Freelance UX researchers: make a notes-only interview a planned option before the session starts.

The Customer Interview Research Kit's fictional Alder Forms example separates two preparation checks: • Participation: the person understands the purpose and may skip questions or stop • Recording: the session owner checks separate permission before starting; a notes-only option is available

For your next client research session, confirm how the conversation and notes will be used through the client's approved process. Confirm any recording separately. If the participant chooses the agreed notes-only route, keep recording off and follow the agreed note-handling arrangement.

Tell the interviewer which route was agreed before the session begins. Keep the permission record in the approved system, with only the needed reference in the working files.

The invitation can also keep preparation manageable: this example asks for a 30-minute conversation about a recent weekly report. Participants can recall the experience without bringing confidential documents or sharing their screen.

Shown: the complete Prepare respectful participation page from the kit's fictional completed example. All names and arrangements are illustrative.

The five-file ZIP includes a six-page editable Word packet, matching print PDF, Excel session register, fictional example and Quick Start. Designed for desktop Word and Excel; PDFs are static. For adult customer research using your existing approved participation and recording process; the kit is not a legal consent form.

Get the kit: https://contra.com/payment-link/Lh1gvons-customer-interview-research-kit

CRAG — Self-Correcting Research Assistant

Overview

A research-assistant project exploring how AI applications can retrieve information and improve the quality of their responses through a self-correction workflow.

Project focus

Python-based AI application development.

Retrieval and research workflow design.

Improving answer reliability through evaluation and correction.

Technologies: Python, AI, retrieval-augmented generation.

Self-correcting retrieval is the upgrade RAG has needed, Daniel. Most systems stop at the first retrieval and hope for the best, so building evaluation and correction into the workflow is a real reliability win. The live telemetry dashboard makes it feel production-ready.