diff --git a/README.md b/README.md
index 5be7db3a..e08c75da 100644
--- a/README.md
+++ b/README.md
@@ -765,3 +765,41 @@ Feel free to raise an issue or propose a PR if you have any idea to optimize the
 ### Why no LLM framework is used?
 
 At the time of development, no LLM framework was available to handle all of these features: streaming capability with multi-tools, backup models on availability issue, callbacks mechanisms in the triggered tools. So, OpenAI SDK is used directly and some algorithms are implemented to handle reliability.
+
+### What would it require to make it production ready?
+
+Quality:
+
+- [x] Unit and integration tests for persistence layer
+- [ ] Complete unit and integration tests coverage
+
+Reliability:
+
+- [x] Reproductible builds
+- [x] Traces and telemetry
+- [ ] Operation runbooks for common issues
+- [ ] Proper dashboarding in Azure Application Insights (deployed with the IaC)
+
+Maintainability:
+
+- [x] Automated and required static code checks
+- [ ] Decouple assistant from the insights in a separate service
+- [ ] Peer review to limit the bus factor
+
+Resiliency:
+
+- [x] Infrastructure as Code (IaC)
+- [ ] Multi-region deployment
+- [ ] Reproductible performance tests
+
+Security:
+
+- [x] CI builds attestations
+- [ ] GitOps for deployments
+- [ ] Red team exercises
+
+Responsible AI:
+
+- [x] Harmful content detection
+- [ ] Grounding detection with Content Safety
+- [ ] Social impact assessment