# Engineering stacks for AI delivery

Arviser maps forty-plus engineering routes: Python, TypeScript, Go, Rust, mobile shells, and platform serving to fixed sprint SKUs instead of open-ended staff aug. Pick a child stack page, cite its topic slug in the scope form, and we attach the right eval recipe within 48 hours. Start with a 24h PoC (€2,400) when retrieval or latency is unproven, a 32h Eval CI harness (€3,100) when code exists without gates, or a 40h Prototype (€3,900) for a vertical slice. Hardening runs €5,600; production MVP €8,500; independent audit slices from €8,000. Figures on the home Open proof section inform methodology; delivery stays commercial and fixed-scope.

**Hub · sprints from €2,400 PoC to €8,500 MVP** · Topic: `engineering` · [Open proof](/#open-proof) · [Sample scorecard](/sample)

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


_AI engineering by stack_

## Why teams trust this stack with Arviser

- Stack-specific gates for Engineering stacks for AI delivery, 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

Pick a stack hub link, request scope with your topic slug, and start at €2,400 PoC instead of a six-figure discovery phase. Credits apply toward MVP or audit within 60 days on Go outcomes.

Browse child pages below, then request scope at /#scope with your topic slug so we attach the right eval recipe and sample gates.

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

- Teams pick a trendy stack before defining eval gates, then rewrite the same RAG twice.
- Shared libraries hide provider API differences until a model deprecation breaks three services.
- Cross-stack auth for agents uses long-lived service tokens never rotated after PoC.

### Sample eval fragment (engineering-hub)

```
hub: engineering
children: 38
default_sprint: 40h-prototype
price_ladder: [2400, 3100, 3900, 5600, 8500]
```

## 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 Engineering stacks for AI delivery 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

[Python](/engineering/python) · [TypeScript](/engineering/typescript) · [Go](/engineering/go) · [Rust](/engineering/rust) · [Java/Kotlin](/engineering/java-kotlin) · [C#](/engineering/csharp) · [RAG and agents](/engineering/rag-and-agents) · [Frontend hub](/engineering/frontend) · [Mobile hub](/engineering/mobile) · [Platform/K8s](/engineering/platform)

