Observed Signal · Apr 15, 2026 · Product Launch · Source: AINews swyx · Impact: 3/5 · Sentiment: Positive
Notion Launches Custom Agents, Builds Agent-Native Workflow
Notion detailed its multi-year effort to build Custom Agents and an agent-centric product architecture in a Latent Space podcast featuring Sarah Sachs and Simon Last. The company rebuilt its agent harness multiple times before shipping, citing early model limitations, context-window constraints, permissioning complexity, and tooling standards as reasons for repeated iterations. Notion described product and org choices: credits-based usage pricing that abstracts tokens/model/serving tiers, an eval-first approach with dedicated Model Behavior Engineers, progressive tool disclosure, and agent composition using Notion pages and databases as primitives. The discussion covered MCP vs CLI trade-offs, retrieval and ranking investments, Meeting Notes as high-signal data capture, and the longer-term vision of “software factories” where agents spec, code, test and maintain systems collaboratively. Notion said it prefers fine-tuning and retrieval investments over building a foundation model in-house.
Notion’s Custom Agents and agent-native design affect how collaboration platforms integrate AI: impacts product workflows, retrieval/ranking needs, enterprise data capture, and pricing models—relevant to MarTech and teams adopting agentic automation, but not a platform-level policy or major platform technical release.
Track Notion Capital Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Notion launched Custom Agents after multiple rebuilds of its agent harness.
- Notion uses a credits-based pricing model for Custom Agents that abstracts tokens, model type, serving tier, web search and sandbox costs.
- Notion created dedicated eval functions and roles, including Model Behavior Engineers, plus eval engineers and data scientists to run regression and headroom tests.
- Notion composes agents using pages and databases as memory primitives and supports manager agents that invoke and supervise specialized agents.
- Notion is prioritizing investments in retrieval/ranking and fine-tuning over training its own foundation model.
Connected Companies & Entities
4 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Notion launches developer platform for AI agents
Notion announced a Developer Platform that turns its workspace into an orchestration hub for AI agents. The release adds Workers — a cloud sandbox for running custom code and webhooks — plus database sync that can pull data from any API-backed database (examples: Salesforce, Zendesk, Postgres). The platform enables teams to connect external agents, chat with and assign work to them, and exposes an External Agent API for internal agent integrations. Notion says customers have built over one million Custom Agents since launching them in February. The Notion CLI will provide developer access on Business and Enterprise plans; Workers usage is free through August to encourage experimentation. Ivan Zhao, Notion co-founder and CEO, framed the shift as making Notion a programmable platform and orchestration layer for people, agents and tools.
Notion's Spec-Driven AI Engineering Workflow
Ryan Nystrom, a software engineer at Notion, describes the company’s spec-driven AI engineering workflow and agent-driven development practices. Nystrom — who joined Notion after its acquisition of Campsite in December 2024 — was a core builder of Notion AI and led work on Notion Custom Agents (launched February 2026). He runs Project Afterburner to reduce CI times and manages a small engineering team. The piece details internal tooling such as “Boxy,” a VM-based background agent system that lets engineers prompt Codex from Notion comments to generate pull requests, and a spec-first workflow that uses Whisper to capture ideas, Codex to format specs, and autonomous agents to implement and verify changes. The article highlights the importance of fast CI, prompting agents to defend reasoning, subagent/MCP integrations, and why engineers and managers should continue coding.
Notion introduces new AI features and blog posts on CRDTs and agent skills
Notion's website has been updated with new AI product pages (Notion AI, Agents, AI Meeting Notes, Enterprise Search) and new blog posts including 'How Notion handles concurrent editing with CRDTs' and 'A skills library for every agent'.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.