Threads / Agents in production

Agents in production

What can an agent do on its own, and which tools should it get? Once it starts acting, someone needs a way to find out when it goes wrong.

Follows the tags agentstool-usemcpcontext-engineering · 237 sessions · 2020 to 2026
20211 session
Meetup · MLOps Meetup #70

Machine Learning in Cybersecurity

Monika Venčkauskaitė, Vinted

Pushed backMonika presented government use of open source intelligence as requiring special permissions and serving security purposes, while Demetrios Brinkmann raised concerns that governments could abuse the tools for surveillance.41:28

202318 sessions
Talk · LLMs in Production 2023

LLMs as Intelligent Assistants

Sarah Aerni, Salesforce

Pushed backSarah Aerni rejects replacing human review with fully autonomous generated output and argues that human review remains critical.23:40

Talk · LLMs in Production 2023

Building Production Copilots

Tristan Zajonc, Continual

Pushed backTristan Zajonc says autonomous agents do not work reliably yet, while the host expresses doubt based on what has been implemented so far.17:18

Talk · LLMs in Production 2023

Building Reliable AI Agents

Travis Fischer

Pushed backFully autonomous agents are not yet the right default for production; more deterministic, code-driven agents should be used instead.9:12

Talk · LLMs in Production 2023

Using LLMs to Power Consumer Search at Scale

Aravind Srinivas, Perplexity AI

Pushed backAravind Srinivas rejects describing Perplexity as merely an LLM wrapper, arguing that the product requires substantial orchestration and software engineering around the models.18:18

14 more from 2023 on this thread
202439 sessions
Podcast · MLOps Podcast #204

MLOps at the Crossroads

Patrick Barker, Kentauros AI & Farhood Etaati, AIMedic

Pushed backLLMOps should be treated as a distinct specialization with specialized tools rather than only as an extension of existing MLOps.19:55

Podcast · MLOps Podcast #215

Becoming an AI Evangelist

Alex Volkov, Weights & Biases

Pushed backDemetrios Brinkmann says agents are not yet ready, while Alex Volkov argues that they are improving and should not be expected to remain at their current level forever.1:21

35 more from 2024 on this thread
202594 sessions
Podcast · MLOps Podcast #282

Machine Learning, AI Agents, and Autonomy

Egor Kraev, Wise Plc

Pushed backEgor Kraev disputes the idea that LLMs should be judged as complete solutions or agents, arguing that they are additional components in a larger system.9:33

Reading group · MLOps Reading Group

AI Agents: The Future of ML Engineering?

Matt Squire, Fuzzy Labs

Pushed backSuccess on Kaggle competitions was disputed as evidence that an agent can perform general machine learning engineering or automate scientific discovery.7:38

Podcast · Agents in Production Series

Web Agents: The Cutting Edge of AI is Here?

Paul van der Boor & Chiara Caratelli, Prosus Group

Pushed backThe team found that performance on the WebArena benchmark did not translate reliably to the web-agent tasks they cared about.17:49

90 more from 2025 on this thread
202685 sessions
Reading group · MLOps Reading Group

AI REWIND 2025 - MLOps Reading Group Year-end Special

Sophia Skowronski, Breckinridge Capital Advisors & Rohan Prasad, EvolutionIQ & Nehil Jain, Stealth AI Startup & Sonam Gupta, AICamp & Lucas Pavanelli, Stone

Pushed backRohan Prasad challenged the assumption that adding all available information to ever-larger context windows reliably improves LLM results.15:10

Talk · Agents in Production 2025

Building Agentic Tools for Production

Sam Partee, Arcade AI

Pushed backSam Partee rejected the idea that all tools should be put in one MCP gateway and said agents should not have too many tools.19:26

Podcast · MLOps Podcast #345

Enterprise AI Operations: The Missing Piece

Rani Radhakrishnan, PwC US

Pushed backStarting with one agent and scaling sequentially is not the only valid approach; parallel development can work when processes are standardized and repeated across departments.9:42

Talk

Tool definitions are the new Prompt Engineering

Chiara Caratelli, Prosus Group & Alex Salazar, Arcade.dev

Pushed backAlex Salazar argued that most people should currently use carefully selected, specific tools, while the long-term goal is to let agents choose from many tools.11:49

81 more from 2026 on this thread