What Codex unlocks for Notion

Notion’s GPT‑5 rebuild unlocks autonomous AI workflows | OpenAI

November 7, 2025

Notion’s GPT‑5 rebuild unlocks autonomous AI workflows

By rebuilding their agent system with GPT‑5, Notion created an AI workspace that can reason, act, and adapt across workflows.

Company size: Mid-market

Region: North America

Industry: Technology

Products: API

Results

7.6%

Improvement over state-of-the-art models on outputs aligned with real user feedback

Loading…

Share

In late 2022, within weeks of getting access to GPT‑4, Notion had already shipped a writing assistant, rolled out workspace-wide Q&A features, and integrated OpenAI models deeply across its search, content, and planning tools.

But as models advanced - and users began asking agents to complete entire workflows - Notion’s team saw limits in their system architecture. The old pattern of prompting models to do isolated tasks was limiting the ceiling of what was capable on their platform. Agents needed to make decisions, orchestrate tools, and reason through ambiguity, and that shift required more than prompt engineering.

> “We didn’t want to retrofit the system. We needed an architecture that actually supports how reasoning models work.”

Sarah Sachs, Head of AI Modeling at Notion

Inside the rollout

Rebuilding for reasoning models, not retrofitting around them

Instead of patching their existing stack, Notion rebuilt it. They replaced task-specific prompt chains with a central reasoning model that coordinates modular sub-agents. These agents can search across Notion, Slack, or the web; add to or edit databases; and synthesize responses using whatever tools the task requires.

With their launch of Notion 3.0, AI isn’t just embedded in workflows; it can now run them. Users assign a broad task - for example, compiling stakeholder feedback - and their agent plans, executes, and reports back. The shift toward agents that choose how to work meant designing for model autonomy from the start.

Results at a glance

Testing GPT‑5 with real product workloads

To validate the architectural shift, Notion evaluated GPT‑5 against other state-of-the-art models using actual user tasks.

Evaluations were grounded in feedback Notion had already marked as high priority, including questions that surfaced in Research Mode, long-form tasks that required multi-step reasoning, and ambiguous or outdated content where model judgment mattered.

The team used a combination of LLM-as-judge scoring, structured test fixtures, and human-labeled feedback.

Key results:

• 7.6% improvement over state-of-the-art models on outputs aligned with real user feedback
• 15% better performance on difficult Research Mode questions
• 100%+ improvement on multi-step, structured tasks like deadline updates and competitor research
• Only model to fully saturate benchmarks with conflicting or outdated inputs

These evaluations helped Notion identify where GPT‑5 added value - for example, in reasoning, ambiguity, research - and where environment-specific tuning would improve results.

> “We didn’t cherry-pick tasks. These were high-signal workflows from our product....That’s where model differences actually show up.”

—Sarah Sachs, Head of AI Modeling at Notion

Leadership lessons

Lessons for teams building with GPT‑5

Notion’s rebuild wasn’t just about launching Notion 3.0. It was about designing a system that could support new model capabilities and adapt as those models get smarter. Their approach offers a clear roadmap for other teams deploying agentic AI in production:

• Evaluate what matters. Use tasks your users actually do, not synthetic benchmarks.
• Test the hard stuff. GPT‑5 shines when information is ambiguous, outdated, or multi-step.
• Architect for autonomy. If agents are making decisions, your system has to give them room to reason and tools to act.
• Clarity drives performance. Even top models fall short without clean tool descriptions and good interface design.
• Rebuilding is better than patching. If your system was built for completion models, it might not scale to agents.

> “We’re already seeing returns from the rebuild....If the next model unlocks something new, we’ll do what it takes to support it.”

—Sarah Sachs, Head of AI Modeling at Notion

Join the new era of work

More than 1 million businesses around the world are achieving meaningful results with OpenAI.

Keep reading

Building a safe, effective sandbox to enable Codex on WindowsEngineeringMay 13, 2026

Our response to the TanStack npm supply chain attackCompanyMay 13, 2026

How finance teams use CodexOpenAI AcademyMay 12, 2026