docs: 0.2.2 — teach agents the Leadbay inbox + two-scoring-layers mental model#14
Merged
docs: 0.2.2 — teach agents the Leadbay inbox + two-scoring-layers mental model#14
Conversation
…tal model Agents were calling pull_leads like a generic DB query rather than treating it as a daily inbox, and didn't know that leads past the auto-qualified top ~10 can still be deepened on demand. This reframes the agent-facing surface to match how Leadbay actually works. - SERVER_INSTRUCTIONS gains "How Leadbay works" (inbox + consumption-based pacing), "Two scoring layers" (basic score vs AI-qualified top ~10 with ai_agent_lead_score), and "Suggested rhythm" (daily check-in, host-agnostic scheduling hint). Verification mandate still leads. - Composite descriptions (pull_leads, research_lead, bulk_qualify_leads, enrich_titles, account_status) reinforce the same model so the agent sees it at both top level and per-tool. - OpenClaw plugin manifest description rewritten to match. - README gains a "How Leadbay thinks" section. - Non-regression test guards the inbox/pace/scoring/daily language. - Bump @leadbay/mcp and @leadbay/leadclaw to 0.2.2 (patch — copy-only, no schema changes, wire-compatible with 0.2.1). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Agents using Leadclaw were calling
pull_leadslike a generic DB query rather than as a daily inbox, and didn't know that leads past the auto-qualified top ~10 still exist and can be deepened on demand. This is a docs/copy-only 0.2.2 patch that reframes the agent-facing surface (MCP server instructions, composite tool descriptions, plugin manifest, README) around how Leadbay actually works: an inbox delivered per login, paced by user consumption; two scoring layers (basicscore+ AI-qualified top ~10 withai_agent_lead_score); and a daily-check-in rhythm with host-agnostic scheduling. No schema changes — wire-compatible with 0.2.1.Test plan
pnpm -r typecheckgreenpnpm -r testgreen (core 58, leadclaw 12, mcp 20 — includes new SERVER_INSTRUCTIONS mental-model assertion)🤖 Generated with Claude Code