At 11:51 on August 9, 2025, an actor researchers track as GRUB1 tried to validate a stolen Cloudflare API token against the Salesforce API using TruffleHog's user-agent string — a tool built for finding leaked secrets, repurposed here to confirm one actually worked. That attempt failed. At 22:14, it didn't. 

That definition of service reliability has changed dramatically.

This article covers what slopsquatting is, why it is different from typosquatting, the documented incidents in 2025 and 2026, and a practical defense stack you can put in your pipeline this sprint.

The fastest way to exceed a document pipeline budget is to let an LLM inspect every document before you have performed lightweight filtering. This sounds obvious, but the bottleneck is invisible at the prototype stage. A single model call is cheap, and it works well on the 20 documents in your test set. Then you hit production traffic.

The failure mode is usually pretty similar across teams: tens of thousands of LLM calls per day, tens of millions of tokens, and a monthly bill that drifts past the assigned budget. No candidate generation. No triage. Raw corpus straight to the model. The cost compounds because the corpus does not shrink without an upstream triage. A more capable model just gives you a more expensive way to process noise.

That’s the orchestration problem — and it’s quietly costing teams months of rework, bloated infrastructure spend, and AI systems that stall at the pilot stage and never reach production scale.

For three years, the industry has obsessed over one question: can we build intelligent systems? That question is basically settled. The models are good — good enough that nobody serious argues otherwise anymore.

You moved your routine AI work to a cheaper model, so you think the cost question is handled; however, often, that is not the case. The decision lives in one person’s head and produces nothing that the person accountable for the invoices can read. Worse, it is an architectural choice nobody documented. 

The AI Routing Policy is the missing artifact of Stage 2 of the Delegation Lifecycle: it records which execution path, from a cheaper model to a frontier model to plain code, handles each class of work, what counts as good enough output to meet the AI Definition of Done, and who owns the call. The skill it needs to work is one you already have: You write acceptance criteria.

The Problem Nobody Puts on the Roadmap

Every AI project starts the same way. Someone wires up a call to an LLM, the demo works, and the room gets excited. Then it goes to production, and within a week:

I have heard a version of this for fifteen years. The app ships. The customers are happy. The code is unfashionable. And somebody wants to tear it down and rebuild it on a stack that looks better on a resume.

There's an idea making the rounds in B2B SaaS product and engineering meetings right now. It sounds reasonable. It feels optimistic. And it's leading companies straight into the same trap they've always fallen into, just at an accelerated rate.

An alert fires at 2 am. An engineer wakes up, SSHs into a server, and begins the manual loop — pulling logs, scanning for errors, guessing what to check next. This loop can take 15 to 45 minutes before the real diagnosis even begins. Multiply that across every incident, every team, every month, and you have thousands of engineering hours lost every year to work that is repetitive, stressful, and largely automatable.

Two figures from the past year carry most of the story.

The agent loops on itself and burns through your token budget. After shipping a few of these systems, I have learned that the durable design question is not "can the agent call a tool" but "what happens when the tool call goes wrong."