Learning Services | DigitalOcean

Featured AI Products
Build, deploy, and scale cloud compute resources
Containers and Images
Safely store and manage containers and backups
Fully managed resources running popular database engines
Management and Dev Tools
Control infrastructure and gather insights
Secure and control traffic to apps
Help protect your account and resources with these security features
Store and access any amount of data reliably in the cloud
Security and Networking
Web and App Platforms
Find out where your agents and models fail in production, then test the fix before it ships. Signals watches traffic on Managed Agents and Serverless Inference and flags the sessions that went wrong, with nothing extra to instrument. Evaluations and Simulations test your change on realistic multi-turn scenarios built from those sessions or from your agent's configuration.
Standard observability tells you the system was up and latency was fine. It can’t tell you the model gave a confidently wrong answer, the agent picked the wrong tool, or a frustrated user gave up. The tool call returned 200 — it just returned the wrong region. The conversation completed — the user left annoyed.
Raw trace volume can exceed 100 GB/s. Grading every session with an LLM judge is prohibitively expensive, and manual review doesn’t scale at all. Most teams learn about failures when a support ticket arrives.
Hand-built tests cover a narrow slice of real behavior. Synthetic test sets aren’t grounded in your agent or your users. Live traffic is realistic, but users pay for the mistakes. And single-response evals miss the failures that only show up across turns: a prompt tweak fixes step two and quietly breaks step five, or a fine-tuned model scores well on in training and regresses in real conversations.
Signals finds the agent and model sessions that went wrong in production and turns them into evaluations you can run. Nothing extra to instrument.
Agent and inference observability
Signals efficiently finds the agent and inference sessions that went wrong in production and turns them into evaluations you can run. Nothing extra to instrument.
For agents on Managed Agents and models served through Serverless Inference.
Evaluations scores agents and models against a consistent bar. Simulations, new in Evaluations, tests any change across full multi-turn conversations before users see it.
Scoring and validation
Evaluate any candidate on your inference stack: Serverless Inference models, Dedicated Inference endpoints, imported BYOM models, and Inference Router policies
Generate scenarios from Signals, plain-language descriptions, or your agent’s configuration
Your models serve through Inference Engine; your agents run on Managed Agents. Nothing to instrument.
Signals stitches turns into sessions, triages them, and identifies trends that you can drill into.
Flagged sessions become evaluation scenarios in one click.
Simulations runs your changed model or agent through those scenarios as full conversations in an isolated sandbox, then grades each conversation on multi-turn metrics.
Deploy the validated change. Signals keep watching. Scenarios worth keeping become regression tests.
Scenarios come from real sessions, and candidates run on the actual production harness, tools, and config. Real behavior, not a synthetic guess.
The same session that reveals a problem becomes the evaluation that validates the fix. No manual test-data prep.
Runs on Managed Agents and Serverless Inference with nothing extra to instrument, whether you’re operating agents, serving models, or both. One console, one bill, one team boundary for your data.
Learning Services is DigitalOcean’s feedback loop for models and agents in production. It’s made up of Signals, agent observability that turns production traces into behavioral insight and ready-to-use evaluations, and Evaluations, which scores agent and model performance and now includes Simulations for rehearsing changes as full multi-turn conversations before they ship. Together they let you improve agents with evidence instead of waiting for a customer to report that something broke.
No. If your models serve through Serverless Inference or your agent runs on Managed Agents, those services already emit the events Signals needs. Enable Signals and data processing begins within about an hour. Signals work best when both your agents and your models run on DigitalOcean. Learn more in the Signals docs.
Signals is opt-in. PII is scrubbed before display and export. Traces and trace-derived evaluations stay within your DigitalOcean Team boundary and are never used to train shared or cross-customer models.
Evaluations scores single responses against defined test cases, and is still the right tool when you want to compare two models on fixed prompts. Simulations is a feature of Evaluations that plays out entire multi-turn conversations against your candidate — on any harness supported by Harness Runtime, including Claude Code, Codex, and OpenCode — so it catches failures that only appear across turns. Every run is graded by the same Evaluations metrics. Check out the docs for Evaluations & Simulations.
Insights is end-to-end tracing: metrics, logs, and traces for every agent turn, connected to the infrastructure underneath. Learning Services is what you do with that behavior: Signals finds the sessions that went wrong, Evaluations scores how your agent or model performs against them, and Simulations tests whether your fix actually makes it better.
Turn on Signals for an agent or model you're already running, and rehearse your next change in Simulations before your users see it.
© 2026 DigitalOcean, LLC.