Why crisis detection must bypass the LLM entirely, how adversarial testing exposed the cost of false positives, and building an AI personality framework where tone is risk management — not cosmetic.
Today I shipped the core journaling loop for my AI companion app, passed adversarial testing, and rebuilt my entire operational workflow from scratch. Here is what I learned about the strategic trade-offs that define early-stage AI product development.
One of the fastest ways to erode user trust is showing features that look interactive but do nothing. I had UI elements for tags and AI-generated summaries stubbed out in the interface, waiting on a Gemini integration that was not ready. I pulled them entirely. The principle is simple: an absent feature is neutral, but a broken-looking feature is negative. This applies doubly to AI products, where users are already calibrating how much to trust the system.
On the backend, I wired journal entry persistence to Supabase with streak tracking, a completion screen, and an unsaved-conversation navigation guard. The guard exposed an early race condition during testing where state was clearing before the check could fire, a reminder that async UI state and user-facing safety checks need deliberate sequencing.
The highest-leverage decision this week was implementing a pre-model crisis detection layer. Before any user message reaches Gemini, it passes through a hardcoded keyword interceptor checking over 30 crisis phrases. If triggered, the system delivers safe harbor resources directly, bypassing the LLM entirely.
Why bypass the model? Two reasons:
During adversarial testing, figurative language like "I'm dying of laughter" triggered false positives. I accepted that trade-off explicitly. For a product in this category, a false positive is an inconvenience. A false negative is a lawsuit or, worse, a real harm. That asymmetry should drive every safety decision.
I formalized this into a four-tier prioritization framework: safety, legal, and privacy requirements override everything. Feature work only advances when those tiers are clear.
AI journaling sits in a psychologically tricky space. Users want to feel heard, but pure validation is documented to be harmful over time. I implemented a three-tone personality framework: Reflective Listener, Warm Companion, and Gentle Coach. The goal is to meet users where they are emotionally while preserving the ability to gently challenge patterns, not just mirror them.
This is a product design decision as much as a prompt engineering one. The personalities are not cosmetic skins. They represent distinct interaction models with different risk profiles, and getting this wrong has real consequences in a mental wellness product.
The single biggest productivity unlock this week had nothing to do with code. It was treating prompt engineering as an infrastructure problem.
I consolidated all project context into a single "golden master file" maintained through diff-only patching. Every new chat session starts from the same canonical source of truth. This eliminated the most persistent failure mode I was hitting: the AI losing critical context across sessions because conversation search could not reliably retrieve earlier work products.
A few other workflow changes that compounded:
Transparency about failure modes matters, so here is where the tools fell short:
The meta-lesson is that AI tooling requires the same observability mindset as any production system. You need to know when it is lying to you, and you need to design workflows that are resilient to that failure mode.
Looking back at the week, a few principles proved consistently useful:
The Gemini integration is the next major milestone, which will bring AI-generated summaries and the full personality framework online. The crisis detection layer and the compliance-first prioritization framework give me confidence that I can ship that integration without introducing unacceptable risk.
The operational workflow is finally stable enough that I am spending more time building product and less time fighting my tools. That ratio is the real metric for whether vibe coding is working.