# AI tooling for runtime and production

Runtime methods have little AI-native tooling: what exists is mostly a
feature inside a general-purpose assistant, or a classical technique
that never needed a model. The field moves quickly, and these entries
may be out of date.

## Contracts and runtime assertions

No mature AI-native contract tool exists; contract generation is a
feature inside general-purpose assistants, which write
[Pydantic](https://docs.pydantic.dev/) or dataclass validators from docstrings.
**Daikon** (Ernst et al. 2007)[^ernst2007] mines invariants classically and is the non-AI
baseline for separate research that translates natural-language intent
into formal postconditions (Endres et al. 2024)[^endres2024]. That work stops at the
research stage: nothing yet turns inferred invariants into enforced
runtime guards, the step that would carry the technique from
documentation into a live check.
[Contracts and runtime assertions](https://quality.stereobooster.com/contracts-and-runtime-assertions.md)
covers the method itself, written contracts as well as inferred ones.

## Monitoring and observability

**Query authoring** is the capability that holds up: Honeycomb's Query
Assistant solves a query problem, not a causal-inference one.
The major observability platforms (Datadog, New Relic, [Grafana](https://grafana.com/)
Sift, Dynatrace, Splunk, PagerDuty) add a real summarization layer;
their *root-cause* claims are overstated. AIOps is the research area
behind those features (Notaro et al. 2021)[^notaro2021].

## Chaos engineering

Production platforms (AWS Fault Injection Service, Chaos Mesh,
LitmusChaos, Steadybit) have no AI features worth naming.
**[ChaosEater](https://github.com/ntt-dkiku/chaos-eater)** (Kikuta et al. 2025)[^kikuta2025a] is a research LLM agent that
designs and runs experiments; it is not production-ready.

## References

[^ernst2007]: Ernst, Michael D., Jeff H. Perkins, Philip J. Guo, et al. 2007. "[The Daikon system for dynamic detection of likely invariants](https://people.csail.mit.edu/cpacheco/publications/daikon-tool-scp2006.pdf)." *Science of Computer Programming* 69 (1–3): 35–45. <https://doi.org/10.1016/j.scico.2007.01.015>.
[^endres2024]: Endres, Madeline, Sarah Fakhoury, Saikat Chakraborty, and Shuvendu K. Lahiri. 2024. "[Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?](https://arxiv.org/pdf/2310.01831)" *Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering (FSE 2024)*, 1889–912. <https://doi.org/10.1145/3660791>.
[^notaro2021]: Notaro, Paolo, Jorge Cardoso, and Michael Gerndt. 2021. "[A Survey of AIOps Methods for Failure Management](https://jorge-cardoso.github.io/rd/Papers/JA-2021-025-Survey_AIOps_Methods_for_Failure_Management.pdf)." *ACM Transactions on Intelligent Systems and Technology*, 1–45. <https://doi.org/10.1145/3483424>.
[^kikuta2025a]: Kikuta, Daisuke, Hiroki Ikeuchi, and Kengo Tajiri. 2025. "[LLM-Powered Fully Automated Chaos Engineering: Towards Enabling Anyone to Build Resilient Software Systems at Low Cost](https://arxiv.org/pdf/2511.07865)." *2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)*, 3861–65. <https://doi.org/10.1109/ase63991.2025.00331>.