conon.ai

conon.ai/Tips

Explanatory Style For Month One

Ask for the explanatory output style and the agent narrates why it chose what it chose as it works — the black box becomes a running commentary. When the explanations start to annoy you, that's your graduation signal: switch back to default.

IntermediateTOOLSClaude Code

Why it works

The default output hides most of the agent's reasoning; explanatory style makes it narrate the why behind each choice as it works — a black box becomes a running commentary. For your first month it's free tutoring calibrated exactly to what you're doing. And it has a built-in graduation bell: the day the explanations start to annoy you is the day you've internalized them.

How to do it

  1. Ask in plain words: 'switch the output style to explanatory.'
  2. Start a fresh session or /clear — styles load at session start.
  3. Work normally; read the why-notes as they stream past ('chose a single file so you can host it anywhere').
  4. When a note surprises you, pull the thread: 'why is that the better choice here?'
  5. A month in, when the notes feel like noise: 'switch back to the default style.'
  6. Keep explanatory in your pocket for genuinely new territory even after graduating.

Copy this

prompt
Switch your output style to explanatory: as you work, briefly explain why you make each significant choice. Confirm the style is active, then continue my task.

What to watch for

  • Style changes apply from the next session — asking mid-conversation and seeing nothing change is the expected behavior, not a bug.
  • Explanatory produces longer transcripts; if you're skimming for results only, you're paying the length without collecting the tuition.

Sources

Original: conon.aiDocumentation: code.claude.com

Read next

Make It Review Its Own Diff
'Done' is a claim, not a fact. Before accepting changes say: 'check these changes before I accept — look for real errors, not formatting'. The agent regularly finds its own bugs, and the closing phrase stops it nitpicking commas instead of logic.
Claude Code
Show A Screenshot, Skip Adjectives
Words like 'modern and minimalist' mean nothing — every ugly site's brief said that. Saw a style you like? Screenshot it into the prompt with 'in this spirit'. A picture transfers taste that three paragraphs of adjectives never will.
Claude Code
More Effort, Or A Bigger Model?
Bad result? Diagnose before you rage-quit to another tool. Skipped files, no self-check, quit halfway — that's low effort: raise the effort level. Read everything and still confidently wrong — that's the model's ceiling: escalate the model. This one question settles 95% of 'the AI got dumber' complaints.
Claude Code
Match The Model To The Chore
Limits are shared, so burning the flagship model on renaming files is how you hit the 5-hour wall by lunch. Live on the workhorse model; switch up consciously for architecture, gnarly bugs, and review — or use opus-plan mode: expensive model plans, cheap model executes, switching itself.
Claude Code

We build and operate the systems behind tips like this one — agents, automations and internal tools, shipped into production. See what the studio does →