Patterns of Agent Interaction — loveyourclanker.org

Skip to content

Learn to love coding agents<br>Start with the patterns

There is more than one way to work with AI agents<br>How you interact with these amazing new tools is up to you. We have collated some of the patterns of interaction that we have seen and that we use. We hope they are helpful. Please contribute if you have a different way.

The patterns<br>Tab Completion<br>In the early days of AI coding, this was it and it is where the agentic engineering journey started for many. Tends to be not used much as there are newer patterns that give a better combination of efficiency with control and safety.<br>Speed<br>Control<br>Quality<br>Safety<br>Skill retention<br>Token thrift

Read the pattern Full Vibing with Agent<br>If you don't understand code at all or for whatever reason, you don't want to put hands on code for this project, you can use your coding agent to do everything and just not touch the code at all.<br>Speed<br>Control<br>Quality<br>Safety<br>Skill retention<br>Token thrift

Read the pattern Full Vibing in a Walled Garden<br>If you don't understand code at all or for whatever reason, you don't want to put hands on code for this project, you can use helpful tools to do everything for you and hide the code and the agent from you. You just prompt and eventually you can get a system.<br>Speed<br>Control<br>Quality<br>Safety<br>Skill retention<br>Token thrift

Read the pattern Plan, Execute, Check<br>A robust and professional approach. Good balance of speed and control. The current meta.<br>Speed<br>Control<br>Quality<br>Safety<br>Skill retention<br>Token thrift

Read the pattern I Code, You Check<br>A High touch, high skill, professional approach for the most critical code. Complete control. You get to do the interesting bits. Not very fast.<br>Speed<br>Control<br>Quality<br>Safety<br>Skill retention<br>Token thrift

Read the pattern More patterns to come<br>The rubric is fixed and the pages are generated, so a new pattern is a new markdown file — same card, same ratings, same page shape.

Side by side<br>The same judgements for every pattern, in the pattern's own terms. Brainrot and token use read the other way round from the rest — low is better.<br>PatternSpeedControlQualitySafetyBrainrotToken useTab CompletionLowHighHighHighLowLowFull Vibing with AgentHighLowLowLow to MediumHighHighestFull Vibing in a Walled GardenHighestLowestLow to MediumLow to MediumHighestHighPlan, Execute, CheckMedium to HighMedium to HighMedium to HighHighMediumMedium to HighI Code, You CheckMediumHighestHighestHighestNegativeMedium

The six axes<br>Further out is better. Every rating below is a word written in the pattern's own markdown file, not a number typed into a spreadsheet.<br>Speed<br>How many features can you deliver in a set time.

Control<br>What is your agency as the Engineer. How enabled are you to shape the codebase, the architecture, the approach.

Quality<br>Software Quality is somewhat vexed. Let's just go with whatever the opposite of 'AI Slop' is. Unslop?

Safety<br>Software with low safety will expose your credentials, make your infrastructure easy to hack and leak the identities of your users. Safety good.

Brainrot<br>How much of your mental agility and capability is being lost because you are handing off all the thinking to our friends. Brainrot bad, Skill Retention good.

Token use<br>How many tokens are you going to use to get to a specific working feature.

Palette