diff --git a/README.md b/README.md
index f8e0788..7f094ab 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,9 @@ Two CDK stacks:
 
 **Always two-axis, never comment-only.** The legacy script's central flaw was
 reading only the comment while ignoring `WO Status` + `Hold Reason`, which left
-~17% in "Other". The two-axis model cuts that to ~9% before any AI.
+~17% in "Other". The two-axis model cuts that to ~9% before any AI — and on the
+real 347-row export the current implementation lands "Other" at **5.2%** (18
+rows) with **18 mismatches** flagged.
 
 - **Axis 1 — comment intent:** regex over the HTML-stripped `Last Comment`,
   most-specific first (escalations → SIM ticket → vendor no-show → scheduling →
@@ -52,6 +54,10 @@ reading only the comment while ignoring `WO Status` + `Hold Reason`, which left
 
 The authoritative spec lives in [`CLAUDE.md`](./CLAUDE.md); the implementation is
 in `lambdas/classifier/classify.py` (owned by the `classifier-engineer` agent).
+The S3-triggered `lambdas/classifier/handler.py` parses each export, classifies
+every non-blank-comment row, writes a per-WO Parquet snapshot to
+`analytics/dt=YYYY-MM-DD/` (registering the Glue partition via awswrangler), and
+emits a `summary.json` for the Phase 4 slack-post Lambda.
 
 ## Repository layout
 
@@ -109,7 +115,7 @@ The export reaches S3 by **direct upload or a local drop-folder**, never SES/ema
   `aws configure --profile apm-wo-drop`.
 
 The classifier Lambda is S3-triggered on the `raw/` prefix regardless of path
-(added in Phase 2 — uploads currently land in `raw/` and wait).
+(any `.xlsx`/`.csv` landing under `raw/` invokes it).
 
 ## Deployment
 
@@ -136,5 +142,14 @@ cdk deploy apm-wo-analysis-grafana    # EC2, ALB, SG, Route53, datasource role
 
 ## Status
 
-**Scaffold (Phase 0).** Build-out proceeds per [`docs/BUILD.md`](./docs/BUILD.md):
-ingestion → classifier → Glue/Athena → Slack → Grafana → docs.
+**Phase 2 — classifier (in review).** Build-out proceeds per
+[`docs/BUILD.md`](./docs/BUILD.md): ingestion → classifier → Glue/Athena → Slack
+→ Grafana → docs.
+
+- **Phase 0** scaffold — merged-pending (PR #6).
+- **Phase 1** ingestion (S3 bucket, drop-folder uploader, OIDC deploy role) —
+  deployed; PR #7 open.
+- **Phase 2** classifier Lambda + Glue database + S3 `raw/` trigger — implemented
+  and `cdk synth`-green; PR #8 open (stacked on Phase 1, not yet deployed).
+- **Phases 3–6** (Glue/Athena query layer, Slack, Grafana, final docs) — not
+  started.