Conversations & signals

Beyond automatic token and cost capture, you can attach your own signals to a conversation: a resolved intent, an outcome, tags, and notes. These are set by your logic (a rules engine, a human, a downstream step) distinct from the LLM classifier.

Set intent and outcome

await ff.signal({
  conversationId,
  intent: "billing",       // optional
  outcome: "resolved",     // optional
});

Writes the intent and/or outcome columns on firstflow_conversations. Use it when your application already knows the answer for example, the user clicked “this resolved my issue.”

Tags and notes

await ff.tagConversation({
  conversationId,
  tags: ["vip", "escalated"],
  notes: "Asked for a refund; promised follow-up.",
});

Writes the tags (text array) and notes columns. Useful for triage and later filtering.

Requirements

These columns ship in migration 0007_conversation_signals.sql apply it first. See Set up Supabase.
Both methods are no-ops (with a warning) if your persistence adapter doesn’t implement signal / tagConversation. The shipped Supabase adapter implements both.

Signals vs. the classifier

	`signal` / `tagConversation`	`classifyIntent`
Decides the value	Your code	An LLM
Cost	Free (a DB write)	One LLM call
Use when	You already know the outcome	You want to infer intent from the transcript

You can use both: classify intent automatically, then signal a final outcome when the conversation closes.

Querying

select intent, outcome, count(*)
from firstflow_conversations
where intent is not null
group by intent, outcome
order by count(*) desc;

Infer intent and sentiment automatically in Intent & sentiment.

Browser SDK

Server SDK

Advanced

Conversations & signals

Set intent and outcome

Tags and notes

Requirements

Signals vs. the classifier

Querying

Next

​Set intent and outcome

​Tags and notes

​Requirements

​Signals vs. the classifier

​Querying

​Next

Set intent and outcome

Tags and notes

Requirements

Signals vs. the classifier

Querying

Next