DigitalOcean Agent Learning Services

DigitalOcean's feedback loop for agents: Insights logs activity, Signals flags failures, Evaluations & Simulations tests fixes. Public preview.

DigitalOcean · Evaluation, observability, and MLOps tooling · product

Published in Feed

Overview

DigitalOcean launched Agent Learning Services on October 12, 2026 in public preview. It has three parts: Insights records what an agent does, Signals identifies where it falls short, and Evaluations & Simulations tests changes before customers see them. It uses DigitalOcean Agent Data Services as its data layer, and an Inference Router optimizer is in separate private preview.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Insights: logs and traces agent activity
  • Signals: flags failures and shortcomings
  • Evaluations & Simulations: tests a change before it reaches customers
  • Backed by Agent Data Services as its data layer
  • Public preview as of October 12, 2026

Use cases

  • Finding failure patterns in production agent traces
  • Regression-testing agent changes with simulations before release

Pricing

Public preview; pricing not published.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
12 Oct 2026
Record updated
15 Oct 2026
Record last checked
15 Oct 2026

Explore the Feed

Other entries filed under evaluation, observability, and mlops tooling; inclusion does not imply equivalent features.

Browse the Feed