# AI Harness: the worst and the best buzzword in the industry

> Source: <https://dev.to/ccortezb/ai-harness-the-worst-and-the-best-buzzword-in-the-industry-3nmc>
> Published: 2026-08-29 00:24:20+00:00



```
---
title: "AI Harness: the worst and the best buzzword in the industry"
published: false
tags: [ai, harness, middleware, finops, aws, bedrock, opensource]
series: "TokenOps on AWS"
cover_image: # TODO: circuit-breaker / middleware diagram
---
```

"El mercado habla de 'AI Harness' como si fuera magia. El verdadero arnés de un LLM es un Proxy Inverso y un Middleware Transaccional determinístico. Es el código tradicional (styrr-llm y sayay-guard) el que confina, audita y presupuesta la inferencia probabilística antes de que toque tu infraestructura en la nube."

— TokenOps raw research, Turno 8

"Harness" is the most polarizing word in AI engineering right now. Depending on who you ask it's either the industry's worst buzzword or the best technical concept ever packaged badly. It's both — and the difference is whether you can name the actual engineering underneath.

`requests`

script or an Express server that wraps the OpenAI or Bedrock API.Strip the LinkedIn marketing and the original *test harness* metaphor becomes genuinely powerful for generative AI: **electrical isolation of uncertainty.**

An LLM is a highly unstable, probabilistic component. You cannot wire it directly into a bank's production database. You need a physical code "harness" that isolates it. When the model goes crazy — spewing corrupt text or prompt injections — the harness acts as a circuit breaker / thermal fuse that absorbs the impact and cuts the current.

A good harness guarantees the LLM **never holds control logic**. The model only processes text. The harness handles:

`styrr-llm`

does)`sayay-guard`

does)Post 2 of **TokenOps on AWS**. In post 1 we established the ontology as the grounding ledger; here we name the harness for what it is — transactional middleware. Post 3 completes the picture by stripping every buzzword down to infrastructure primitives.

The real "AI Harness" is three composable packages, all published, all zero hard dependencies:

```
npm install @carloscortezcloud/sayay-guard   # budget control (the financial circuit breaker)
npm install @carloscortezcloud/styrr-llm      # physical routing (the reverse proxy)
npm install @carloscortezcloud/tinkuy-agent   # format translation (the schema middleware)
```

Budget is checked **before** inference, recorded **after**. On block, it raises a native `TokenBudgetExceededException`

that Step Functions matches in its Catch block — the harness cuts the current *before* the retry bill grows:

``` js
import { SayayGuard, DynamoStorage } from '@carloscortezcloud/sayay-guard';

const guard = new SayayGuard({
  storage: new DynamoStorage({ tableName: 'sayay-ledger' }),
  budget: { dailyUsd: 5 },
});

// Throws TokenBudgetExceededException on block → ASL ErrorEquals catch
const decision = await guard.checkOrThrow('user-42', 0.005);
// ASL: the harness's circuit breaker trip
"Catch": [{ "ErrorEquals": ["TokenBudgetExceededException"], "Next": "HandleBudgetExceeded" }]
```

Physical routing of inference — decide in microseconds which endpoint gives the best cost per compute unit:

``` js
import { StyrRouter } from '@carloscortezcloud/styrr-llm';

const router = new StyrRouter({
  apiKey: process.env.OPENROUTER_API_KEY!,
  models: [
    { id: 'anthropic.claude-3-sonnet-20240229-v1:0', provider: 'bedrock' },
    { id: 'meta-llama/llama-3.3-70b-instruct:free', provider: 'openrouter' },
  ],
});
```

**1. Isolation, not magic.** A harness's job is to isolate the black box: the model stays behind the middleware, the production system stays in front. Nothing else.

**2. Separation of responsibilities.** Auth, routing, budget, format translation — four traditional software jobs, four layers, zero "agentic" smoke.

**3. TokenOps renames the harness.** From the raw research: *"Al llamarlo por su nombre técnico (Middleware, Proxies, Circuit Breakers), educas a la comunidad de AWS y demuestras que el control de la IA no se logra con más IA, sino con ingeniería de software robusta y tradicional."*

`block`

, not `warn`

, is what stops the bill.`npm install @carloscortezcloud/sayay-guard`

`npm install @carloscortezcloud/styrr-llm`

`TokenBudgetExceededException`

pattern"The No-Buzzwords Manifesto: your AI stack is Buffers, Load Balancers, and State Machines"

*Built by Carlos Cortez — AWS Community Hero, Lima, Perú. Part of the TokenOps open-source ecosystem.*