---
title: "When Your Agent Books the Flight"
newsletter: "MLOps Community"
date: 2025-10-30
source: https://aaif.live/newsletters/mlopscommunity/2025-10-30-when-your-agent-books-the-flight
---

# When Your Agent Books the Flight

*Plus… decoding pretraining pipelines, scaling RL laws, and GPU comms you’ll actually use.*

*MLOps Community — Agentic AI Foundation, 2025-10-30*

Every Halloween there are stories about drugs given to trick-or-treaters. Every year I go out but come back with just candy.

Anyway, the real danger this year is in your training data - it could be spiked to make your model hallucinate. Anthropic just showed a few samples can corrupt even the biggest models [https://go.mlops.community/intro30oct].

## Scaling Fatigue

The scaling race never stopped to ask if less could do more.

Is efficiency the real frontier - or just the unfunded one?

## I’ll never leave you.

You've all set your stacks to be the AI version of Annie Wilkes in Misery.

## Hidden Gems

## Sr. Developer Advocate, Machine Learning // Databricks (Seattle, WA, USA)

Databricks is seeking a Senior Developer Advocate to engage and support the data science and ML community. The role focuses on education, outreach, and technical advocacy for Databricks’ AI and ML platforms, including Mosaic AI and MLflow.

Responsibilities

 * Create technical content on ML, MLOps, and LLMOps best practices
 * Speak at events and host community meetups for data practitioners
 * Collaborate with product teams to represent developer needs
 * Build and maintain open-source and educational resources
   

Requirements

 * 5+ years in DevRel, engineering, or solution architecture
 * Strong skills in Python, SQL, PyTorch, and scikit-learn
 * Experience contributing to open-source or technical communities
 * Proven ability to teach and communicate complex ML concepts

Find more roles on our new jobs board [https://go.mlops.community/jobsnl] - and if you want to post a role, get in touch.

[Sr. Developer Advocate, Machine Learning](https://go.mlops.community/usjob30oct)

## Best AI Hackathon Project Ever | Unicorn Mafia Wins $100,000+

Something a bit different: a hackathon story about building an AI travel agent in under a week. Building an AI agent that books a full group holiday sounds fun - until it starts handling your credit card. This hackathon team did both.

 * Secure agent transactions: They used browser automation and Skyvern to book real flights and hotels, with Stripe’s one-time virtual cards enabling safe, autonomous payments.
 * Guardrails for chaos: Multiple agents worked together through a custom orchestrator, managing everything from WhatsApp chats to voice calls without losing control.
 * Bleeding-edge integrations: ElevenLabs’ new dial-tone API was wired in days after release, letting the agent navigate real phone menus.

A working multi-agent travel planner with real revenue - all built in under a week.

Video [https://go.mlops.community/ghw30oct] || Spotify [https://go.mlops.community/shw30oct] || Apple [https://go.mlops.community/ahw30oct]


PRETRAINING: BREAKING DOWN THE MODERN LLM TRAINING PIPELINE

Pretraining is where LLMs learn most of what they know. Misread it and you ship brittle models, burn compute, and get weird failure modes.

 * Pipeline: Next-token CLM builds world knowledge, then post-training aligns behavior - ULMFiT and InstructGPT shaped this baseline.
 * Data at scale: Trillion-token corpora, strict curation, and Chinchilla-style data-parameter balance matter more than sheer model size.
 * New twists: Instruction-augmented corpora, multi-phase and continual pretraining, plus RPT recasting pretraining as RL to boost zero-shot reasoning.

Get the pretraining map right and downstream results get a lot more predictable.

Read the blog [https://go.mlops.community/blog30oct]


IN PERSON EVENTS

 * San Jose [https://luma.com/eqatoz90] - October 30
 * Helsinki [https://luma.com/29uac5sx] - November 6
 * London [https://luma.com/agentworldtourlondon] - November 12


VIRTUAL EVENTS

 * Agents in Production - MLOps x Prosus [https://home.mlops.community/home/events/agentsinproduction2025-mlops-prosus] - 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/ghw30oct)

## Chronologically Cursed

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

## 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/2025-10-30-when-your-agent-books-the-flight