diff --git a/README.md b/README.md
index c436692..36de7fa 100644
--- a/README.md
+++ b/README.md
@@ -53,7 +53,7 @@ nodes columns share, on every step; `rep:collect`) → CSV → register file
 
 ## The profile: a map of the data
 
-A profile lists the kinds of things in the data (entities), what each one
+A profile (using SHACL + some extensions) lists the kinds of things in the data (entities), what each one
 has (fields), and which fields lead to other entities (links). The app
 writes it; the service ships no profile and knows no vocabulary.
 
@@ -285,6 +285,7 @@ The validator (`src/runner/check.js`) runs on every proposal and again
 before every run. It returns the first problem, in words the LLM can act on.
 On top of the rules above, it checks that:
 
+- the Turtle holds one `rep:ReportSpec`, no more: one answer is one report;
 - every step of every path exists in the profile;
 - no path is longer than `MAX_PATH_DEPTH` steps;
 - a date or number test ends on a value field, not on a link;
@@ -504,4 +505,4 @@ non-admin callers. Opening this up means adding the type to their group first.
 ## What it will not do
 
 No counting, no sorting, no top-N, no comparing two subjects, one class per
-report, suggestions stop at the public graph.
\ No newline at end of file
+report, suggestions stop at the public graph.
diff --git a/src/llm/loop.js b/src/llm/loop.js
index 2ce38a7..adda16b 100644
--- a/src/llm/loop.js
+++ b/src/llm/loop.js
@@ -48,6 +48,9 @@ Rules:
   applies. Say that in Dutch in your proposal, so the user can check it.
 - Only offer what validate_spec accepted. Before you suggest an alternative,
   write it and validate it; if it does not validate, say it cannot be done.
+- One answer carries one spec, and one spec is one report on one profile. If
+  the question needs two reports, say so, propose the first, and offer the
+  second as the next step.
 - You cannot count, sort, take the first N, or compare two subjects. Say so.
 - The report's title is the dct:title you write in the spec. There is no other
   title input.
@@ -101,7 +104,13 @@ export async function ask(turns, profiles) {
       }
       // validate_spec answers "ok" (plus notes) when the spec checks out;
       // that spec becomes the bijlage of the answer.
-      if (call.function.name === 'validate_spec' && /^ok(\n|$)/.test(result)) spec = args.spec;
+      // One answer carries one spec: say so when this one replaces another.
+      if (call.function.name === 'validate_spec' && /^ok(\n|$)/.test(result)) {
+        if (spec && spec !== args.spec) {
+          result += '\nThis spec replaces the one you validated before. Your answer carries only this one.';
+        }
+        spec = args.spec;
+      }
       messages.push({ role: 'tool', tool_call_id: call.id, content: result });
     }
   }
diff --git a/src/runner/spec.js b/src/runner/spec.js
index a2a0bfc..51a2b18 100644
--- a/src/runner/spec.js
+++ b/src/runner/spec.js
@@ -13,8 +13,13 @@ export function parseSpec(turtle) {
   const quads = parser.parse(turtle);
   const store = new N3.Store(quads);
 
-  const specNode = store.getQuads(null, RDF + 'type', REP + 'ReportSpec')[0]?.subject;
-  if (!specNode) throw new Error('spec has no rep:ReportSpec');
+  const specNodes = store.getQuads(null, RDF + 'type', REP + 'ReportSpec').map(q => q.subject);
+  if (!specNodes.length) throw new Error('spec has no rep:ReportSpec');
+  // One spec is one report. A second one would pass unchecked and never run.
+  if (specNodes.length > 1) {
+    throw new Error(`one spec per answer. This Turtle has ${specNodes.length} rep:ReportSpec. Keep one, and offer the other as the next report.`);
+  }
+  const specNode = specNodes[0];
 
   const one = (s, pred) => store.getQuads(s, pred, null)[0]?.object || null;