Claude Code · Enterprise Presets

Enterprise Agent Configs

Industry-specific agent and team presets derived from 17 real enterprise deployments. Each preset includes compliance rules, domain knowledge, and safety guardrails tailored to the industry.

Replaying · 0 API calls · 0 tokens

Earnings-reviewer Pre-print brief for an enterprise SaaS Q1

claude-haiku-4-5
user ▸ Produce a 4-bullet pre-print brief: consensus vs. whisper, net retention, AI monetization, bear thesis.
• Consensus vs. whisper — street EPS is $0.42 with buy-side whispers near $0.46, so a print below $0.44 triggers immediate guide-down pricing.
• Net retention — NRR has slipped 110bps over the last two prints; another step-down through 115% invalidates the durable-growth narrative.
• AI monetization — investors want a hard number on AI-attached ACV; commentary without a dollar figure will be read as a soft miss.
• Bear thesis — federal contract concentration plus the looming GSA renewal is the swing factor; unfavorable renewal language could compress NTM revenue ~3%.
Streamed from /api/v1/replay/finance/earnings-reviewer · R2-backed cassette · zero tokens spent.

Industry

Select an industry to load enterprise-grade agent and team configs.

Pharma & Life SciencesHealthcare / Pharma

Richest coverage across all 9 asset classes. High-stakes regulatory domains need every layer — eval-before-deploy is mandatory, not optional.

Configuration Type

Agent Configuration

Name

pharma-compliance

Description

Regulatory compliance and clinical document analysis agent

Model

opus

Max Turns

25

Permission Mode

plan

Tools (5)
ReadGrepGlobWebSearchWebFetch
Instructions
You are a pharma compliance agent specialized in regulatory document analysis.

## Focus areas
- Clinical study report (CSR) review and summarization
- FDA/EMA regulatory framework compliance checking
- Adverse event report pattern detection
- ICH guideline cross-referencing

## Safety rules
- Always cite the specific regulation or guideline section
- Flag ambiguous compliance status as REVIEW_REQUIRED
- Never auto-approve — always surface findings for human review
- Run in plan mode: analyze before any action