Skip to main content
The fastest way to understand DecimalAI is to see its two headline outputs on real-looking data. Both ship as one-command sandboxes that seed your workspace and link you straight to the result:
  1. decimalai demo regression — what a risky agent change does to production traffic (the impact report)
  2. decimalai demo skills — the skills registry, ranked by measured effectiveness
Everything seeded is prefixed [Demo] and fully removable. No agent code, no framework setup, no LLM API keys.

​
Prerequisites

  • Python 3.10+ (python --version — older Pythons silently install an outdated SDK)
  • A DecimalAI API key from app.decimal.ai/settings
1

Run the regression demo

In ~30 seconds this seeds a demo support agent with two manifest versions and a production trace corpus, then runs the regression check:
The v1→v2 diff contains the three change types you’ll actually ship: a model swap, a tool rename + removal, and a prompt rewrite.
traces: 10 and Traces analyzed: 110 mean different things. 10 is the seeded corpus you’ll see in the dashboard; ~110 is what the engine actually analyzes — it pulls in roughly 100 additional history rows so the check runs against a realistic volume.
2

Read the impact report

Open the printed link. The report answers the question every reviewer has — what does this change do to traffic we’ve already served?
  • 🔴 HIGH IMPACT — traces that called the removed tool. They will break.
  • 🟡 MEDIUM IMPACT — traces touched by the model swap / prompt rewrite. Outputs may differ; structural analysis can’t predict direction.
  • 🟢 LOW IMPACT — traces that never touched a changed surface.
Below the severity bands, each affected trace gets a keep / repair / replay / drop verdict — the same classification that keeps training datasets valid as your agent evolves.This is exactly what the GitHub Action posts on every PR — computed against your production traces instead of seeded ones.
3

Run the skills demo

Seeds three public skills with deliberately varied effectiveness and runs the stats recompute:
The three seeded skills land at different SkillScores by design:The high performer is verified and tops the ranking; the weak one sits at the bottom — because SkillScore is computed from live eval pass rates and AI-judge quality, not install counts.
4

Clean up (optional)

Removes all [Demo] -prefixed agents, manifests, traces, and skills. Exact-prefix matched — anything you created yourself is untouched. Re-running either demo also resets first by default, so you always land in a clean state.

​
What just happened

No agent was executed and no LLM was called — the regression check is a structural query against the trace store, which is why it runs in seconds and costs nothing. The same mechanism, pointed at skills, produces the registry’s effectiveness ranking.

​
Do it with your own agent

Quickstart

Instrument your agent and get your first real trace in ~5 minutes.

Regression Check on every PR

Wire the GitHub Action so this report appears on your next pull request.

Skills guide

Auto-discover your SKILL.md files and measure them on your traffic.

Run the manual loop in Colab

Prefer code? Build the v1→v2 loop yourself in a live notebook.