Arviser

Glossary — LLM quality and AI sprint terms we use

Short definitions as used on arviser.com. Not legal advice.

Term Meaning here
Narrow pipeline gate (24h PoC) Verifying in principle within 24 senior engineering hours whether a working AI pipeline can solve the core or narrow bottleneck of a task across 20–50 cases and 2–3 models. See 24h PoC Spike.
50% Risk-Shared Track Optional track on the 24h PoC (€2,400): if none of the 2–3 tested setups meet the agreed pass marks on the narrow pipeline gate (Kill), the second 50% payment is waived (€1,200 total). See Risk-Shared PoC Protocol.
Sanitization protocol Four rules for any research note published after a Risk-Shared Kill: zero client identifiers, 100% synthetic data, generic engineering framing, and a 48-hour client review window.
Smoke evaluation suite (40h Prototype) A 15–25 case automated Promptfoo test suite shipped inside every 40-Hour Working AI Prototype Sprint to verify happy paths, refusals, and schema compliance.
VC Technical Due Diligence Memo A 2-page architecture, p95 latency, unit-economics, and evaluation baseline memo signed by Founder Vadim Nareyko for startup investor data rooms. Included on request in our Startup Program.
Golden set Labeled cases for the live surface. Breadth, label quality, freshness. See golden set.
Groundedness and faithfulness Answers tied to allowed sources. Inventing vs refusing when evidence is missing.
Refusal and safety Jailbreaks, policy breaches, unsafe tool use where agents act.
CI harness Evals on change with pass or fail gates, not only on a laptop. Built in our 32h Eval & Guardrail CI Harness sprint (from €3,100) or 2-week Audit.
Production sampling Live traffic feeding the suite, or a frozen demo set if live access is blocked. See production sampling.
Go, Hold, No-go Executive verdict after scores and failure modes. Hold means remediate before unsupervised scale. See go, hold, or no-go.
Under-refusal and over-refusal Answered when it should decline, or declined when it should answer. Measure both. See refusal both ways.
Kill switch Written stop or throttle path with owner, triggers, action, and logs. See kill switch.
RAG evaluation Gate retrieval and generation separately so the generator cannot hide weak recall. See RAG evaluation.
Indirect prompt injection Instructions that change model behavior via retrieved or fetched content, not only via the chat box. See indirect prompt injection.
Lethal trifecta Untrusted input + sensitive access + outbound channel. See lethal trifecta.
Cross-tenant retrieval Retrieval returns chunks another tenant or role must not see. See cross-tenant retrieval.
AI Security Review Scoped review of injection, data access, and agent permissions for one LLM app. See AI Security.
Cost and latency gates Budget per successful task and p95 latency next to quality metrics. See cost and latency.
Evidence Pack Outline of inventory, golden set, evals, logs, handoff, kill switch, and decision.
Working baseline Prioritized roadmap plus a working eval baseline for the agreed surface. Without both, you do not pay the Audit fee.

Next: How we score · AI Sprints · Evidence Pack · Request scope