diff --git a/cmd/mavend/repair.go b/cmd/mavend/repair.go
new file mode 100644
index 0000000..63329e0
--- /dev/null
+++ b/cmd/mavend/repair.go
@@ -0,0 +1,197 @@
+package main
+
+import (
+	"context"
+	"log"
+	"strings"
+	"time"
+
+	"github.com/kami/maven/internal/router"
+)
+
+// Conversation repair (Vikunja #455).
+//
+// The classifier has been able to learn from a correction since it was
+// written — CorrectMisroute appends the utterance as a new example for the
+// intent he names, append-only, no retrain. Nothing in the daemon could reach
+// it: the only caller was a test. So the mechanism existed and the behaviour
+// did not.
+//
+// This is the reachable half. He says she got it wrong and names what it
+// should have been, she redoes the previous utterance under that intent, and
+// she says out loud that the correction landed — because a correction he
+// cannot see is indistinguishable from one that was dropped.
+//
+// Taken before routing, like the confirm and clarify turns: "нет, это была
+// заметка" is an answer to the previous turn, not a fresh command, and routing
+// it as one files the correction itself as a note.
+
+// routedTurn — the previous utterance and where it went, which is all a
+// correction needs to point at.
+type routedTurn struct {
+	utterance string
+	intent    router.Intent
+	at        time.Time
+}
+
+// repairWindow — how long a turn stays correctable. Long enough that he can
+// hear the wrong answer, think, and say so; short enough that "это заметка"
+// half an hour later is a fresh sentence and not a verdict on something he has
+// forgotten.
+const repairWindow = 5 * time.Minute
+
+// repairMarkers — the ways he says she got it wrong. One of these must appear:
+// naming an intent alone is an ordinary sentence ("напиши заметку"), and
+// treating it as a correction would rewrite the last turn every time he used
+// the word.
+var repairMarkers = []string{
+	"не так поняла",
+	"неправильно поняла",
+	"ты не поняла",
+	"не поняла меня",
+	"ты ошиблась",
+	"это не",
+	"а не",
+	"не про то",
+	"got it wrong",
+	"not a ",
+	"that was wrong",
+}
+
+// repairIntents — the words he uses for each intent. Prefixes, because Russian
+// declines them: "заметка", "заметку", "заметкой".
+var repairIntents = []struct {
+	word   string
+	intent router.Intent
+	say    string
+}{
+	{"заметк", router.IntentNote, "заметка"},
+	{"напоминани", router.IntentReminder, "напоминание"},
+	{"напомнить", router.IntentReminder, "напоминание"},
+	{"факт", router.IntentFact, "факт"},
+	{"вопрос", router.IntentQuery, "вопрос"},
+	{"команд", router.IntentAct, "команда"},
+	{"note", router.IntentNote, "заметка"},
+	{"reminder", router.IntentReminder, "напоминание"},
+	{"fact", router.IntentFact, "факт"},
+	{"question", router.IntentQuery, "вопрос"},
+}
+
+// parseRepair reads a spoken correction: a marker saying she was wrong, plus
+// the intent it should have been.
+//
+// The negated half is skipped. "это заметка, а не напоминание" names both
+// intents, and the one he is correcting TO is the one he did not put "не" in
+// front of.
+func parseRepair(utterance string) (router.Intent, string, bool) {
+	s := strings.ToLower(strings.TrimSpace(utterance))
+	if s == "" {
+		return "", "", false
+	}
+	// A leading "нет" is a marker on its own — "нет, это заметка" is the
+	// shortest correction he actually says. Only leading: "нет" in the middle
+	// of a sentence is an ordinary word.
+	marked := strings.HasPrefix(s, "нет") || strings.HasPrefix(s, "no,")
+	for _, m := range repairMarkers {
+		if marked || strings.Contains(s, m) {
+			marked = true
+			break
+		}
+	}
+	if !marked {
+		return "", "", false
+	}
+	best, say, at := router.Intent(""), "", -1
+	for _, w := range repairIntents {
+		i := strings.Index(s, w.word)
+		if i < 0 || negatedAt(s, i) {
+			continue
+		}
+		// Leftmost wins: "это заметка, а не напоминание" corrects to the first.
+		if at < 0 || i < at {
+			best, say, at = w.intent, w.say, i
+		}
+	}
+	if at < 0 {
+		return "", "", false
+	}
+	return best, say, true
+}
+
+// negatedAt reports whether the word at i is the one he is ruling out. Only
+// the words immediately before it are read, so "не напоминание, а заметка"
+// negates the first and leaves the second alone.
+func negatedAt(s string, i int) bool {
+	before := strings.TrimSpace(s[:i])
+	return strings.HasSuffix(before, "не") || strings.HasSuffix(before, "not")
+}
+
+// recordTurn keeps the utterance a correction would point at. Only turns she
+// acted on: a clarify asked instead of acting, so there is nothing yet to be
+// wrong about.
+func (h *reactiveHandler) recordTurn(utterance string, intent router.Intent) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.lastRouted = &routedTurn{utterance: utterance, intent: intent, at: h.now()}
+}
+
+func (h *reactiveHandler) takeLastTurn() *routedTurn {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	last := h.lastRouted
+	// Taken, not read: one utterance is corrected once. Saying "нет, не так"
+	// twice would otherwise redo the same request twice.
+	h.lastRouted = nil
+	return last
+}
+
+// resolveRepair handles a spoken correction of the previous turn: teach the
+// classifier, redo the request under the corrected intent, and say so.
+func (h *reactiveHandler) resolveRepair(ctx context.Context, text string) (string, bool) {
+	corrected, say, ok := parseRepair(text)
+	if !ok || h.router == nil {
+		return "", false
+	}
+	last := h.takeLastTurn()
+	if last == nil || h.now().Sub(last.at) > repairWindow {
+		return "", false
+	}
+	if last.intent == corrected {
+		// She already did what he is asking for. Correcting the classifier
+		// here would teach it the label it produced, and redoing the request
+		// would file it twice.
+		return "", false
+	}
+	learned := true
+	if err := h.router.CorrectMisroute(ctx, last.utterance, corrected); err != nil {
+		// The redo is still worth doing: he asked for something and it did not
+		// happen. Only the learning half is lost, and he is told so.
+		log.Printf("voice: repair: could not learn %q as %s: %v", last.utterance, corrected, err)
+		learned = false
+	}
+	log.Printf("voice: repair — %q was %s, corrected to %s (learned=%v)", last.utterance, last.intent, corrected, learned)
+
+	dec := router.Decision{
+		Utterance: last.utterance,
+		Stage:     2,
+		Intent:    corrected,
+		Slots:     h.extractor.Extract(ctx, corrected, last.utterance, h.now()),
+	}
+	// A reminder's Text is what she says at the hour and stays empty when it
+	// was not spoken, so the gap is asked about rather than filled with the
+	// whole sentence. Everywhere else the utterance IS the payload.
+	if dec.Slots.Text == "" && corrected != router.IntentReminder {
+		dec.Slots.Text = last.utterance
+	}
+	return repairLine(say, learned) + " " + h.finishClarified(ctx, dec), true
+}
+
+// repairLine — what she says before redoing it, so the correction is visible
+// and not just filed. Feminine, informal, no apology: he corrected a routing
+// call, he did not complain about her.
+func repairLine(say string, learned bool) string {
+	if !learned {
+		return "поняла, это " + say + " — переделываю, но запомнить поправку не вышло."
+	}
+	return "поняла, это " + say + " — запомнила."
+}
diff --git a/docs/design.md b/docs/design.md
index 9c9e01d..95e441f 100644
--- a/docs/design.md
+++ b/docs/design.md
@@ -223,6 +223,23 @@ Not alternatives — layers:
 Router contract: `[{"intent":<enum>, key?, value?, text?, verb?}, ...]` over
 7 intents (`fact, reminder, note, query, act, chat, system`).
 
+#### Saying she got it wrong is a feature
+
+Landed 2026-08-04 (Vikunja #455). `Router.CorrectMisroute` could always append a
+corrected utterance as a new classifier example, and until now nothing in the
+daemon called it, so the mechanism existed and the behaviour did not.
+
+`cmd/mavend/repair.go` reaches it. He says she got it wrong and names what it
+should have been — "нет, это заметка", "это не напоминание, а факт" — and three
+things happen in one turn: the classifier learns the utterance under the named
+intent, the request is redone under it, and she says the correction landed. The
+utterance he is correcting TO is the one with no "не" in front of it.
+
+Read before routing, next to the confirm and clarify turns, because a correction
+routed as a fresh utterance files the correction itself. One turn is correctable
+once, inside five minutes, and only turns she acted on — a clarify asked instead
+of acting, so there is nothing yet to be wrong about.
+
 #### A restart expires a parked question
 
 Decided 2026-08-04 (Vikunja #385). The follow-up dialogue session survives a
diff --git a/internal/router/router.go b/internal/router/router.go
index 1df278c..c30738e 100644
--- a/internal/router/router.go
+++ b/internal/router/router.go
@@ -2,6 +2,7 @@ package router
 
 import (
 	"context"
+	"errors"
 	"log"
 	"time"
 )
@@ -201,5 +202,10 @@ func (r *Router) gateLLMDecision(d *Decision) {
 // retrain). Same shape as nudges.outcome tuning cooldowns: more reliable over
 // time, introspectable, no model surgery.
 func (r *Router) CorrectMisroute(ctx context.Context, utterance string, corrected Intent) error {
+	if r == nil || r.classifier == nil {
+		// The LLM router can run with no classifier wired. The correction has
+		// nowhere to land then, and the caller redoes the request anyway.
+		return errors.New("router: no classifier to correct")
+	}
 	return r.classifier.AddExample(ctx, corrected, utterance)
 }