Compress the path from live feedback to a testable code change by capturing the user’s words, structuring the issue, creating a Linear ticket, and invoking a context-rich coding agent from Slack.
Source episode · 37:00
How I AI: Chintan Turakhia’s Playbook for AI Adoption at Coinbasewith Claire Vo
Chintan records live feedback, turns the audio into a structured issue and Linear ticket, then invokes an internal Slack bot that uses repository and observability context to prepare a pull request and preview.
A traceable Linear issue and draft pull request linked to the original feedback, with a preview that makes the proposed fix easy to test.
Anthropic AI assistant
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Use a mobile friendly recorder with one obvious control. Capture the user’s words during a consented dogfooding session and attach the session, product area, and timestamp.
The app only needs a simple record button to minimize friction and capture feedback in the moment.
Transcribe the audio and return structured fields for observed behavior, expected behavior, product area, user journey, severity evidence, title, and concise summary. Keep diagnosis explicitly separate.
Process this consented user feedback recording. Return JSON with transcription, feedback_type, product_area, user_journey, observed_behavior, expected_behavior, impact, concise_title, ticket_summary, and open_questions. Preserve the user’s evidence. Do not invent a root cause.
The prompt should guide the model to extract the core problem and user journey, for example: 'On trade tab, typing into from field does not display numbers, user cannot initiate a trade.'
Search Linear for a matching issue. Create a new ticket only when needed, attach or link the audio and transcript, and apply the relevant journey and feedback labels.
This step eliminates manual data entry and ensures that feedback is logged consistently and immediately.
From the shared Slack thread, invoke the coding bot with the repository and ticket ID. Have it retrieve authorized code, error, and analytics context, create a draft PR, and return the PR plus preview to the same thread.
Claude bot create pr --repo wallet-mobile --ticket [TICKET_ID]. Read the ticket and attached feedback, inspect authorized Sentry, Datadog, analytics, and repository context, state the likely cause with evidence, implement the smallest fix, run relevant checks, and return a draft PR plus preview link to this thread.
For maximum effectiveness, this bot should be integrated with other services like Datadog and Sentry to pull in relevant context for debugging.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.
Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.
Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.