What breaks your AI agents?
@gregisenberg709K followers
29,231 views
33 Comments
Comments from the original post on X (Twitter)

@NotionHQ
hi friends @Shopify @github @figma @whatagraph
10 likes

@gregisenberg
@Shopify @github @figma @whatagraph we are a happy family
2 likes

@njpCoder
Love the video
1 like

@TiTan_Web3_
The model gets blamed; stale state and oversized permissions usually did the damage
1 like

@itsthedonhashim
@gregisenberg trying to get them to handle unexpected inputs without breaking. learned the hard way that flexibility is key.
1 like

@adriankxyz
Another banging video
1 like

@promptyx_ai
I think my AI Agents instead break my brain
1 like

@kemalegebuilds
permissions drift and silent tool failures. agents rarely die in the prompt. they die when a tool returns almost-right data and nobody logged the handle.

@DrBuscema
for me its usually unclear ownership. agent does the draft fine then nobody owns the weird case so it all lands back on the founder

@JasonDigital
Mine always break if I do no marketing.

@LeaT_Design
breakage is the feature. my agents just don't talk to each other. like toddlers with nukes. shit.

@MINDFUEL_NIRAJ
The quality of video is very good btw greg👀🫶🏻

@KanjiNoguchi
For us it's almost never a 500 — it's a 200 with an empty array. We run a Japanese wholesale catalog that agents call directly, and queries land as short category nouns in whatever language the human typed; the agent passes that phrasing straight through instead of rewriting it for the index. When it misses, nothing errors, so the agent concludes the product doesn't exist and moves on. The other killer is latency shape: our product-detail reads sit around 20ms while search is two orders of magnitude slower, and search is the first call every agent makes. A slow front door in front of fast reads loses agents before they ever reach the useful part.

@alexandrekerner
@Abidebyabid Love the video, what did u use to make it?

@ChinazaJos10
What breaks AI agents is relying on a single model without independent review. That’s why we use human-in-the-loop multi-agent orchestration: architecture, independent model review, and strict validation before execution.

@joulsounet
Long context plus a stale rule file is my usual failure mode

@MaR1236Cool
What breaks agents for me: flaky tools + silent context rot. Curious what your top failure mode is when they look smart until they… don’t.

@carpenter_17992
Usually the tool loop—not the model: one bad retry policy can burn the budget while every individual call looks “successful.”

@Relaystack
Bad instructions.

@nordinbuilds
Context collapse mid-task.












