---
title: "How Small Models Think Big"
newsletter: "MLOps Community"
date: 2025-11-06
source: https://aaif.live/newsletters/mlopscommunity/2025-11-06-how-small-models-think-big
---

# How Small Models Think Big

*Plus… stress-testing MCP agents, securing GCP endpoints, and scaling ML jobs on Kubernetes.*

*MLOps Community — Agentic AI Foundation, 2025-11-06*

Is impulse shopping the new Turing test [https://go.mlops.community/NL_Intro_Nov6]?

## Rubric Roulette

Benchmarks built by LLMs, for LLMs, judged by LLMs.

Progress or a feedback loop with better grammar?

## Less is more

At least “less but smarter” can take the moral support to the bank.

## Hidden Gems

## Job of the Week

[https://go.mlops.community/NL_Jobs_Board](https://go.mlops.community/NL_Jobs_Board)

## Fine-Tuned Models Are Getting Out of Hand

When agents start watching your screen, that’s when things get real. The discussion explores what happens when enterprise AI shifts from chat interfaces to full-blown digital coworkers that see how you work, learn your decisions, and start acting on your behalf.

 * Fast vs slow data: RAG handles “fast” factual retrieval, but fine-tuned small models capture the why behind decisions - the slow data that defines judgment.
 * Small models, big context: SLMs can be trained cheaply to mirror individual workflows, encoding how specific roles think and act.
 * From chatbots to doers: The next step is agents that control tools directly - editing, emailing, or coding with human-like intuition.

The endgame? A billion personalized small models, each fine-tuned to how you work.

Video [https://go.mlops.community/NL_Pod_G_Nov6] || Spotify [https://go.mlops.community/NL_Pod_S_Nov6] || Apple [https://go.mlops.community/NL_Pod_A_Nov6]


STRESS TESTING AND DIAGNOSING MCP-ENABLED AGENTS ON CHALLENGING QUERIES

Agents that use live MCP tools still stumble - in a new 101-task benchmark, even top models solved only ~58% of multi-step, screen-realistic jobs.

 * How it’s built: 101 time-varying tasks across real MCP servers, with a reference run plus a test agent. Scoring checks both the final answer and the tool-use trajectory to reduce drift.
 * What breaks: Wrong tool picks and bad parameters dominate, plus “answer without tools” misfires. More iterations help up to ~30, but token waste rises.
 * Caveats: One-shot runs and an LLM-as-judge introduce variance and potential self-preference.

Net: promising, but tool reliability and evaluation hygiene must improve before trusting agents with critical workflows.

Watch the Reading Group [https://go.mlops.community/NL_RG_Nov6]


DEPLOYING AI AGENTS IN THE ENTERPRISE WITHOUT LOSING YOUR HUMANITY USING ADK AND GOOGLE CLOUD

Shipping an agent without punching holes in your VPC is possible. This piece shows how to expose UI, API, and agent-to-agent endpoints on GCP while keeping identity end-to-end.

 * Identity propagation: use IAP at the edge, IAM for policy, and signed JWTs with strict audience for A2A.
 * Cloud Run sweet spot: one container serves UI, API, and A2A, scales to zero, simple ops.
 * Vertex AI Agent Engine: managed API path with monitoring, limited flexibility for custom UI or A2A.

Bottom line: secure exposure today with Cloud Run + IAP, while AgentSpace matures.

Read the blog [https://go.mlops.community/NL_Blog_Nov6]


IN PERSON EVENTS

 * Helsinki [https://go.mlops.community/NL_IRL_Helsinki_Nov6] - November 6
 * London [https://go.mlops.community/NL_IRL_London_Nov12] - November 12


VIRTUAL EVENTS

 * Agents in Production - MLOps x Prosus [https://go.mlops.community/NL_VEvent_Nov18] - November 18
   Learn how leading teams from OpenAI, NVIDIA, Meta, and Google DeepMind are turning agentic AI experiments into production systems.

[Video](https://go.mlops.community/NL_Pod_G_Nov6)

## A little space

[https://go.mlops.community/NL_Confess](https://go.mlops.community/NL_Confess)

## Making the hard stuff simpler

Working on something tricky or planning ahead? Here’s how we can help - just hit reply:

 * Custom workshops tailored to your company’s needs
 * Hiring? I know some quality folks looking for a new adventure
 * Want to connect with someone tackling similar problems? I can introduce you

Thanks for reading, catch you next time!

---
Source: https://aaif.live/newsletters/mlopscommunity/2025-11-06-how-small-models-think-big