Outreach automation system - #10
Draft
chehaba wants to merge 13 commits into
Draft
Conversation
…oomInfo) - Lead Campaign Assignment Matrix: evidence-based mappings from Oops.csv - assign_lead_to_campaign.py: Job Title + Industry → Campaign + service phrase - Supports single lead CLI and CSV batch; tier 1 industries (Healthcare, Gov, etc.) - IT Director × Healthcare → 03 Ownership; Finance Director → 07; Marketing Manager → 09 Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- Evidence tables: Industry×Seniority×Service, Function×Seniority×Industry×Service - Supports --min-n and --json for pipeline use - Documented in Lead Campaign Assignment Matrix and README Co-authored-by: chehaba <chehaba@users.noreply.github.com>
|
Cursor Agent can help with this pull request. Just |
- 'this SharePoint migration' → 'nobody owns this anymore' - 'this Power BI deployment' → 'reports take too long' - 'this Dynamics implementation' → 'too many duplicates' - HubSpot: 'need help setting up', 'too many duplicates' - BPO: 'can't keep up with tickets' - AI: 'where do we start', 'information overload' - Migration: 'need to consolidate' Based on Inbound What They Want pain language and user examples. Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- 'nobody owns this anymore' → 'Most waste comes from systems nobody officially owns anymore—orphan sites, permissions drift.' - 'reports take too long' → 'Reports take too long to get, or the answers aren't there when you need them.' - 'too many duplicates' → 'Too many duplicates, messy data, and teams that work around the CRM instead of using it.' - All pain phrases are now complete thoughts—usable as hooks or opening lines in copy, not cryptic fragments. Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- Add linear workflow reference table - Each skill: step-by-step, prerequisites, output, how to validate, common failures - 12 skills: tech stack, Austin scrape/export/enrich, assign campaign, evidence analysis, target matrix, conversion teardown, attribution, deep parse, run analysis, persona normalization - Validation checklist: what to check before asserting findings Co-authored-by: chehaba <chehaba@users.noreply.github.com>
…xport flows - Foundation (1-13) + Elite (1-10) tiers - Elite 1: Full lead pipeline Austin→enrich→assign→export - Elite 2: Win-rate-weighted prioritization - Elite 3: Tech stack vs. won deals (competitive intelligence) - Elite 4: Cross-source synthesis (Austin + Oops + Inbound) - Elite 5: Regeneration discipline (when to refresh what) - Elite 6: Export-to-platform flows (D365, ZoomInfo, Gong) - Elite 7: Gap analysis (who's missing) - Elite 8: Signal stacking (multi-signal scoring) - Elite 9: Anti-patterns (don't do this) - Elite 10: Staleness & data quality checks - Skill 13: ATX lead scoring (MW/Mkt fit) Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- Affirma does mainframe, VMware, Oracle, SAP (partners, deep skill set) - First motion: legacy/on-prem collaboration/productivity → AWS, Azure, GCP, IBM Cloud, Oracle Cloud, Alibaba Cloud - GCP = data analytics/AI focus - Replace 'out of scope' with 'first-motion focus' across Targeting Strategy, prompts, AGENTS, CONTRACT - Target cloud list: AWS, Azure, GCP, IBM Cloud, Oracle Cloud, Alibaba Cloud Co-authored-by: chehaba <chehaba@users.noreply.github.com>
…file each - cloud-migration-modernization/MASTER.md: Targeting Strategy + Market Analysis Tables - outbound/MASTER.md: SDR Guide, Messaging Framework, Enterprise Legacy, Segment Packs, Value First, Campaign index - reports/MASTER.md: Lead Campaign, Company Type Matrix, Messaging Summary, Inbound What They Want, Analysis Report, index - prompts/MASTER.md: Cloud Migration Targeting + Messaging Motion prompts - agent/MASTER.md: AGENTS workflow, CONTRACT, full SKILLS (Foundation + Elite) Each directory: one master file, even if long. Added READMEs pointing to MASTER. Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- consolidated/cloud-migration-modernization.md - consolidated/outbound.md - consolidated/reports.md - consolidated/prompts.md - consolidated/agent.md - README with regen commands Co-authored-by: chehaba <chehaba@users.noreply.github.com>
- PROMPT.md: Read first. Workflow, triggers, constraints. - CONTENT.md: All reference data consolidated (Market, Messaging Lookup, Lead→Campaign, Inbound, Win Rates, Scripts). No grep, no folder hopping. - scripts/: Symlinks to repo scripts. Run from root: python3 agent-pack/scripts/<name>.py - README: Usage and regen instructions Co-authored-by: chehaba <chehaba@users.noreply.github.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
2 participants
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.
Add scripts and a matrix for automated, evidence-based lead-to-campaign assignment to scale outreach.
This PR introduces
scripts/assign_lead_to_campaign.pyto automate lead assignment based on job title and industry, focusing on director and manager levels, andscripts/analyze_lead_campaign_evidence.pyto generate the underlying data-driven rules, ensuring reproducibility and transparency of the assignment logic.