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.
Listen to the full conversation: go.mlops.community/8th2va
Spotify: open.spotify.com/episode/7xZ…
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.
Full conversation here: go.mlops.community/n8nios
Spotify: open.spotify.com/episode/3HZ…
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.
Listen to the conversation: go.mlops.community/m5dgdo
Spotify: open.spotify.com/episode/6Gq…
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.
Catch the episode: go.mlops.community/wlp2z2
Spotify: open.spotify.com/episode/2AS…
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.
Listen here: go.mlops.community/ve06af
Spotify: open.spotify.com/episode/3Ws…
James Barney (MetLife) on tying token spend to cost per business outcome, and why a cheaper model you have to run twice can double the bill.
Hear the whole thing: go.mlops.community/kmixqd
Spotify: open.spotify.com/episode/5eS…
AAIF Community retweeted
AWS has ~16,000 APIs, so its MCP server runs in code mode. @JamesWard (@AWS) on why agent-written Python is hard to review, and the restricted, schema-validated DSL he's testing instead.
AWS has ~16,000 APIs, so its MCP server runs in code mode. @JamesWard (@AWS) on why agent-written Python is hard to review, and the restricted, schema-validated DSL he's testing instead.
Hear the whole thing: go.mlops.community/y07qhw
Spotify: open.spotify.com/episode/0Ex…
A server that lists its skills and serves them as resources, so tools ship with instructions for using them. Ola Hungerford of @Nordstrom on Skills over MCP, dependency gaps, and the context bloat that returns at hundreds of skills.
Catch the episode: go.mlops.community/9l7v0d
Listen here: open.spotify.com/episode/7Ar…
WebMCP moves tool calling into the web page, scoped to the page you are on and running in your logged-in session, instead of an agent screenshotting and searching the accessibility tree. Angie Jones on why that matters and what still blocks adoption.
Full conversation here: go.mlops.community/sy8ks7
Spotify: open.spotify.com/episode/5nZ…












