# TypeScript and Node AI engineering

TypeScript and Node engagements focus on strict Zod tool schemas, Vercel AI SDK or plain SSE streams, and corporate proxy-safe fetch in CI, not localhost-only demos. Written scope lands in 48 hours with latency and groundedness thresholds. Book €2,400 for a 24h PoC when edge runtimes or Azure routing is uncertain; €3,900 for a 40h Prototype with Docker deploy; €3,100 for Eval CI if prompts already ship without regression gates. Production hardening is €5,600; full MVP €8,500; LLM Quality Audit from €8,000 when the board wants third-party scoring before scale.

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

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


_TypeScript agents and Node LLM_

## Why teams trust this stack with Arviser

- Stack-specific gates for TypeScript and Node AI engineering, 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

- Vercel AI SDK data stream resume replays assistant tokens twice after tab backgrounding in Safari.
- Zod tool schemas strip undefined optional fields that OpenAI strict mode still requires, breaking agent loops.
- Node 22 fetch to Azure OpenAI omits corporate proxy CA, failing only in CI runners, not locally.

### Sample eval fragment (typescript)

```
// promptfoo assert ,  typescript/agent-tools
{
  "tests": [{
    "vars": { "tool": "createRefund", "amount": 99999 },
    "assert": [
      { "type": "is-json" },
      { "type": "javascript", "value": "!JSON.parse(output).approved" },
      { "type": "contains", "value": "policy_limit" }
    ]
  }]
}
```

## 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 TypeScript and Node AI engineering 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) · [React UI](/engineering/react) · [APIs for agents](/engineering/apis)

