ProspectingAgentLoop

JoeBot/ProspectingAgentLoop

Fork 0

Commit Graph

Author	SHA1	Message	Date
Chris Olson	c2854ba163	Anthropic OAuth LLM, entitlements (feature 1), renewals, + 7 enhancements - LLM: Anthropic Sonnet 5 (effort=low) via OAuth Bearer (Claude Code keychain token, expiry-aware); NVIDIA/LM Studio endpoints kept commented for switch-back. - Entitlements: scripts/import_entitlements.py joins ACL export to accounts by normalized parent name (324/342 matched; ID column Excel-corrupted), maps products->capabilities via data/product_capability_map.json. Raw ACL csv and entitlements.json are gitignored (confidential); accounts.json carries derived currentProducts + ownedCapabilityIds. Owned capabilities tag briefs EXPANSION. - Renewals: local renewal-proximity score boost (window 365d, max +0.10) + 'renewals' report; briefs/digests show RENEWAL WINDOW context. - Batch runs: loop --limit/--rep with persistent cursor (strategic + stale-first). - Digests: per-rep HTML export; timestamped digest_<date>_<time>.md kept forever. - Account narrative memory fed into relevance/synthesis; synthesis maintains it. - Signal quality gate drops PR fluff pre-LLM; SEC EDGAR filings connector. - Citation verification: talking points must cite [S#] signals or are dropped. - Brief filenames use account-name slug; whitespace report + installed-base view. - USAGE.md: full command/flag/env reference. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-11 19:12:36 -04:00
Chris Olson	b4e3ed9d9b	Batch LLM calls per account; add 5 pilot accounts - Relevance filter: evaluate all of an account's signals in one LLM call (keyed array, chunked at 8) instead of one call per signal. - Synthesizer: produce all of an account's briefs in one call (one object per capability) instead of one call per capability. ~2 calls/account. - llm: wrap JSONDecodeError in LLMError so callers fall back to mock instead of crashing; disable Gemini thinking (thinkingBudget=0) to stop thinking tokens truncating JSON; add 429 backoff. - accounts: add Booz Allen, Dominion Energy, Hope Gas, Markel, GW Medical Faculty Associates (verified domains; CRM tier captured in crmTier). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-06-23 18:16:08 -04:00
Chris Olson	39a338990f	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>	2026-06-23 11:39:59 -04:00

Author

SHA1

Message

Date

Chris Olson

c2854ba163

Anthropic OAuth LLM, entitlements (feature 1), renewals, + 7 enhancements

- LLM: Anthropic Sonnet 5 (effort=low) via OAuth Bearer (Claude Code keychain
  token, expiry-aware); NVIDIA/LM Studio endpoints kept commented for switch-back.
- Entitlements: scripts/import_entitlements.py joins ACL export to accounts by
  normalized parent name (324/342 matched; ID column Excel-corrupted), maps
  products->capabilities via data/product_capability_map.json. Raw ACL csv and
  entitlements.json are gitignored (confidential); accounts.json carries derived
  currentProducts + ownedCapabilityIds. Owned capabilities tag briefs EXPANSION.
- Renewals: local renewal-proximity score boost (window 365d, max +0.10) +
  'renewals' report; briefs/digests show RENEWAL WINDOW context.
- Batch runs: loop --limit/--rep with persistent cursor (strategic + stale-first).
- Digests: per-rep HTML export; timestamped digest_<date>_<time>.md kept forever.
- Account narrative memory fed into relevance/synthesis; synthesis maintains it.
- Signal quality gate drops PR fluff pre-LLM; SEC EDGAR filings connector.
- Citation verification: talking points must cite [S#] signals or are dropped.
- Brief filenames use account-name slug; whitespace report + installed-base view.
- USAGE.md: full command/flag/env reference.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-11 19:12:36 -04:00

Chris Olson

b4e3ed9d9b

Batch LLM calls per account; add 5 pilot accounts

- Relevance filter: evaluate all of an account's signals in one LLM call
  (keyed array, chunked at 8) instead of one call per signal.
- Synthesizer: produce all of an account's briefs in one call (one object
  per capability) instead of one call per capability. ~2 calls/account.
- llm: wrap JSONDecodeError in LLMError so callers fall back to mock instead
  of crashing; disable Gemini thinking (thinkingBudget=0) to stop thinking
  tokens truncating JSON; add 429 backoff.
- accounts: add Booz Allen, Dominion Energy, Hope Gas, Markel, GW Medical
  Faculty Associates (verified domains; CRM tier captured in crmTier).

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

2026-06-23 18:16:08 -04:00

Chris Olson

39a338990f

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>

2026-06-23 11:39:59 -04:00

3 Commits