diff --git a/README.md b/README.md
index 31f21ff..689d815 100644
--- a/README.md
+++ b/README.md
@@ -8,9 +8,11 @@ decides the numbers; domain experts judge the outcomes (human-in-the-loop); and
 
 > **Status:** the full 8-step agentic loop is wired and proven with load-bearing tests, and the
 > end-to-end proof is an **offline simulation** with a scripted stand-in client — no live-model
-> run yet. The ingest layer (real data sources) is specified but not yet implemented. A sibling
-> implementation of the same method on the **Claude Agents SDK** is built in parallel from the
-> same shared spec.
+> run yet. The **ingest layer** (real data sources) is implemented — file/CSV and SQL on both
+> stacks with bit-identical golden extractions from the shared spec, plus HTTP as a MAF-only
+> demonstrated extension point against a local mock — but exercised only against committed
+> fixtures: no bundle has yet been materialized from a live source. A sibling implementation of
+> the same method on the **Claude Agents SDK** is built in parallel from the same shared spec.
 
 > **Disclaimer — technical framework only.** Deploying organizations own their processing
 > purposes and assessments (DPIA, risk/ROS, security review). The framework ships the technical
@@ -87,9 +89,11 @@ when the seam is detached, so the loop cannot silently degrade into theater.
   [ingest spec](shared/ingest-spec.md), the expert-reviewer persona as an Agent Skill, and an
   example bundle with a golden suite as the only ground truth. Both stacks implement from the
   spec alone.
-- **Per project: one OKF bundle** — hand-curated today; the specified ingest layer will
-  materialize bundles from real sources (file catalogues/CSV, SQL, HTTP as an extension point)
-  via a deterministic, schema-validated manifest that runs *before* the loop.
+- **Per project: one OKF bundle** — the bundled examples are hand-curated; the ingest layer that
+  materializes a bundle from a source (file catalogues/CSV + SQL, HTTP as a MAF-only demonstrated
+  extension point) via a deterministic, schema-validated manifest that runs *before* the loop is
+  implemented and exercised against committed fixtures — no bundle has yet been materialized from
+  a live source.
 - **Run:** the CLI takes a bundle directory and a verdict inbox directory; stop criteria and
   budget caps are required at startup. Try the offline end-to-end proof (no model, no network):
   `uv run python -m portfolio_optimiser.simulation`