# RAG grounding failure playbook

RAG grounding failures send stale snippets into support macros, cite footnotes mobile users cannot open, or pass checks when section numbers are wrong. Playbook encodes citation-to-source page parity. €2,400 PoC; €3,100 Eval CI; €3,900 prototype fix; €5,600 hardening; €8,500 MVP; audit from €8,000. Written scope arrives within 48 hours with numeric pass marks on accuracy, groundedness, p95 latency, and cost per thousand runs; deliverables include Dockerized repos, handoff notes, and Promptfoo or DeepEval fixtures your team can extend. Deliverables include Dockerized repos and Promptfoo or DeepEval fixtures wired to your CI provider.

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

HTML: [/use-cases/rag-grounding](/use-cases/rag-grounding) · Markdown: [/use-cases/rag-grounding.md](/use-cases/rag-grounding.md)


_Grounding failure use case_

## Why teams trust this stack with Arviser

- Stack-specific gates for RAG grounding failure playbook, 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: golden-set workshop add-on, 32h harness (€3,100) encoding this failure mode, then hardening (€5,600) or prototype (€3,900) depending on existing UI.

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

- Support macro expands stale retrieval snippets into customer emails.
- Answer cites changelog footnote users cannot open from mobile app.
- Grounding check passes when citation is wrong section number.

### Sample eval fragment (uc-rag)

```
citation_must_match: source_page
```

## 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 RAG grounding failure playbook 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

[Use cases hub](/use-cases) · [Open proof](/#open-proof)

