# C# and .NET AI modernization

C# and .NET teams use Arviser for Semantic Kernel planners, Blazor or minimal-API streaming, and Azure content-filter interactions that silently break multi-step tools. We document pass marks on latency, groundedness, and tool-call counts. €2,400 24h PoC when filter or planner behavior is unknown; €3,900 40h Prototype with Docker and smoke evals; €3,100 harness when CI lacks regression detection. Hardening €5,600; MVP €8,500 with RBAC hooks; independent audit from €8,000. Credits from Risk-Shared PoC apply toward MVP within 60 days on Go outcomes.

**Sprints from €2,400 PoC · €3,100 eval CI · €3,900 prototype · €5,600 hardening · €8,500 MVP · audit from €8,000** · Topic: `engineering-csharp` · [Open proof](/#open-proof) · [Sample scorecard](/sample)

HTML: [/engineering/csharp](/engineering/csharp) · Markdown: [/engineering/csharp.md](/engineering/csharp.md)


_.NET modernization with LLM assist_

## Why teams trust this stack with Arviser

- Stack-specific gates for C# and .NET AI modernization, not generic AI slideware.
- Senior engineers (10+ yrs) with daily eval tooling; founder architecture review (30+ yrs IT).
- Proof links include Open proof and sample scorecards, commercial sprints stay fixed-scope.

## Dual path

### For CTO / Staff Eng

Senior engineers (10+ yrs) build the vertical slice, wire retrieval and tools, and leave a repo your team can extend, with modular prompts, typed tool schemas, and CI eval fixtures.

### For VP Product / CFO

Fixed-hour packages (€2,400–€8,500) de-risk AI spend: kill fees on Risk-Shared PoC when narrow hypotheses fail, 100% PoC credit toward MVP on Go, and no surprise T&M overruns inside written scope.

Route: 24h PoC (€2,400) if unknown feasibility, else 40h Prototype (€3,900); add 32h Eval CI (€3,100) before scale; harden at €5,600 or ship MVP at €8,500.

## Stack-specific failure modes we gate in eval CI

- Semantic Kernel planners emit duplicate function calls when Azure content filter interrupts mid-plan.
- .NET 9 minimal APIs deserialize enum tool args case-sensitively, failing silently on mobile client payloads.
- IAsyncEnumerable streaming to Blazor Server circuits buffers entire completions, blowing memory on long RAG answers.

### Sample eval fragment (csharp)

```
{
  "SemanticKernelEval": {
    "MaxToolCalls": 3,
    "RefusalBothWays": true,
    "LatencyP95Ms": 1500
  }
}
```

## Which sprint fits?

| Situation | Recommendation | Sprint |
| --- | --- | --- |
| Hard unknown on this stack | 24h Technical PoC | €2,400 · 3–5 days |
| Working demo, no CI evals | 32h Eval CI harness | €3,100 · 1 week |
| Pilot traffic soon | 60h Hardening or 80h MVP | €5,600–€8,500 |

## FAQ

### Do you build C# and .NET AI modernization under fixed scope?

Yes. We deliver written scope in 48h and fixed-hour packages; overruns inside agreed spec are on us.

### Can we start with eval CI only?

Yes, 32h Eval CI from €3,100 when a prototype exists but gates do not.

Reviewed by Vadim Nareyko, 30+ yrs IT · Last updated 2026-11-06

## Related

[Engineering hub](/engineering) · [Open proof](/#open-proof)

