Calibrate AI Agents to Your Personal Work Preferences

4 comments

Apps it uses

Most AI agents are built around general best practices. That’s useful, but it doesn’t mean they work the way I want them to.

I’ve started using a simple calibration process to tailor my agents to my preferences. Instead of telling an agent what to do on each task, I have it interview me about how I like work done in its specific domain. A writing agent asks different questions than a research agent, and a strategy agent asks different questions than a coding agent.

The goal is to make my working preferences part of how the agent operates.

Step-by-step

  1. I pick an agent I use regularly, such as one for writing, research, strategy, coding, analysis, or career advice—especially where my personal preferences matter.
  2. I ask the agent to interview me about how I prefer work to be done in its domain. A writing agent might ask about tone, structure, editing style, and how much pushback I want. A research agent might ask about source quality, depth, recency, citations, and how much synthesis I prefer.
  3. I have the agent summarize what it learned and separate durable preferences from temporary or situation-specific ones.
  4. I review the proposed changes and ask the agent to show me exactly how it wants to update its instructions or skills. I correct anything it misunderstood and explicitly approve the changes before anything is modified.
  5. Once I approve the changes, I have the agent apply them to its instructions or skills so those preferences become part of how it works going forward.
  6. I use the agent normally and pay attention to where it feels more aligned and where it still misses the mark.
  7. When I notice recurring friction, I add or adjust the relevant preference instead of repeatedly correcting the same behavior task by task.
  8. I repeat the interview periodically. My preferences, tools, and workflows change, so the agent should be able to ask which preferences are still valid, which ones I keep overriding, what has been annoying me, and what should be added or removed.

The result is an agent that doesn’t just know how to do the job; it knows how I want the job done. Because every change is proposed and approved before it becomes permanent, the personalization stays intentional rather than turning into a collection of guesses about me.

4 comments

Have a question about this workflow, or a way to improve it?

Log in to comment Create a free account
Alper Tayfur

Separating durable preferences from temporary ones is the part that makes this feel sustainable. Otherwise personalization can slowly turn into a pile of outdated rules. Do you track which preferences the agent keeps getting corrected on as a signal that it’s time for another calibration?

Guillermo Gómez

The interview reaches the part someone can articulate about how they work. Where it tends to leak is that stated preferences and applied ones come apart. I've told editors "make it drier" more times than I can count and it has never once meant anything, while cutting the first four seconds off one specific shot and explaining why that one taught it in an afternoon. Step 7 gets at this from the other end, adjusting when friction recurs, but the interview itself still happens in the abstract. Have you tried running it with a real deliverable open, and does it produce a different list?

Posting guidelines