Blog
Notes on public-facing AI — trust, safety, and how AI should represent a business.
Boaty McBoatface Is Now an AI Problem
In 2016, the public named a ship Boaty McBoatface and the institution panicked. The same pattern is playing out in AI deployment right now. Lock it down or let it rip -- or build the trust layer.
You Can't Trust What You Can't Trace
Knowledge sources passed as document blocks return citations linked to specific generated text. The portal renders cited claims with inline source badges, so owners can see exactly where every answer came from.
The Compliance Team Isn't Coming
Lab-scale frameworks (NIST AI RMF, EU AI Act, OWASP Agentic Top 10) were built for organizations with compliance teams. The actual risk has moved to the plumber, the clinic, the campaign. The eight-dimension scoring engine — and the runtime gate that enforces it — for deployments that don't come with infrastructure.
You Just Might Get It
Every configuration change to a public-facing AI is a wish -- and the AI grants exactly what was asked. Instead of blocking the risky ones, the trust layer explains the wish before granting it, and captures the owner's response as labeling signal. Progressive disclosure and data labeling turn out to be the same surface.
Why We Don't Sanitize User Messages in Our AI Agent
The correct boundary for prompt injection defense is between system content and user content -- not between safe and unsafe words. Here's why regex filters on user input do more harm than good.
How Customer-Facing AI Agents Determine Trust
Phone numbers, portal sessions, and API keys -- three ways an AI agent decides who it's talking to and what actions it can take. The architecture behind trust boundaries.
Efficiency Is a Design Decision, Not an Optimization
The biggest efficiency gains in AI systems aren't in the code. They're in what you decide not to build. Every scaffolding layer costs energy, money, and human effort. Less machine is the goal.
Trust the Model, Save the Energy
Every layer between the user and the model costs energy. Sierra, Decagon, and Intercom build scaffolding because they don't trust the model. The scaffolding depreciates every 2 months. The model improves.
Speed to Lead Statistics in 2026: How Fast Should You Respond to Leads?
Responding in under 5 minutes makes you 100x more likely to connect. Here are the speed-to-lead statistics that matter — and what they mean for your business.
How Missed Calls Cost Property Managers Tenants and Leases
Tenants call at all hours. Prospects won't leave a voicemail. Here's how missed calls drain property management revenue — and what the best PMs are doing about it.
Best Missed Call Text-Back Services in 2026: What to Look For
Not all missed call text-back services are the same. Some send a template. Others have real AI conversations. Here's how to evaluate them — and what actually matters.
How to Set Up AI Text-Back for Your Business (Step-by-Step)
AI text-back takes minutes to set up — not weeks. Here's exactly how it works, from sign-up to your first recovered lead.
Denver Small Business Tools: AI That Actually Helps You Grow
Denver's small business scene is booming — but growth means more missed calls. Here are the tools Denver businesses are using to capture every lead.
Answering Services vs. AI Text-Back: A 2026 Comparison for Service Businesses
Traditional answering services charge per minute and read scripts. AI text-back responds in 30 seconds with real conversations. Here's how they compare on cost, speed, and results.
How Service Businesses Lose $50K+ Per Year to Missed Calls
27% of calls to businesses go unanswered. 78% of those callers never call back. Here's the math on what that actually costs — and what to do about it.
What Is Missed Call Text-Back? A Complete Guide
Missed call text-back automatically sends a text to customers when you can't answer. Here's how it works, what it costs, and why businesses are adopting it.