AAIF Community

The AAIF community is an open and transparent community where all are welcome to participate. It is a place where Agent builders can collaborate and share

[AAIF Community @mlopscommunity]

Watch here: https://t.co/RiuBdwt7bq

Listen to the conversation: https://t.co/Nd8zx3j5zS

[AAIF Community @mlopscommunity]

AI infrastructure is hitting physical limits: power, cooling, rack density, and hardware supply chains. Zachary Smith of Datum discusses the constraints and how data centers could reuse waste heat.

[AAIF Community @mlopscommunity]

Watch here: https://t.co/RiuBdwt7bq

Listen to the conversation: https://t.co/Nd8zx3j5zS

[AAIF Community @mlopscommunity]

AI infrastructure is hitting physical limits: power, cooling, rack density, and hardware supply chains. Zachary Smith of Datum discusses the constraints and how data centers could reuse waste heat.

[AAIF Community @mlopscommunity]

Watch the conversation: https://t.co/uBkd6i1ENd

Spotify: https://t.co/RplbMVOn1h

[AAIF Community @mlopscommunity]

An AI agent recommended hiring another engineer. Applying the Google SRE handbook’s lens on operational toil changed the answer.

Tim O’Reilly on domain expertise, context engineering, and building more reliable agents.

[AAIF Community @mlopscommunity]

Listen here: https://t.co/Om8mI6zYuu

Spotify: https://t.co/funcXa0dxP

[AAIF Community @mlopscommunity]

AI-generated code needs verification before it reaches a PR. Erica Hughberg and @Dpbrinkm discuss QA sub-agents, workflow-based tests, and using screenshots to catch broken behavior before human review.

[AAIF Community @mlopscommunity]

Listen: https://t.co/7KgbVUKWc8

Spotify: https://t.co/O4OcDoMI5H

[AAIF Community @mlopscommunity]

AI coding ROI isn't measured in lines of code. Pepijn Senders shares how to track token spend against product value and why accepting code you don't understand can create risks in production.

[AAIF Community @mlopscommunity]

Listen to the full conversation: https://t.co/keSMptn4Pk

Spotify: https://t.co/rvj8HkCwdL

[AAIF Community @mlopscommunity]

AI agents can test thousands of attack paths in parallel. A small network vulnerability in a supposedly isolated sandbox can become an escape route.

Erica Hughberg and @Dpbrinkm discuss agent security and bots with buying power.

[AAIF Community @mlopscommunity]

Full conversation here: https://t.co/FGD92b6wk3

Spotify: https://t.co/leQdiOJ0eO

[AAIF Community @mlopscommunity]

Browser agents scraping DOMs and screenshots are slow, token-intensive, and unpredictable. Sarah Drasner of @Google explains how WebMCP exposes defined actions, flags consequential operations, and helps developers guide agents safely.

[AAIF Community @mlopscommunity]

Listen to the conversation: https://t.co/pyOcsOxaXR

Spotify: https://t.co/SP7HnIvwCV

[AAIF Community @mlopscommunity]

Can a narrowly scoped agent outperform a general-purpose setup?

Justin Schroeder, co-founder of Standard Agents, explains how prompts, tools, models, and runtimes shape agent effectiveness - and why standards matter for sharing reliable agents.

[AAIF Community @mlopscommunity]

Catch the episode: https://t.co/EYrtyygDK6
Spotify: https://t.co/eL8l2x0Ra1

[AAIF Community @mlopscommunity]

What if an MMORPG launched already full of agent players instead of scripted NPCs? Issac Lee of NEXUS sees it as a way past a new game’s chicken-and-egg player problem.

[AAIF Community @mlopscommunity]

Listen here: https://t.co/SeXvUFjJhp
Spotify: https://t.co/89lAoZt1M4

[AAIF Community @mlopscommunity]

A prompt bloat flag at C.H. Robinson traced back to a code error that kept a service in a retry loop, using tokens again on every pass. Jason Ward on tracking AI spend with observability metrics.