#AI
12 pieces filed under “AI”.
LLMs in the design process: acceleration with a seatbelt
How we use LLMs in the studio: synthetic drafts, copy pressure-testing, edge-case generation — and the verification rules that keep AI-assisted design honest.
Multimodal inputs: the upload box is a trust surface
File, image and audio uploads are where AI features win or lose trust. Design limits, preprocessing transparency, privacy prompts and honest errors for multimodal UX.
RAG and the staleness problem: freshness is a ranking signal
Stale retrieval makes RAG answers confident folklore. Treating freshness as a ranking signal, surfacing 'last updated' in answers, and designing the re-indexing pipeline.
Onboarding for AI features: sell the p50, not the demo
AI onboarding fails when it promises the demo's best-case output. Design first-run flows around median performance — calibrated examples, honest scope, progressive trust.
Multimodal interfaces: beyond the chat box
When chat is the wrong interface: designing AI products with the right modality — voice, image, structured output, inline suggestions — and how to choose.
Teaching what the AI can do: feature discovery as curriculum
AI features fail when users don't know what to ask. Designing discovery surfaces — prompt starters, worked examples, capability demos — that teach, not decorate.
The model deprecation playbook nobody writes until it's 3am
Your LLM provider just announced a deprecation window. How to migrate without panic: abstraction layers, eval-gated cutovers, shadow traffic and honest customer comms.
Onboarding users to an AI assistant
First-run design for copilots: capability discovery without homework, starter prompts that teach, mental-model calibration, and measuring adoption honestly.
AI cost observability: tokens are a line item now
LLM features live or die on unit economics. Build per-feature token budgets, cost-per-successful-task dashboards, cache tracking and frontier charts execs actually read.
Showing the swarm: status UX for multi-agent systems
Multi-agent features bury users in log firehoses or leave them staring at a spinner. Designing step summaries, cost displays, interruption and failure narration.
Feedback loops users will actually feed
Thumbs-down rates near zero tell you nothing. Designing AI feedback signals that collect usable data, close the loop visibly, and track volume as a health metric.
Pylon Care: an AI support assistant that knows its limits
Pylon Health's support queue drowned in the same five questions. We shipped an AI assistant with citations, red lines and a kill switch — evals first.