Use business records to compare time allocation with priorities and produce a strategy grounded in the underlying numbers.
Source episode · 07:03
How I AI: My First Impressions of Claude Opus 4.8 – Coding, Strategy, and Where It Shineswith Claire Vo
07:03 to 09:31: Claire compares Opus 4.7 and 4.8 on a business strategy grounded in three months of work, then asks for a roadmap and checks whether the model actually searched the available data.
A business strategy that traces its priorities to verified operating evidence.
Anthropic AI assistant
Anthropic AI assistant
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
In Claude Cowork, select the Claude Opus 4.7 model. For data-heavy strategic analysis, this older model is more effective at grounding its responses in the provided context.
Use the model best suited to structured analysis and source-grounded business reasoning.
Grant the model access to a wide range of business context. Include sources like documents, messages, calendars, and code repositories to provide a comprehensive basis for its analysis.
Review the supplied records and summarize current priorities, time allocation, revenue or usage signals, and constraints with source links.
Prompt the model to analyze your time allocation over the last three months against your strategic business goals. The aim is to identify discrepancies between where you spend your effort and where you should focus to grow the business.
Compare where time is spent with the stated goals, then recommend the three highest-leverage changes and their tradeoffs.
Review the model's analysis. Look for a structured, numbers-anchored response that directly references the data sources you provided. Opus 4.7 should produce a data-driven summary of your activities.
Check every conclusion against the source table and flag unsupported or weakly supported claims.
In a follow-up message, ask the model to convert its analysis into a specific roadmap. The goal is to get a set of actionable strategic initiatives based on its data-driven findings.
Turn the accepted strategy into a 90-day roadmap with owners, milestones, measures, and decisions.
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
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.