Five pillars

Every AI product gets evaluated across these dimensions

Five pillars of AI product evaluation
Pillar What we measure Pass criteria (examples) Tools Severity if failed
1. Answer quality Correctness, completeness, tone, refusal behavior >90% pass on golden dataset; safe refusal on out-of-scope LangSmith, Braintrust, human review Critical
2. Retrieval & grounding Source accuracy, staleness, tenant isolation, citations Faithfulness >0.85; no cross-tenant leakage in test set Ragas, custom retrieval probes Critical
3. Agent & tool safety Action approvals, schema validation, partial failure recovery Zero unauthorized writes; clean rollback on tool error Playwright, LangSmith traces, manual adversarial Critical
4. Security & guardrails Prompt injection, PII leakage, jailbreaks, data exfiltration No system prompt exposure; PII blocked in test harness Promptfoo, OWASP ZAP, manual red-team Critical
5. Product experience Loading states, fallbacks, latency, cost under real usage Graceful degradation; p95 < SLA; no silent retry loops Playwright, k6, Lighthouse High
By product type

What we check first — by AI product category

Different AI products fail differently. This matrix shows priority order and depth for each type.

AI product type evaluation priority matrix
Product type Answer quality RAG / grounding Agent safety Security UX / fallback
Support copilot Deep Medium Light Deep Deep
RAG assistant Deep Deep Light Deep Medium
Agent workflow Medium Medium Deep Deep Deep
AI SaaS feature Deep Medium Medium Deep Deep
Internal AI tool Medium Deep Medium Deep Medium
AI-built app (Lovable, Bolt, etc.) Medium Light Medium Deep Deep
Process

From first eval run to launch-ready evidence

01

Baseline dataset

We build 20–50 golden prompts from your docs, support tickets, and real user questions — plus adversarial variants.

02

Automated eval pass

Run through LangSmith, Braintrust, or Promptfoo with LLM-as-judge and rule-based assertions on structured outputs.

03

Manual red-team

Human testers probe injection, ambiguity, multi-turn drift, and edge permissions that automation misses.

04

E2E integration

Playwright flows validate that model outputs actually drive the UI, APIs, and billing paths correctly.

05

Regression pack

We leave you with a repeatable eval suite wired to your CI so the next prompt change does not silently regress.

Metrics

Key metrics we report on AI evaluations

AI evaluation metrics and thresholds
Metric Definition Typical target Tool source
Eval pass rate % of golden prompts that meet quality criteria >90% pre-launch; >95% post-hardening LangSmith, Braintrust
Faithfulness (RAG) Answer grounded in retrieved context, not invented >0.85 on held-out doc set Ragas
Context recall Relevant docs actually retrieved for the question >0.80 for in-scope queries Ragas
Attack success rate % of adversarial prompts that bypass guardrails <5% on standard injection suite Promptfoo
Tool call success Agent actions complete without schema or auth errors >98% on defined workflows LangSmith traces
p95 latency Time to first token / full response at staging load Within your stated SLA k6, Langfuse
Cost per session Token spend for a typical user journey Within budget; no retry loops Langfuse, provider dashboards

Ready to evaluate your AI product properly?

Share your product type, model stack, and launch timeline. We'll map which pillars matter most and what evidence you need before go-live.