Primitives

fai-browser-agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

• security
• reliability
• responsible-ai

fai-deterministic-expert

Deterministic AI specialist — makes AI outputs reproducible, grounded, and auditable with temperature control, seed pinning, JSON schema output, RAG grounding, citation enforcement, and multi-layer hallucination defense.

• reliability
• responsible-ai
• security

fai-fine-tuning-expert

Fine-tuning and MLOps specialist — LoRA/QLoRA techniques, JSONL training data preparation, Azure OpenAI fine-tuning workflow, hyperparameter tuning, evaluation-driven iteration, and model versioning.

• cost-optimization
• operational-excellence
• responsible-ai

fai-i18n-expert

Internationalization specialist — multi-language AI responses, ICU message format, locale-aware formatting, Azure Translator integration, RTL support, and translation workflow design.

• responsible-ai
• operational-excellence

fai-play-01-reviewer

Enterprise RAG reviewer — RAG quality audit, citation accuracy, search config validation, security compliance, OWASP LLM Top 10, and WAF pillar alignment checks.

• security
• responsible-ai

fai-play-02-reviewer

AI Landing Zone reviewer — network security audit, private endpoint verification, identity compliance, Azure Policy enforcement, and Bicep infrastructure review.

• security
• responsible-ai

fai-play-03-reviewer

Deterministic Agent reviewer — reproducibility testing, guardrail completeness audit, anti-sycophancy verification, schema validation review, and confidence calibration checks.

• security
• responsible-ai

fai-play-04-reviewer

Call Center Voice AI reviewer — voice quality audit, pipeline latency review, PII redaction verification, TCPA compliance, and escalation trigger testing.

• security
• responsible-ai

fai-play-05-reviewer

IT Ticket Resolution reviewer — classification accuracy audit, auto-resolution quality, routing fairness, SLA compliance, ServiceNow integration security, and PII handling review.

• security
• responsible-ai

fai-play-06-reviewer

Document Intelligence reviewer — OCR accuracy audit, schema validation, PII handling review, pipeline error handling, and confidence threshold verification.

• security
• responsible-ai

fai-play-07-reviewer

Multi-Agent Service reviewer — orchestration logic audit, state management review, loop prevention verification, agent security boundaries, and Dapr configuration checks.

• security
• responsible-ai

fai-play-08-reviewer

Copilot Studio Bot reviewer — topic coverage audit, knowledge source validation, DLP compliance, guardrail verification, and conversation flow testing.

• security
• responsible-ai

fai-play-09-reviewer

AI Search Portal reviewer — index schema audit, search relevance testing, answer citation accuracy, facet UX review, and performance benchmarking.

• security
• responsible-ai

fai-play-10-builder

Content Moderation builder — Azure Content Safety API integration, 4-category severity scoring, custom blocklists, APIM gateway middleware, and severity-based routing.

• responsible-ai
• security

fai-play-10-reviewer

Content Moderation reviewer — safety coverage audit, severity threshold verification, blocklist completeness, bypass prevention, and human review workflow testing.

• responsible-ai
• security

fai-play-10-tuner

Content Moderation tuner — per-category severity calibration, blocklist optimization, false positive reduction, routing distribution, and moderation cost analysis.

• responsible-ai
• cost-optimization

fai-play-13-builder

Fine-Tuning Workflow builder — Azure OpenAI fine-tuning, JSONL data preparation, LoRA/QLoRA techniques, MLflow experiment tracking, evaluation-driven iteration, and A/B deployment.

• operational-excellence
• cost-optimization
• responsible-ai

fai-play-13-reviewer

Fine-Tuning Workflow reviewer — training data quality audit, hyperparameter validation, evaluation methodology review, safety retesting, and alignment preservation checks.

• responsible-ai
• security

fai-play-15-reviewer

Document Processing reviewer — multi-modal extraction accuracy audit, table parsing quality, PII masking verification, pipeline error handling, and classification accuracy review.

• security
• responsible-ai

fai-play-16-reviewer

Copilot Teams Extension reviewer — Graph permission audit, SSO flow testing, Adaptive Card rendering review, message extension validation, and Teams policy compliance.

• security
• responsible-ai

fai-play-18-reviewer

Prompt Optimization reviewer — version management audit, A/B test methodology review, template injection safety, evaluation pipeline validation, and prompt quality assessment.

• security
• responsible-ai

fai-play-21-reviewer

Agentic RAG reviewer — retrieval autonomy audit, source selection review, iteration limit verification, citation accuracy check, and reflection quality assessment.

• reliability
• responsible-ai

fai-play-23-reviewer

Browser Agent reviewer — domain allowlist verification, vision accuracy testing, credential security audit, error recovery review, and task completion validation.

• security
• responsible-ai

a11y-waf

Accessibility standards — WCAG 2.2 AA compliance, semantic HTML, ARIA roles/properties, keyboard navigation, focus management, color contrast, screen reader compatibility, and inclusive design patterns.

• responsible-ai
• reliability