The four moving parts
1. A content source holds the data
1. A content source holds the data
Your records live in an index — documents pushed in from a PIM, ERP, CMS, or any other system. Speedtrain reads them; it never edits them.A task can also run over another task’s approved output, which is how you chain jobs together. Content sources
2. A task configuration describes the job
2. A task configuration describes the job
The configuration says who the AI is, what dimensions the output varies across, what tools it may use, and how the result will be judged.It deliberately does not say which data to run over. That is chosen when you start a session, so one configuration can serve several feeds. Task configurations
3. A review session runs it over real records
3. A review session runs it over real records
Starting a session binds a configuration version to an input source and one option per variant dimension. Each document produces one generation, which is then scored by every applicable quality rule.The quality gate aggregates those scores into accept or reject, and the item is presented for a human decision. Review sessions
4. A destination publishes what was accepted
4. A destination publishes what was accepted
Accepted content is delivered to an Enterspeed source, from where it flows on to wherever you need it.Only accepted items in an active destination are delivered, and delivery is never retroactive. Destinations
What happens to a single item
1
Generation
The platform assembles a prompt from the specialist’s role, the bound variant options, the output contract, the quality rules, and any special instructions. The model returns a JSON object.
2
Scoring
Every applicable rule runs in parallel. Deterministic rules execute as code in milliseconds at zero token cost. AI rules are separate model calls, each judging one question in isolation.
3
Gate
Scores are aggregated by the configured gate —
strict, balanced, or lenient. This is pure arithmetic.4
Routing
Passing items can auto-approve. Failing items go to human review with the failing rule’s feedback attached.
5
Decision
A person accepts, declines, or retries. On a retry, the previous attempt’s failure feedback is fed back into the next generation.
Quality rules are used twice. Before generation they are injected into the prompt so the model knows what it will be judged on. After generation they execute for real. The first pass improves quality; only the second proves anything.
Versions and rollout
A configuration is versioned, and exactly one version is published at a time. The safe path is always the same:1
Save a draft
Edit freely. Drafts do not affect anything running.
2
Preview against the draft
Run a test session over a handful of documents and read the results — especially the rejected ones.
3
Publish
Publishing names the version it displaces, so rolling back is a single action.