From Coder to Manager: Navigating the Shift to Agentic Engineering with Notion Co-Founder Simon Last

2026-03-12 · Source: No Priors: AI, Machine Learning, Tech, & Startups · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Data Science & Analytics · Depth: Advanced, extended

Summary

Notion co-founder Simon Last discusses the company's aggressive embrace of AI, transitioning from a tool for human-direct work to a platform for humans managing AI agents. The journey began in 2022 after experiencing GPT-4, leading to a rapid launch of an AI writing assistant in February 2023. This was followed by a more complex Q&A feature in October 2023, which involved building a real-time semantic index across Notion workspaces and external data sources like Slack and Google Drive. Notion's engineering approach involves frequent "harness" rewrites (every six months) to adapt to evolving AI models and leveraging coding agents to increase ambition and robustness in development. The company has launched personal agents for every user and custom agents that can autonomously perform knowledge work tasks, such as email triage and bug routing, by interacting with Notion databases and external channels like Slack.

Key takeaway

For CTOs and VPs of Engineering evaluating AI integration, your teams should recognize that AI fundamentally shifts the engineering paradigm from direct coding to agent management. Embrace frequent iteration on AI infrastructure and empower engineers to leverage coding agents for increased output and ambition. Focus on designing internal APIs and workflows that are optimized for AI agent interaction, enabling autonomous task execution and allowing human oversight to scale effectively across complex operations.

Key insights

Notion is evolving into an agent-centric platform, shifting from human-direct work to human-managed AI agents.

Principles

• Continuously adapt to evolving AI models.
• Empirical iteration is key for retrieval systems.
• Small teams enhance productivity with AI tools.

Method

Notion's development involves frequent AI harness rewrites (every ~6 months) to align with current model capabilities, using coding agents for end-to-end implementation and verification, and designing agent-friendly APIs (e.g., Markdown dialect, SQLite for databases).

In practice

• Use coding agents for ambitious, robust development.
• Train custom agents with approval loops for automation.
• Prioritize agent-friendly API design for integration.

Topics

• Notion AI
• AI Agents
• Large Language Models
• Semantic Indexing
• Agent-Driven Development

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, AI Product Manager, MLOps Engineer

Related on AIssential

• The End of Software Engineering: How AI Agents Are Fundamentally Restructuring the Software Paradigm — AI agents fundamentally restructure software engineering by making code an ephemeral tool for LLM-driven reasoning, not a static artifact.
• The Sequence Radar #849: Last Week in AI: OpenAI Ships Agents, xAI Eyes Cursor, DeepSeek and Kimi Advance — AI is transitioning from standalone models to integrated, operational systems that coordinate action within workflows.
• Steve Yegge Wants You to Stop Looking at Your Code — AI agents will transform coding into orchestration, shifting human roles to managing complex problems and leveraging taste.
• Why Notion’s biggest AI breakthrough came from simplifying everything — Simplifying AI interactions with human-readable formats and minimal abstraction dramatically improves model performance and user adoption.
• Running an AI-native engineering org — Agentic coding fundamentally redefines engineering bottlenecks, shifting focus from code generation to verification and strategic human oversight.
• Faster Code, Slower Understanding: A Survival Note from a Year of Agent-First Engineering — AI shifts the engineering bottleneck from code production to comprehension and maintenance, demanding new optimization strategies.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by No Priors: AI, Machine Learning, Tech, & Startups.