July 2026

The Chatbot I Actually Want to Build

Experimental

One-Size Fits No One

This isn't about building a smarter support bot. It's about what happens when you treat a chatbot as a design research instrument — and discover the real work was never in the interface.

When I first started this project, I was — and still am — convinced that chatbots are almost always a generic experience. Real life taught me to resent using them. They feel like a last resort, a wall between you and an actual person, clouding whatever value they might otherwise offer. So when I decided to build one, I wanted to understand the mechanics underneath — what it actually takes to make a tailored experience wherever the user decides to engage.
Could I shape the conversation in accordance with how the user intended it to go? Was it smart enough to ask questions and remember what was said? How intrusive would it feel? Was it actually helpful at the moment it appeared?
These were the questions I brought into the build. What I found was that the biggest influence on the experience had almost nothing to do with the interface — it came from managing a living document of principles, tone, and cadence that together shaped something that felt personal, even if it was artificial in nature.

The placement of a tool is a design decision as much as the tool itself. Showing up at the wrong moment erodes trust faster than not showing up at all.

Visibility restraint builds more trust than availability. The chatbot was removed from the homepage entirely — placed only where a visitor is already showing intent.

Prompt Engineering Is Living Document

Token usage entered the conversation early, and it shaped the decision-making process more than expected. Every feature had to earn its place. Free models have real limitations — and those limitations were worth testing before committing to anything more advanced or costly.

Sycophancy Is The Default

Several rounds of prompt updates focused specifically on counteracting those tendencies: introducing uncertainty language, pushing back through curiosity rather than compliance, being precise about tone and cadence. Being explicit helps, but it comes with tradeoffs. Every added instruction is more tokens, and more tokens means more cost and more surface area for the model to break mid-conversation.

Restraint Builds More Trust

The chatbot sits on the experimental Lab page, the portfolio index, and all individual project pages. A seven-second scroll nudge appears near the footer — close to the contact information — once per session. These were deliberate decisions rooted in the same thinking that shapes any good experience: respect for the visitor's attention is not optional.

Context Is The Conversation

Passing the current page URL to the backend so the chatbot knows where the visitor is turned out to be a small technical addition with outsized impact. A visitor on a project page is likely evaluating specific work. A visitor on the Lab page is likely curious about the experiment itself. That context — available before a single message is typed — allows the experience to feel tailored from the first interaction, not just after several exchanges.

What started as a few lines of instruction evolved into a structured document — changed only when necessary, refined through real conversations, and updated deliberately on the backend where the actual behavior lives.
The real leverage wasn't in the UI. Every meaningful behavior change — the personality, the memory, the project knowledge, the way it shifted tone depending on who it was talking to — came from how the instructions were written, not from anything visible on screen. My skepticism toward a format I actively disliked became one of the more honest design experiments on my website. The chatbot works because every decision about what it says, where it appears, and how it behaves was made with the same intentionality that should go into any experience meant to serve a person rather than just occupy their screen.
This project has been an interesting addition to the site, and it will need more time and real user data to fully assess its value. The next considerations include testing more stable models and building toward the early stages of a lead capture and client pipeline — a system that works in tandem with the chatbot to turn meaningful conversations into something actionable.