How a unified config file turns your inbox from a pile of unrelated messages into a prioritized, project-aware briefing. The system drafts. It never sends. That is a design decision, not a limitation.
One triage agent reads every email and routes it. Specialized workers handle enrichment, prioritization, and drafting. A daily digest surfaces what matters. You stay in the loop at exactly one checkpoint. You review a single daily digest and approve or adjust suggested drafts. The human checkpoint is not an afterthought. It is the point of the architecture.
The config is not a settings file. It is the system's understanding of your practice. When you update a project here, every downstream automation inherits the change. This is the Setup Frame applied to systems, not conversations. The config is version-controlled and access-controlled like any other critical system file. Changes are committed to git, reviewed before deploy, and auditable after the fact.
A 1-10 score that influences digest ranking. The Death Star assault outranks supply logistics. When two emails arrive at the same time, the system knows which one you see first.
Per-contact tone guidance. Mon Mothma gets formal briefings. Han Solo gets directness. The drafter reads these notes before generating a response. Same principle as giving Claude context about your audience.
The trust calibration. "Low" means the system produces a skeleton with placeholders. "High" means it drafts a near-ready response. Strategic relationships stay at "low" because the cost of a wrong tone is higher than the time saved.
What the enrichment worker uses to pull relevant context. When an email from Ackbar arrives, the system knows to surface the exhaust port analysis and squadron readiness status alongside it.
Five emails arrive overnight. The triage agent classifies each one, the enrichment worker pulls context, the prioritizer ranks them, and the drafter generates responses where confidence allows. Click each email to see what the system surfaces.
Death Star Assault Planning
Open deliverable: "Attack run briefing" is in-progress and due before Yavin approach. Exhaust port analysis thread is active.
9.4 / 10 - Highest-weight project, deliverable deadline, requires response from strategic leader.
Death Star Assault Planning
Ackbar's comm style: direct operational language, dislikes ambiguity. X-wing squadron readiness is an active thread.
8.1 / 10 - Same project, deliverable-related, but review request rather than decision-required.
Independent Contractor Pipeline
Lando is a warm referral. Charming but cautious. Wants to know what is in it for him. Relationship is "cultivating."
5.2 / 10 - Medium-weight project, scheduling request, no deliverable attached.
"Thursday works for me. Same time? Looking forward to catching up on the Cloud City logistics."
Base Operations (auto-matched by domain)
No active threads or deliverables connected. Routine operational update.
1.8 / 10 - Low-weight project, informational, no response needed.
"Received, thank you. Filed for reference."
None. Contact not in config. Email flagged for manual review.
No prior history. Possible referral, possible noise. System cannot determine intent.
Unscored. Unknown contacts bypass the priority algorithm.
Notice what the system does not do. It does not reply to Mon Mothma. It does not guess at Maz Kanata's intent. It does not skip the human checkpoint for high-stakes relationships. The value is not in what it automates. The value is in how it organizes your attention so you spend your judgment where it matters most.
Each phase adds one capability. You can stop at any phase and still have a useful system. The sophistication of the architecture follows the complexity of the problem, not the other way around.
Move from per-client files to one unified config. Existing transcript processing reads from the new file. Validate that output quality is identical. Change nothing else.
Build the triage agent. It classifies email against the config and writes a digest. No drafting. Backtest against three days of history, then run live for a week. Target: 85% classification accuracy.
When an email matches a project, pull active threads, deliverable status, and contact communication style. The digest now includes a "Context" block per email.
Generate drafts where confidence allows. All drafts go to Gmail drafts folder. Track: used as-is, edited then sent, or discarded. Target: 40% usable with minor edits. Zero relationship-damaging drafts.
Connect all workers to a morning briefing. "Here is what you are working on today, ranked by priority." The inbox becomes a curated briefing rather than an unfiltered stream.
A config is only useful if it reflects current reality. Three rhythms keep it honest.
Every design decision in this system maps to a principle from the program. The same skills you are building in conversation with AI apply to building systems with AI.
The config file is a Setup Frame for an automated system. The quality of the context you provide determines the quality of every output. Same principle, different scale.
Running three days of historical email through the triage agent and refining the rules is the Iteration Loop applied to systems. Test, evaluate, adjust, repeat.
The drafter produces plausible responses. The more polished they look, the less critically you evaluate them. The human checkpoint exists because AI predicts plausible, not true.
The max_draft_confidence setting is explicit trust calibration. High confidence for scheduling acknowledgments. Low confidence for strategic relationships. You set the threshold before the system runs, not after.
"Drafts, never sends" is a design decision. Removing the human from the loop is not the goal. Removing the noise between the human and the decision is the goal.
Phase 1 changes nothing except how the config is structured. Each subsequent phase adds exactly one capability. You can stop at any phase and have a useful system.