Skip to main content
DecimalAI is built around a single idea: when your agent changes, you need to know what still holds. Every trace your agent produces is tied to the exact agent configuration that produced it — its manifest. When you change a prompt, swap a model, add a tool, or edit a sub-agent, DecimalAI knows precisely which past traces are still valid and which are now stale. This is manifest-aware versioning, and it is the foundation under everything else. This page is the entry point — each section below has its own focused deep-dive.

The foundation: manifest-aware versioning

A manifest is a structured snapshot of your agent across ten compatibility surfaces — prompt stack, model runtime, tool registry, skill registry, workflow, sub-agents, output contract, guardrails, context config, and environment. Every trace records the manifest it ran under. When the manifest changes, DecimalAI compares old to new surface-by-surface and tells you, for each past trace, whether it was structurally touched. That single capability is what makes the three product capabilities possible:
CapabilityWhat it answersWhat manifest-awareness gives it
Regression checksDid this change break anything?Knows exactly which surfaces changed, so it scopes the check to traces that actually depend on them
Skills registryWhich skills measurably help?A skill is a manifest surface; SkillScore is measured against the manifest the trace ran under
Training-data validationWhich traces are safe to train on?Stale traces — those whose manifest no longer matches the current agent — are filtered before they poison a dataset
Each capability works on its own. They compound because they share one model of what an agent is — its manifest.

The agent lifecycle

Manifest-aware versioning tracks your agent across its whole life — from the first prototype to a retrained model that starts the cycle again.
StageWhat happensWhat manifest-awareness does
PrototypeYou build the agent and capture first tracesRecords the initial manifest as the baseline
ShipThe agent runs in productionStamps every trace with the manifest it ran under
ImproveYou change a prompt, model, tool, or sub-agentRuns a regression check; flags which past traces are now stale
RetrainValid traces become a training set; you fine-tuneFilters out stale traces, then a better model ships and the loop repeats
The three capabilities each work standalone, but they compound on one foundation — manifest-aware versioning.

The data model

These are the core entities DecimalAI captures and how they relate. A session groups the traces of one logical run; each trace is pinned to the manifest it executed under and decomposes into spans and LLM calls; a trace can link to a parent trace when a sub-agent is invoked.
EntityWhat it is
SessionA logical run that groups one or more traces
TraceOne agent execution, pinned to the manifest that produced it
ManifestThe structured snapshot of the agent across its ten compatibility surfaces
SpanA single step inside a trace (a tool call, a retrieval, a sub-step)
LLM CallA single model invocation recorded within a trace
parent_trace_idSelf-link on Trace — set when a sub-agent trace is spawned by a parent trace

Read in order

Execution Model

Traces, spans, LLM calls, sessions — how DecimalAI captures and organizes agent activity.

Versioning & Compatibility

Manifests, components, compatibility verdicts, repair — the core innovation.

Evaluation

Evaluators, eval scores, eval verdicts, the unified decision engine.

Multi-Agent Systems

Orchestrators, sub-agents, delegation vs handoff, drift detection.

Skills & Data Pipeline

Skills (SKILL.md), datasets, export formats (SFT/DPO), replay, repair.

Glossary

Quick A-Z reference for any term.

The improvement loop

Putting all the concepts together, here’s how they connect into a continuous cycle: This loop runs continuously. Each iteration produces a better model, which produces better traces, which produce better training data.

Where to next

Quickstart

If you’re new — install the SDK and get your first trace in 5 minutes.

2-Minute Demo

One command seeds a demo agent and links you to a live impact report.

Glossary

A-Z quick reference for any term used in these concept pages.

API Reference

Every REST endpoint with examples and schemas.