Ask HN: What are the biggest limitations of agentic AI in real-world workflows?
There’s a lot of momentum around agentic AI systems that can plan and execute multi-step workflows autonomously.
For teams that have tried deploying these in production environments, where do they actually break down?
Is it reliability over long action chains, tool integration issues, cost unpredictability, state management, latency, observability, or something else entirely?
I’m especially interested in failure modes that only became obvious after moving beyond controlled demos into real usage.
6 comments
[ 3.3 ms ] story [ 21.3 ms ] threadConstraint adherence degrades over long chains. You can put rules in system prompts, but agents follow them for the first few steps, then gradually drift. Instructions are suggestions. The longer the chain, the more they're ignored.
Cost unpredictability is real but solvable.
Ultimately, the systems need external enforcement rather than internal instruction. Markdown rules, or jinja templates etc., that the agent can read (and ignore) don't work at production scale. We ended up solving this by building Python enforcement gates that block task completion until acceptance criteria are verified, tests pass, and architecture limits are met. The core learning being that agents can't bypass what they don't control.
Curious; have you seen drift follow a pattern, like step count or constraint complexity?
We’ve tried hybrid setups: ephemeral agent state plus external validation gates. Cuts down rollbacks while keeping control tight.
Would love to hear if anyone else has experimented with something similar.
Your external gate instinct is right, but the gate has to be structurally external, not just logically external. If the agent can reason about the gate, it can learn to route around it.
We’ve been experimenting with pre-authorization before high-impact actions (rather than post-hoc validation) - I've drafted Cycles Protocol v0 spec to deal with this problem.
What’s interesting is that anomalous reservation patterns often show up before output quality visibly degrades — which makes drift detectable earlier.
Still early work, but happy to compare notes if that’s useful.
This is especially true. Earlier iterations of our build had python backed enforcement modules in an accessible path. The agent would identify the module that was blocking completion and, instead of fixing the error, it would access the enforcement module and adjust the code to unblock itself.