Tag: agentic-coding
-
Claude Code: Writing a CLAUDE.md that captures tacit team knowledge
A field-tested take on writing a CLAUDE.md that captures tacit team knowledge with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Difference between an agent and a slow script
A field-tested take on the difference between an agent and a slow script with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Using sub-agents for parallel research across a large codebase
A field-tested take on using sub-agents for parallel research across a large codebase with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Budgets as the only feature that stops a bad loop
A field-tested take on budgets as the only feature that stops a bad loop with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Planning mode as a cheap insurance policy against cascading edits
A field-tested take on planning mode as a cheap insurance policy against cascading edits with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Building trust with agents the way you build it with juniors
A field-tested take on building trust with agents the way you build it with juniors with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Running Claude Code headlessly in CI as a structured reviewer
A field-tested take on running Claude Code headlessly in CI as a structured reviewer with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Why short agent loops beat heroic ones
A field-tested take on why short agent loops beat heroic ones with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Claude Code: Composing slash commands into a bespoke team-specific DSL
A field-tested take on composing slash commands into a bespoke team-specific DSL with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Agentic coding: Rollback plans for changes you did not watch land
A field-tested take on rollback plans for changes you did not watch land with Agentic coding: what it rewards, where it breaks, and how to keep the workflow honest.
-
Diffing agent output against main before you trust a single file
Claude Code can touch a dozen files in one run and you'll only ever see what it decides to show you in the transcript. A clean working tree before you start is what turns 'trust the summary' into 'read the actual diff.'
-
The honest case for agents that only suggest
Suggest-only agents lost the marketing war years ago. The argument for them isn't caution, it's that the review step is where the value actually lands, and autonomy is what removes it.
More posts tagged agentic-coding
- Claude Code: Quiet art of pausing the agent instead of letting it churn
- Agentic coding: How to review a PR an agent opened in the middle of the night
- Claude Code: Keeping Claude honest with explicit acceptance criteria, not vibes
- Agentic coding: Guardrails before autonomy, always
- Claude Code: Hooks that enforce lint, test and security gates before any write
- Agentic coding: Planning outputs as the real product of the first turn
- Claude Code: Checkpointing long sessions to protect yourself from context rot
- Agentic coding: What to log when an agent writes for you
- Claude Code: Writing a CLAUDE.md that captures tacit team knowledge
- Agentic coding: Difference between an agent and a slow script
- Claude Code: Using sub-agents for parallel research across a large codebase
- Agentic coding: Budgets as the only feature that stops a bad loop
- Claude Code: Planning mode as a cheap insurance policy against cascading edits
- Agentic coding: Building trust with agents the way you build it with juniors
- Claude Code: Running Claude Code headlessly in CI as a structured reviewer
- Agentic coding: Why short agent loops beat heroic ones
- Claude Code: Composing slash commands into a bespoke team-specific DSL
- Agentic coding: Rollback plans for changes you did not watch land
- Claude Code: Diffing agent output against main before you trust a single file
- Agentic coding: Honest case for agents that only suggest
- Claude Code: Quiet art of pausing the agent instead of letting it churn
- Agentic coding: How to review a PR an agent opened in the middle of the night
- Claude Code: Keeping Claude honest with explicit acceptance criteria, not vibes
- Agentic coding: Guardrails before autonomy, always
- Claude Code: Hooks that enforce lint, test and security gates before any write
- Agentic coding: Planning outputs as the real product of the first turn
- Claude Code: Checkpointing long sessions to protect yourself from context rot
- Agentic coding: What to log when an agent writes for you
- Claude Code: Writing a CLAUDE.md that captures tacit team knowledge
- Agentic coding: Difference between an agent and a slow script
- Claude Code: Using sub-agents for parallel research across a large codebase
- Agentic coding: Budgets as the only feature that stops a bad loop
- Claude Code: Planning mode as a cheap insurance policy against cascading edits
- Agentic coding: What agentic coding taught us about how we really work
- Claude Code: First pass at measuring Claude Code against ordinary coding
- Agentic coding: Retrospective after our first week of full agentic coding
- Claude Code: Learning to pause the agent on purpose
- Agentic coding: Deliberate agent downtime as an early productivity discovery
- Claude Code: Moment Claude Code beat a human reviewer on taste
- Agentic coding: First PR an agent opened that we merged without edits
- Claude Code: Slash commands as the first real team workflow
- Agentic coding: Cost-per-merged-change metric we invented out of necessity
- Claude Code: When headless Claude Code became part of our CI
- Agentic coding: Long-running agent that finally paused itself
- Claude Code: Turning a chaotic commit history into a tidy narrative
- Agentic coding: How a junior engineer earned their first autonomous task
- Claude Code: First time Claude Code said no to a bad instruction
- Agentic coding: Case for suggest-only agents in safety-critical code
- Claude Code: Running Claude Code on a legacy repo nobody wanted to touch
- Agentic coding: Short loops as the winning rhythm, discovered through long ones
- Claude Code: Hooks as a cheap gateway drug to workflow automation
- Agentic coding: First rollback plan we actually used
- Claude Code: Cost spike that taught us to checkpoint
- Agentic coding: Guardrails before autonomy, learned the expensive way
- Claude Code: Sub-agents the first time they saved an afternoon
- Agentic coding: Planning outputs as the real product of the initial turn
- Claude Code: Planning mode as the training wheels we kept
- Agentic coding: Budgets as the first feature any agent had to have
- Claude Code: Writing your first CLAUDE.md and learning what to leave out
- Agentic coding: First overnight agent run we dared to approve
- Claude Code: First week of Claude Code at the terminal
- Agentic coding: What agentic coding taught us about how we really work
- Claude Code: First pass at measuring Claude Code against ordinary coding
- Agentic coding: Retrospective after our first week of full agentic coding
- Claude Code: Learning to pause the agent on purpose
- Agentic coding: Deliberate agent downtime as an early productivity discovery
- Claude Code: Moment Claude Code beat a human reviewer on taste
- Agentic coding: First PR an agent opened that we merged without edits
- Claude Code: Slash commands as the first real team workflow
- Agentic coding: Cost-per-merged-change metric we invented out of necessity
- Claude Code: When headless Claude Code became part of our CI
- Agentic coding: Long-running agent that finally paused itself
- Claude Code: Turning a chaotic commit history into a tidy narrative
- Agentic coding: How a junior engineer earned their first autonomous task
- Claude Code: First time Claude Code said no to a bad instruction
- Agentic coding: Case for suggest-only agents in safety-critical code
- Claude Code: Running Claude Code on a legacy repo nobody wanted to touch
- Agentic coding: Short loops as the winning rhythm, discovered through long ones
- Claude Code: Hooks as a cheap gateway drug to workflow automation
- Agentic coding: First rollback plan we actually used
- Claude Code: Cost spike that taught us to checkpoint
- Agentic coding: Guardrails before autonomy, learned the expensive way
- Claude Code: Sub-agents the first time they saved an afternoon
- Agentic coding: Planning outputs as the real product of the initial turn
- Claude Code: Planning mode as the training wheels we kept
- Agentic coding: Budgets as the first feature any agent had to have
- Claude Code: Writing your first CLAUDE.md and learning what to leave out
- Agentic coding: First overnight agent run we dared to approve
- Claude Code: First week of Claude Code at the terminal