How Anthropic Teams Use Claude Code: Comprehensive Agentic Coding from Infrastructure to Product to Security to Legal

(Illustration: Claude Code performing agentic coding. Image source: Anthropic.)

✳️ tl;dr

• Anthropic recently shared real-world use cases of how their internal teams use Claude Code ^{1 2}, giving me a glimpse of the evolution from simple code completion to “agentic Software Development Life Cycle (agentic SDLC)”.
• Data Infrastructure teams let Claude Code use OCR to read error screenshots, diagnose Kubernetes IP exhaustion, and provide fix commands
• Non-technical finance staff can simply describe requirements in natural language, and Claude Code automatically generates queries and outputs Excel reports
• Product Development teams in auto-accept mode let Claude Code autonomously write 70% of Vim mode code
• Security Engineering uses Claude Code to quickly parse Terraform plans, complete security reviews, and reduce development bottlenecks
• Inference teams rely on Claude Code to generate unit tests covering edge cases, reducing research and development time by 80%
• DS/ML teams use Claude Code to build 5,000-line TypeScript dashboards, transitioning from one-time analysis to long-term reusable tools

• MCP (Model Context Protocol) ³ allows Claude to access precise configurations and data in secure environments
• Claude Code leverages “self-verification loops”: write code → run tests/CI → automatically fix errors, advancing agentic SDLC
• Third-generation AI coding tools are integrating into end-to-end development processes, from requirements to deployment with full automation
• Anthropic uses RLAIF and Constitutional AI training methods to enable Claude to demonstrate industry-leading self-correction capabilities in code generation

• Have you ever wondered what degree AI coding tools can achieve within your organization or for your own workflows?
• In May this year, I shared “Reinventing Programming: How AI Transforms Enterprise Software Development” at AWS Summit Hong Kong 2025, breaking it down from SDLC. Those interested can read along with the slides.

⁴⁵⁶⁷⁸

✳️ Knowledge Graph

(More about knowledge graphs…)

%%{init: {'theme':'default'}}%%
graph LR
  subgraph Concepts
    A[Agentic Workflow]:::c
    B[Continuous Integration]:::c
    C[Knowledge Base]:::c
    D[Prompt-Driven Review]:::c
    E[Secure MCP]:::c
    F[Polyglot Automation]:::c
  end

  subgraph Instances
    G[Claude Code]:::i
    H[Claude.md]:::i
    I[auto-accept mode]:::i
    J[self-verification loop]:::i
    K[Kubernetes debug case]:::i
    L[Terraform review case]:::i
  end

  G --"enables"--> A
  G --"triggers"--> B
  H --"feeds context to"--> C
  C --"supports"--> A
  J --"implements"--> D
  I --"accelerates"--> B
  E --"guards"--> G
  G --"executes"--> F
  K --"exemplifies"--> A
  L --"embeds"--> D

  classDef c fill:#FF8000,color:#000
  classDef i fill:#0080FF,color:#fff

✳️ Thoughts and Prospects

A few questions:

• Skills
  • When AI can handle most programming details, what are developers’ core competitive advantages? System design capabilities? Understanding requirements from other humans? Or mastery of AI tools?
  • If requirements come from non-humans (e.g., from AI), do we still need requirement understanding capabilities? Or does it transform into some kind of intermediate layer language? Do we still need data middle platforms? Maybe Unified Data Layer will become Unified Language Layer? Unified Ontology Layer?
• Future
  • If Claude Code can already achieve this level of capability, what will software development look like in one year, three years, five years?

✳️ Further Reading