Preview in 5.0.x

Your acceptance
is the signal.

When you accept an answer, the platform notices. A multi-stage pipeline turns that signal into incremental retraining for the on-device router model. Bad signal is quarantined; the customer's thumbs-up is a vote that lands. The cluster's intent classification gets quietly better at your queries over weeks, without explicit fine-tuning runs.

Next patch


How the loop works

How the signal flows.

Today, the platform classifies every incoming query — is it a tool-requiring request, a knowledge-base search, a plain chat, a system query, a science query? That classification drives routing across the cluster. The classifier is good, but it's a static model: it doesn't know which of your queries it called right, and which it got wrong.

The next 5.0.x patch closes that loop. When you give an answer a thumbs-up, or when an agentic step's tool call succeeds and you accept the result, the system records the (query, classification, outcome) triple as a positive signal. A pipeline filters that signal:


What changes

It gets better at your work.

For customers whose queries don't look like the public-internet average — anyone with domain language, internal acronyms, project-specific shortcuts — the platform's classification quality drifts upward over weeks of normal use. No explicit fine-tuning step. No data leaves the installation. The cluster simply notices what worked, distils it, and folds it back into the router model.

The same signal feeds the dream engine and the memory system — accepted answers reinforce associations, rejected answers attenuate them. The platform doesn't just remember what you've asked; over time it remembers what tends to work for queries like yours.


What's pending

Honest gates on this page.

Still in flight

  • Acceptance-signal capture from the chat shell, macOS GUI, iOS app, and CLI
  • Semantic-novelty filter (in-cluster, no external model)
  • Quality-judge pass with the configured local model
  • Recurrence-threshold tuning by tenant size and license tier
  • Incremental classifier update pipeline + audit log
  • Admin opt-out switch per tenant (some customers will want it off by default)

This page updates as each piece lands. The release notes are the formal cut.


Read next.

For the rest of the memory work landing in 5.0.x, see memory scoping & gated visibility and per-token recall. For the full 5.0.x roadmap, see what's next in 5.0.x.