Claude & Claude Code workflows Start by understanding the project, then make changes with a clear way to check the result. Reviewed 15 November 2026 · Utilising AI Pty Ltd https://www.utilisingai.com/learn/claude-code-workflows Claude chat and Claude Code are different working environments. The code tips require Claude Code with access to your project. We reviewed the linked talk’s auto-generated transcript and cross-checked product details against current Anthropic docs. Independent educational guide. Original examples; documentation-based guidance. Product availability varies. No provider integration or AI request is run by this download. Quick start =========== 1. Open a backed-up project and ask one question about how it works, without requesting edits. 2. Choose one small change. Explain the symptom and what success would look like. 3. Provide the project’s real test command or a visual reference, then inspect the result and changes. Practical tips ============== Set success criteria before polishing a prompt For writing or analysis in Claude chat, decide what a good answer must contain and how you will assess it. If the output misses the mark, change one instruction or example and compare the result. Prompt wording is not a substitute for a usable evaluation. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview Supply what the repository cannot reveal Name the user-visible symptom, the preferred behavior and constraints such as “keep the current database structure.” Claude Code can inspect code patterns, but it cannot infer an unpublished business decision. Add the missing decision rather than a large generic instruction manual. https://code.claude.com/docs/en/best-practices Make verification concrete Give the agent a relevant test, build command or screenshot comparison. Ask for the observed result, not an assurance that things “should work.” A successful build checks one part of the system; it does not prove account access or a payment flow works. https://code.claude.com/docs/en/best-practices Boris Cherny’s practical talk: lessons worth using ================================================== Timestamped paraphrases from the linked recording, uploaded by Solomon Alfred. Auto-captions sometimes misname Claude; we use the correct product name. These are historical workflow lessons, not a current feature or privacy guarantee. 4:00 · Start with questions: Learn the codebase before asking for edits. https://www.youtube.com/watch?v=M8HuXu_bOco&t=240s 5:49 · Ask about history: Use Git history to understand a surprising design decision. https://www.youtube.com/watch?v=M8HuXu_bOco&t=349s 8:22 · Plan larger changes: Agree on an approach before a substantial implementation. https://www.youtube.com/watch?v=M8HuXu_bOco&t=502s 11:02 · Close the feedback loop: Provide tests or screenshots the agent can check. https://www.youtube.com/watch?v=M8HuXu_bOco&t=662s 12:22 · Keep shared context concise: Store useful project commands and conventions in CLAUDE.md. https://www.youtube.com/watch?v=M8HuXu_bOco&t=742s 22:23 · Isolate parallel work: Separate checkouts or worktrees avoid overlapping edits. https://www.youtube.com/watch?v=M8HuXu_bOco&t=1343s 25:02 · Use visual references: Give the agent a mockup instead of describing every pixel. https://www.youtube.com/watch?v=M8HuXu_bOco&t=1502s Developer notes =============== Keep CLAUDE.md focused Record the project-specific commands and gotchas that save repeated rediscovery. Keep long procedures separate. Natural-language instructions guide the model; hard access boundaries require permissions, sandbox controls or enforced checks. https://code.claude.com/docs/en/memory Use today’s shortcuts The current terminal reference lists Ctrl+R for searching prompt history and Ctrl+O for the detailed transcript. The linked talk describes an older Ctrl+R behavior. Use the current reference for your terminal and version rather than memorising every shortcut from a recording. https://code.claude.com/docs/en/interactive-mode Give feedback without starting over Use a focused follow-up to preserve the good parts and correct the failing part. For a design task, provide the actual screenshot and ask for a comparison after the change. This is our recommended review pattern, not a guarantee that an agent will catch every defect. https://code.claude.com/docs/en/common-workflows Original examples to adapt ========================== First conversation with an unfamiliar codebase I am new to this project. Explain how [feature] works, where the main logic lives, and which tests cover it. Point to files and explain unfamiliar terms. Read-only for now; do not change files. Original example inspired by the talk’s codebase Q&A approach. https://www.youtube.com/watch?v=M8HuXu_bOco Plan a meaningful change I want [specific behavior]. Current behavior: [example]. Constraints: [requirements]. Explore the relevant code and propose an approach with affected files, trade-offs and checks. Stop after the plan so I can review it. Use the plan step when choices or scope need agreement. Tiny fixes may not need it. https://code.claude.com/docs/en/common-workflows Project instructions starter (CLAUDE.md) # Project notes - Product behavior to preserve: [describe]. - Run one relevant test: [actual command]. - Typecheck/build: [actual commands]. - Project gotcha: [one important exception]. - Definition of done: [observable acceptance criteria]. A template to adapt, not a runnable command. Confirm all commands exist. Instruction files are not security enforcement. https://code.claude.com/docs/en/memory Check the result ================ - Is the correct project open and its starting state backed up? - Can you see test output or a before/after screenshot? - Have you reviewed the diff and any changed dependency or permission? Common mistakes =============== - Copying old installation or shortcut advice without checking current docs. - Treating the talk’s historical privacy statements as today’s data-handling policy. - Granting broad command or connector access just to avoid prompts. Sources ======= Boris Cherny talk · Practical Claude Code tips · Talk · user-supplied video, uploaded by Solomon Alfred https://www.youtube.com/watch?v=M8HuXu_bOco Anthropic · Claude Code best practices · Official documentation https://code.claude.com/docs/en/best-practices Anthropic · Claude Code interactive reference · Official documentation https://code.claude.com/docs/en/interactive-mode Anthropic · Prompt engineering overview · Official documentation https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview Anthropic · Project memory and instructions · Official documentation https://code.claude.com/docs/en/memory Anthropic · Common coding workflows · Official documentation https://code.claude.com/docs/en/common-workflows