[{"content":"I keep seeing invoice processing built as a crew of AI agents that burns hundreds of dollars a month in tokens, when a script plus one LLM call does the exact same thing for less than 10 shekels. Or lead routing \u0026ldquo;upgraded\u0026rdquo; to an autonomous agent, and suddenly leads go to the wrong teams because of a small hallucination, while the Zapier flow it replaced did the job with zero extra cost.\nPart of the problem is naming. Every simple automated process, including scripts that have been running for 20 years, now gets the title \u0026ldquo;AI agent\u0026rdquo;. The mislabeling leads to bad decisions: the wrong tool gets chosen, and real money gets wasted.\nUsing a full agent for a task that a script or a regular workflow solves in 10 minutes costs more (reasoning loops, multiple model calls, retries), runs slower, is harder to debug, and is often less reliable because it \u0026ldquo;thinks too much\u0026rdquo; about simple things.\nThere are three tiers. Workflow automation is rule-based: if X, do Y. Scripts, ETL, a Zapier flow. An AI-enhanced workflow is that same linear flow with one step that calls a model as a black box, which is what lets it handle unstructured input: classify, extract, summarize. An autonomous agent gets a goal instead of a script, and decides the order of steps, which tools to use, and what to do when something fails.\nMost of what gets built as tier 3 is tier 2. Here is where the line actually fell on a system we shipped.\nOne system, both sides of the line We built a WhatsApp support system that answers customer messages with AI. Two decisions in it landed on opposite sides of the line, and the second cost far more than the first.\nThe first was deciding which inbound messages the AI is allowed to answer at all. That sounds like judgment, so it sounds like a job for an agent. It is one model call in a linear flow. A guard classifies each message into one of four verdicts (reply, escalate to a human, ignore, reject) and the flow branches on the answer. No planning, no tool selection, no loop. Tier 2, and it has been the most reliable part of the system.\nTier 3 was the right call for the conversation itself. Nobody can script a support dialogue. But that is where the bill came due.\nWhat the agentic tier actually costs On paper the conversation loop worked. A 50-turn live battery produced no errors and no silences.\nWhat it produced instead was the failure mode of the tier. The agent claimed it had handed the conversation to a human when it had not. It sent empty acknowledgements. It leaked its own tool calls and reasoning into customer replies. None of that appears in an error log. All of it appears to the customer.\nFixing it was not one bug. It was handover confirmation, recovery for responses that came back with no text, language-aware fallbacks, containment for tool output, and a cap on iterations. That is the real price of tier 3, and it is not the token bill.\nThere is a smaller lesson in the guard, and it points the same way. When mixed messages started slipping past it, the obvious fix was another conditional in the prompt. That change turned real customer messages into silent skips. What worked was narrowing the existing rule rather than adding a new one. In a linear flow you can find that in an afternoon, because there is one step to test. In an agent loop the same class of bug is somewhere in fifty turns of context.\nStart boring Build the simplest thing that works. Move up a tier only when the one below it has visibly hit its limit, and budget for the guardrails, not just for the tokens.\n","permalink":"https://blog.box.devly.me/posts/boring-automation-still-wins-rewrite/","summary":"Most of what we automate needs boring, safe automation, not an agent. Where the line actually fell on a system we shipped.","title":"Boring Automation Still Wins: Why You Shouldn't Agentify Everything"},{"content":"I keep seeing invoice processing built as a crew of AI agents that burns hundreds of dollars a month in tokens, when a script plus one LLM call does the exact same thing for less than 10 shekels. Or lead routing \u0026ldquo;upgraded\u0026rdquo; to an autonomous agent, and suddenly leads go to the wrong teams because of a small hallucination, while the Zapier flow it replaced did the job with zero extra cost.\nPart of the problem is naming. Every simple automated process, including scripts that have been running for 20 years, now gets the title \u0026ldquo;AI agent\u0026rdquo;. The mislabeling leads to bad decisions: the wrong tool gets chosen, and real money gets wasted.\nUsing a full agent for a task that a script or a regular workflow solves in 10 minutes costs more (reasoning loops, multiple model calls, retries), runs slower, is harder to debug, and is often less reliable because it \u0026ldquo;thinks too much\u0026rdquo; about simple things.\nMost of what we automate today needs boring, safe automation, not an agent that tries to act like a human. There are 3 tiers, and picking the right one is the whole game.\nWorkflow automation A rule-based process that performs repetitive tasks predictably: if X happens, do Y. Scripts that process files, ETL in Airflow, Zapier flows connecting apps. No thinking, no adaptation, just reliable and cheap execution.\nAI-enhanced workflow The same linear, predefined flow, with one step that calls an AI model as a black box. In an email processing flow: step 1 scans the message, step 2 classifies it with a model (spam/urgent/order), step 3 sends a notification. The tools are an OpenAI or Google Cloud AI API inside a flow like Make or n8n.\nThe AI adds the ability to handle unstructured content (classification, extraction, sentiment), but the process itself stays linear and predefined. This tier covers most of the cases people reach for agents to solve.\nAutonomous agent Receives a goal, not a script. It plans, decides the order of actions, chooses tools, corrects mistakes, and asks for clarification when stuck. It can handle a request like \u0026ldquo;plan me a family trip on budget X\u0026rdquo;, including weather checks, bookings, and adjustments along the way.\nChecklist: do you really need an agent? Does the process repeat in 95%+ the same way every time? → Workflow automation Is most of the data structured, with clear if-then rules? → Workflow automation Do you need AI in only one specific step (classification, extraction, generation)? → AI-enhanced workflow Does the system need to decide the order of steps on its own? → Autonomous agent Does it need to pick tools dynamically based on what it discovers? → Autonomous agent Does it need to recover from failures on its own (try a different approach, switch tools, ask a human)? → Autonomous agent Does the \u0026ldquo;right\u0026rdquo; way to perform the task change mid-process as new information arrives? → Autonomous agent Is the task so variable or creative that fixed rules are impossible or need endless maintenance? → Autonomous agent (start with a prototype) Are you willing to accept higher costs, longer debugging, occasional weird behavior, and the need for guardrails? → Only then build a full agent Can you get 80% of the value with simple rules plus one LLM call in a regular flow? → Do that first In short: start boring. Build the simplest thing that works. Move to an autonomous agent only when the workflow has proven it is hitting its limit, and you have the budget to monitor token spend.\n","permalink":"https://blog.box.devly.me/posts/boring-automation-still-wins/","summary":"Most of what we automate needs boring, safe automation, not an agent. Three tiers, and a checklist for picking the right one.","title":"Boring Automation Still Wins: Why You Shouldn't Agentify Everything"},{"content":"This is a placeholder post so the theme has something to render. Delete it once there is a real one.\nCreate the next post with:\nhugo new content posts/my-post.md It starts as a draft. Drop draft: true from the front matter when it is ready to publish.\n","permalink":"https://blog.box.devly.me/posts/hello-world/","summary":"The obligatory first post, and a note on how this site is built.","title":"Hello World"},{"content":"Placeholder. Say who you are here.\n","permalink":"https://blog.box.devly.me/about/","summary":"About","title":"About"}]