Triage a bounded LinkedIn inbox using explicit reply, archive, skip, and stop rules while keeping final messages reviewable.
18:31 to 20:40: Claire opens LinkedIn in Codex browser automation, defines how to triage the inbox, and watches the agent inspect messages and prepare responses.
A triage log plus draft replies for messages that meet the response rules.
OpenAI conversational AI
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
4 steps
Open your AI desktop app, such as ChatGPT, and use its built-in browser feature to log into your LinkedIn account.
Open LinkedIn in the authenticated browser profile and navigate to the specified inbox segment.
Provide a direct prompt that tells the AI how to handle your messages. Specify what to reply to, what to flag for your review, and the tone it should use.
For the next [number] messages: draft a reply when [rules], archive when [rules], skip when [rules], and escalate [sensitive cases]. Do not send.
Run the prompt and let the AI navigate your inbox. It will click through unread messages, analyze their content, and perform the actions you specified.
Inspect one thread at a time and log sender, message summary, rule matched, and proposed action.
Review the AI's drafted replies and notes, and handle any messages it flagged for you. Calibrate your approach as needed. For a simple task like this, a faster, less powerful model may be more efficient.
Review this sample of triage decisions, apply these corrections [list], and rerun only the untouched items.
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
Create context-aware guardrails for your enterprise AI agent using a 'Project' governance layer. As a project owner, define rules, scope tools, and require human-in-the-loop approval for sensitive actions, ensuring safe and effective AI use.
Transform a successful AI chat session into a reusable skill that anyone in your company can use. Package prompts, tools, and code into a standardized workflow, making it easy to share and scale automation across your organization.
Use a natural language AI agent to instantly generate and iterate on custom data dashboards. This workflow queries your company's data securely, allowing non-technical users to perform their own 'last mile' data analysis without filing tickets.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.