Sakana AI launches Aquarium, an enterprise AI decision-making agent platform
SakanaAILabs · x · 2026-10-23
Sakana AI announced Sakana Aquarium, an AI agent platform for decision support and execution in enterprises, born from recurring challenges in its AI deployment work: models alone aren't enough—AI must understand the meaning and relationships of organizational data and the rules behind decisions, which previously had to be rebuilt per project.
The platform has three pillars: (1) Ontology—connect existing tables and documents without migration and define their semantics so AI understands context; (2) Managed Agents—describe flows like "collect info → AI judgment → human approval → execution" as workflows and run them as agents; (3) Governance—configure access rights and approval timing, with full logging of AI reasoning and actions for audit. Sakana's FDEs will build and validate with customers going forward.
More from coding & agent
- 7 Mistakes Economists Make With Claude Skills: Not Building Their Own and Making Too Few — aniketapanjwani · 2026-10-23
- MIT Sloan research: AI speeds up coding but delivery still bottlenecks on testing — sven_ai · 2026-10-23
- Agents logging into bank accounts violate most banks' terms, even with user consent — pstAsiatech · 2026-10-23
- Codex desktop shipped with no editor: 4-person team bet everything on agents — sujingshen · 2026-10-23
- Under matched token budgets, most gains of web agent online augmentation vanish — hllo_wrld · 2026-10-23
- First company officially incorporated by an AI agent via Stripe's Atlas MCP — jeff_weinstein · 2026-10-23