One person's best AI session vanishes the second they close the tab. Grab the 3 prompts that make it your team's.

2026-06-07 · Source: Nate’s Substack · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Shopify's internal AI coding agent, River, has seen significant adoption, with 5,938 employees using it across over 4,400 Slack channels in a 30-day period. In one week, River generated 1,800 pull requests in Shopify's main mono repo, contributing to approximately one in every eight merged pull requests. Beyond these impressive statistics, the key design choice enabling River's impact is its public operation. Unlike typical private AI interactions, every conversation with River occurs in a public Slack channel. This transparency allows other engineers to review threads, observe how senior engineers scope tasks, provide context, identify where the agent encountered difficulties, and see what outputs were rejected or accepted, fostering collective learning and knowledge transfer within the engineering team.

Key takeaway

For AI Architects or Directors implementing internal AI tools, consider designing for transparency from the outset. If your team's AI interactions remain private, you miss critical opportunities for collective learning and prompt engineering refinement. Make AI agent conversations public within team communication platforms. This enables peer observation and accelerates skill transfer. It also improves overall AI utilization across your organization.

Key insights

Public AI interactions foster team learning and knowledge transfer by exposing operational details.

Principles

• Transparency in AI use drives collective learning.
• Exposing AI workflows enhances team skill development.
• Public interaction logs reveal effective prompting.

Method

Integrate AI agent conversations directly into public team communication channels, allowing all members to observe and learn from interaction histories.

In practice

• Route AI agent chats to public Slack channels.
• Review public AI threads for best practices.
• Analyze agent failures to refine prompts.

Topics

• AI Agents
• Knowledge Transfer
• Prompt Engineering
• Internal Tools
• Team Collaboration
• Shopify River

Best for: CTO, VP of Engineering/Data, AI Engineer, Director of AI/ML, AI Architect, Software Engineer

Related on AIssential

• 68% of AI power users do one thing differently — and it is not a prompt trick — Briefing advanced AI agents, rather than prompting, fully utilizes their capabilities and enhances human communication.
• Nicole Radziwill on organizational consciousness, reimagining work, reducing collaboration barriers, and GenAI for teams (AC Ep26) — Generative AI can transform team collaboration by fostering shared understanding and psychological safety.
• The Pulse #157: Internal dev tooling at Meta & the “trajectories” feature — Big Tech's internal tooling, monetization strategies, and regulatory challenges are evolving rapidly.
• Imagine if your Teams or Slack messages automatically turned into secure context for your AI agents — PromptQL built it — PromptQL transforms team communications into secure, actionable context for AI agents via an AI-native workspace and shared wiki.
• Alexandra Samuel on her personal AI coach Viv, simulated personalities, catalyzing insights, and strengthening social interactions (AC Ep28) — Custom AI coaches can transform self-reflection and productivity by externalizing internal monologues and fostering playful engagement.
• Inside Nathan's Second Brain: Daniel Miessler, Security Expert & Creator of PAI, Audits My AI Setup — A robust personal AI infrastructure integrates deep context with autonomous agents for enhanced productivity and security.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Nate’s Substack.