Struct
AI agent that root-causes engineering alerts
575 followers
AI agent that root-causes engineering alerts
575 followers
Struct is an AI agent that root-causes engineering alerts using logs, metrics, traces, and code. Resolve incidents faster with a composable, customizable system that deploys in minutes and works with your existing DevOps workflows.
Congrats guys - I’m curious since this is a crowded space what’s your favorite counter point / unique thing about your approach?
Struct
@dexhorthy great question - upfront, we're leaning into composability and customizability. you can build your own SRE agents and runbooks that are complementary to your existing workflows and agents, and of course, you can set it up and try it out for free in <5 minutes.
longer term, we're planning to take a much more proactive approach that is more tightly coupled to low-level observability data. stay tuned for more on this.
Autumn
Great product that we’re really enjoying using. Congrats on the launch!!
Struct
@ay_ush We're so glad you guys are loving the product! Amazing customers also working on a great product ❤️
OpenFunnel(YC F24)
Congrats on the launch - we are very happy users !
Struct
@aditya_lahiri Excited to support you guys and your product's growing scale!
Excited for this launch, we've been in Structs alpha, very impressed with Nimesh and Deepan, and Struct's capabilities. Its now my go to to triage alerts that are complex and stateful. Its a key piece of our infrastructure at Fermat as shipping velocity increases rapidly with coding agents.
Struct
@shreyas_kumar4 we’re so excited to be able to help you tackle this new bottleneck of ensuring your code is working well in production, now that your dev output has exploded!
Congrats! The gap between vibe-debugging and vibe-coding is massive and this is extremely needed
Is there a way to communicate “tribal knowledge” to the agent so that it can do more informed investigations?
@antonio_vespoli Yes! We have the ability to provide additional instructions throughout the configuration. Additionally, we have a memory that informs the agent from past investigations, which makes it get it right more going forward.
As someone who's woken up to countless night pages, I really like the trajectory of the product. I usually find that the most difficult issues are the ones not clearly traceable through logs or code. These require deeper understanding of the system infra and the relation between services. Plus, in practice you'll never have logging available for every situation.
I'm curious whether Struct is able to analyze and correlate between different metrics/dashboards/graphs for issues that are not apparent from log dives.
@tteer Yup! Metrics is a core source. We plug into most metric sources, whether it is your cloud provider, Prometheus, Datadog, etc. It's incredibly valuable for debugging systemic issues, identifying recurring patterns, and evaluating impact.
Merge
Really great team and product! We’ve been working with them through beta and it’s been an incredible experience. Huge congrats on the launch!!!
Struct
@gil_feig It's been amazing partnering with you as well! Thank you so much for your support!