# Platform

Developer experience, self-service, and internal tooling for AI platform teams.

## Core Concepts

| Concept | Description |
|---|---|
| **Internal Developer Platform (IDP)** | Self-service platform for AI teams to deploy models and apps |
| **Model Serving as a Service** | Managed inference endpoints abstracting infrastructure |
| **Prompt Management** | Versioned, reviewed prompt templates shared across teams |
| **Cost Showback** | Attributing AI inference/training costs to teams and products |
| **Golden Paths** | Paved-road templates for common AI workloads (RAG, fine-tuning, eval) |
| **Self-Service Evals** | Teams run their own evals without platform team involvement |

## Decision Guidance

| Situation | Recommended Approach |
|---|---|
| Many AI teams, one platform | Build an IDP with golden paths for RAG and fine-tuning |
| Cost visibility needed | Tag inference/training spend by team; monthly showback |
| Prompt sprawl | Central prompt registry with versioning and review |
| Repeated infra setup | Paved-road templates (Terraform/Helm) for common workloads |

## Anti-Patterns

| Anti-Pattern | Fix |
|---|---|
| Every team reinvents model serving | Golden path: one supported serving stack |
| No cost visibility | Tag all AI spend; showback to teams |
| Prompts hardcoded in apps | Central prompt registry with versioning |
| Platform team becomes bottleneck | Self-service evals and deployment; platform enables, doesn't gate |

## Related Notes

- [[AgenticEngineering/Production/Deployment-Architecture.md]] — Serverless, containers, edge, hybrid
- [[AgenticEngineering/Production/Cost-Optimization.md]] — Caching, model selection, token budgets
- [[MLOps/]] — Deployment and training pipelines
- [[Inference/]] — Model serving and inference engines
- [[Observability/]] — Monitoring AI systems

## Sources

* Backstage, Humanitec, AWS Proton, Google Cloud AI Platform, Azure ML, Internal Developer Platform patterns, Team Topologies, platform engineering community.*