Initial commit: prospecting agent loop MVP

Closed-loop account-intelligence system: harvest -> relevance filter vs.
Capability Library -> synthesize -> score -> deliver -> feedback.

- 40-capability Broadcom + VMware library
- Live Exa.ai news connector with hard free-plan request ceilings
- Provider-agnostic LLM layer (Gemini/Anthropic) with offline mock fallback
- LLM confidence wired into composite scoring + low-confidence floor
- 7-account pilot list

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

sales-agent/src/capabilities.py

@@ -0,0 +1,61 @@
+"""Capability Library loader + lightweight keyword pre-filter.
+
+The design uses a vector ANN pre-filter to cut LLM calls ~60%. For the MVP we
+approximate that with keyword overlap scoring (no embedding service required).
+The interface is the same: given a signal, return candidate capabilities.
+"""
+from __future__ import annotations
+
+import json
+import re
+from functools import lru_cache
+
+from . import config
+
+
+@lru_cache(maxsize=1)
+def load_library() -> dict:
+    return json.loads((config.DATA_DIR / "capabilities.json").read_text())
+
+
+def capability_by_id(cap_id: str) -> dict | None:
+    for cap in load_library()["capabilities"]:
+        if cap["id"] == cap_id:
+            return cap
+    return None
+
+
+def _tokens(text: str) -> set[str]:
+    return set(re.findall(r"[a-z]{3,}", text.lower()))
+
+
+def prefilter(signal_content: str, top_k: int = 3) -> list[dict]:
+    """Return capabilities whose keywords overlap the signal, best first.
+
+    Stand-in for the vector ANN pre-filter in the design (section 5.2).
+    """
+    sig_tokens = _tokens(signal_content)
+    scored: list[tuple[float, dict]] = []
+    for cap in load_library()["capabilities"]:
+        kw = set(k.lower() for k in cap.get("keywords", []))
+        kw_tokens: set[str] = set()
+        for k in kw:
+            kw_tokens |= _tokens(k)
+        overlap = len(sig_tokens & kw_tokens)
+        if overlap:
+            scored.append((overlap, cap))
+    scored.sort(key=lambda x: x[0], reverse=True)
+    return [cap for _, cap in scored[:top_k]]
+
+
+def library_summary_for_prompt(candidates: list[dict]) -> str:
+    """Compact capability descriptions for the relevance-filter prompt."""
+    lines = []
+    for c in candidates:
+        lines.append(
+            f"- {c['id']} | {c['name']}: {c['description']}\n"
+            f"  Buying signals: {'; '.join(c['buyingSignals'])}\n"
+            f"  Anti-signals: {'; '.join(c['antiSignals'])}\n"
+            f"  Target buyer: {', '.join(c['targetBuyer']['titles'])}"
+        )
+    return "\n".join(lines)