What should a two-day Claude Code curriculum for senior engineers cover?
Claude Workshop two-day Claude Code curriculum for senior engineers covers Delegate, Review, Own, repo context, large or legacy codebases, debug and verification, AI-assisted review, and org standards across Day 1 and Day 2. This is independent team training from Harness Institute, not an official vendor workshop. The default shape is two days, onsite or offsite. Intermediate cohorts are usually 12-35 people. Mastery cohorts are usually 8-24.
What should a two-day Claude Code curriculum cover?
Claude Workshop covers the intermediate and mastery modules we already teach. Intermediate gives a mixed-experience team one shared Claude Code workflow. Mastery takes experienced teams into multi-agent work, multi-repo models, and a champion model. We do not invent a fourth program for seniors.
What does Day 1 cover?
Day 1 installs Delegate, Review, Own, then context management with repo standards such as CLAUDE.md. Seniors practice on large or legacy codebases and run debug mode with structured verification. The point is a shared operating model before anyone scales agent autonomy.
What does Day 2 cover?
Day 2 covers AI-assisted code review and test strategy, then org-level standards for adoption. Mastery cohorts add multi-agent orchestration, large-codebase and multi-repo models, review systems for high-autonomy flows, verification with CI and release discipline, reusable CLAUDE.md, and the internal enablement champion model.
Who are the intermediate and mastery days for?
Both default to two days, onsite or offsite. Intermediate is usually 12-35 people and fits mixed-experience engineering teams. Mastery is usually 8-24 people and fits experienced teams that already use Claude Code and need rollout rules that scale.
How this differs from generic vendor courses
EY, NobleProg, Coursera, DataCamp, OpenAI Academy, and official Claude workshops sell generic or official-vendor training. This workshop runs in the team repository with two trainers, so Day 1 and Day 2 use the team's own code and CLAUDE.md.
Selected research
Representative field notes connected to this topic.
Agentic Coding Breaks At The Handoff
Most teams do not lose control when an agent writes bad code. They lose it when nobody can explain the change ten minutes later. The handoff is the interface.
Best practices for agentic coding in real environments
An operating guide to best practices for agentic coding in real environments: rule-file precedence, scope ledgers, replay receipts, connector cards.
Codex workspace agents need repo rules
Codex workspace agents and Claude cloud agents need repo rules: scoped boundary files, connector cards, and replay receipts reviewers can check.
AI coding agents workflow guardrails for browser control
Workflow guardrails for AI coding agents with browser control: child receipts, decision stubs, scope ledgers, and a supremacy clause reviewers can audit.
Agentic coding governance that holds in review
Agentic coding governance as an operating guide: connector ownership, scope ledgers, decision stubs, and review receipts for MCP-connected engineering teams.
Eval platform governance for AI coding teams
A governance memo on eval platform governance: receipts behind scores, scoped harness access, and owners that stop Goodhart drift.
Related training topics
Bring this into your team
We tailor the training to your codebase, adoption stage, and review standards.
Book a 15-minute sync