@inproceedings{raptors2026-c054,
  title     = {{Seven Engineering Lessons from Running AI in Production}},
  author    = {Jingar, Nirmal Kumar},
  booktitle = {Proceedings of the Raptors Conference},
  volume    = {1},
  year      = {2026},
  publisher = {Hackathon Raptors},
  address   = {London, United Kingdom},
  doi       = {10.68495/rc.2026.C054},
  url       = {https://doi.org/10.68495/rc.2026.C054},
  abstract  = {This paper draws on the production use of an agentic platform across engineering, product, operations, and business teams. Teams use it to explore supply-chain data, trace delivery estimates, diagnose routing issues, investigate incidents, and answer operational questions. The platform connects models to company data and engineering tools, with identity and access checks, usage limits, audit logging, and monitoring. Since the work spans changing data and multiple systems, teams need to verify answers and understand how they were produced. The paper presents seven lessons: keep policy and execution rules in deterministic code, validate inputs and outputs, limit retries and provide safe fallbacks or human handoff, record decisions for review, enforce permissions and budgets at runtime, deploy in stages with rollback, and separate model reasoning from system actions. It explains how to record useful decision details, such as model and tool versions, validation results, actions, latency, and outcomes, while limiting sensitive data. It also describes a release path from offline evaluation through shadow testing, canary release, measured rollout, and rollback. These lessons are for teams introducing AI into workflows where answers can influence operational decisions. They offer a way to define what the model may do, what the system must verify, and what happens when a check fails. These controls help teams check outputs, recover from failures, and understand decisions.}
}