Bug Your Agent Will Never Reproduce
A user sends you a screenshot of your agent doing something wrong.Your Agent Makes the User Watch a Spinner for 20 Seconds
Your agent does real work before it answers: it searches, calls three tools, reasons about the results, then writes a reply.Your Agent Retried and Charged the Card Twice
A tool call times out, your agent retries it, and the customer gets billed twice because the first request went through before the response came back.Your Agent Has 200 Tools and Picks the Wrong One
Connect enough MCP servers and your agent carries hundreds of tool definitions into every turn.Your Agent Kept Working After the User Left
A user closes the tab and your agent keeps going: three tool calls in flight, two subagents still reasoning, tokens still burning for an answer nobody will read.Let Your Agent Ask Before It Does the Irreversible Thing
Most of what an agent does is safe to let run.Your Agent Just Leaked One Customer's Data to Another
Input defenses stop bad instructions from getting in.
July 2026
Your Agent Will Do Whatever the Web Page Tells It To
The moment your agent reads untrusted content and can also call tools, a hidden instruction in a web page or email can hijack it.Your Agent Keeps Retrying a Tool Call That Will Never Work
Most agent failures in production are not bad reasoning, they are bad tool calls: wrong arguments, expired tokens, timeouts.Your Agent Forgets You the Second You Close the Tab
LLMs are stateless, so every new session starts from zero.Your Agent Is One Prompt Doing Six Jobs
A single LLM handling routing, retrieval, reasoning, and execution is easy to prototype and brittle in production.Your Agent Reads 150,000 Tokens Before It Sees the Request
Connect a dozen MCP servers to an agent and you pay for every tool definition on every turn, before the user has said a word.Context Compaction for Long-Running AI Agents
Long-running AI agents fail when context grows without bound, blowing up token costs, latency, and reliability.