Wireframes — AI integrations (W23–W29, W35)¶
Visuals: wireframes-ai.html · Slide deck
Every AI surface follows the same four rules: show the grounding, expose confidence, require human approval before customer contact, and capture accept/edit/reject feedback that flows to the model console (W28). All generation runs on the local purpose-tuned LLM (3.3) unless a task is explicitly switched to a hosted API through the adapter interface. v4.3 adds the model lifecycle pipeline (W29) — how an adapter graduates from eval to production with a human signing the promotion — and interaction review (W35), which turns each call, email, and visit into playbook-fit coaching and tracked commitments. Deliberately not built: a general-purpose chatbot (every surface here is task-shaped) and a standalone lead-scoring screen (the score lives on W19; its evaluation lives on W28).
W23 — AI composer (in-context drafting)¶
Drafting from inside a job or Contact 360: template intents, tone/length controls, personality match applied, and a grounding panel showing exactly which retrieved facts (pgvector) the draft used, plus consent and pricing-floor checks. The AI never sends — approve/edit/reject is the human gate, and that feedback trains the next adapter (W28).
Visual: wireframes-ai.html
W24 — AI nodes in the automation canvas¶
Extends the W4 canvas with AI node types — generate message, classify reply, extract fields — under guardrails: a confidence branch routes anything below threshold to a human task, an approval-gate node is required before customer-facing sends, and each AI node has a model selector exposing the local-adapter vs. hosted-API choice from 3.3.
Visual: wireframes-ai.html
W25 — Photo damage detection review queue¶
Vision AI over the media hub (W20): proposed hail-hit annotations with per-detection confidence, accept/adjust/reject controls, and a certification path into the insurance packet. The principle: AI proposes, a named inspector certifies — nothing reaches an adjuster without human sign-off, and the packet records who approved what. Accept rates feed the model console (W28).
Visual: wireframes-ai.html
W26 — Inbox triage & reply classification¶
Inbound texts/emails auto-classified (interested · scheduling · question · not-now · opt-out) feeding the automation engine. The compliance hook is the point: AI-detected opt-outs write to the suppression layer immediately with no approval gate, while low-confidence classifications route to a human queue. Override rates feed W28.
Visual: wireframes-ai.html
W27 — Ask-your-data analytics¶
Natural-language questions over the warehouse, answered with the chart plus provenance — which continuous aggregate, which filters, the generated SQL — so answers are auditable, not oracular. Read-only access against Timescale aggregates; no AI write path to data.
Visual: wireframes-ai.html
W28 — Model ops & eval console (admin)¶
The governance screen the v4 LLM decision demands: active base model and LoRA adapter version, held-out rubric scores side-by-side against the hosted-API baseline (the comparison the adapter escape hatch enables), GPU cost vs. estimated API spend, per-surface human feedback rates (W23/W25/W26), drift alerts, and the retune queue with rollback targets.
Visual: wireframes-ai.html
W29 — Model lifecycle & promotion pipeline¶
How a model change ships: offline eval against the rubric → shadow mode beside the live adapter (output never shown to users) → canary A/B through the experiments console (W30) → promotion behind a required human sign-off → post-promote monitoring with a warm rollback target. No stage can be skipped, including for hosted-API swaps through the adapter interface; accepted/edited/rejected outputs from W23/W25/W26 become the next version's training set.
Visual: wireframes-ai.html
W35 — Interaction review & relationship health¶
Every interaction — call, email, text, site visit — reviewed by the local LLM against the customer's personality playbook and stored history: playbook-fit checks, sentiment, and detected commitments tracked to completion (a promise made on a call becomes a task). Aggregates roll up to a relationship-health score on the customer side and a coaching view on the rep side. Guardrails are part of the design: per-state recording consent with played disclosure, reps see their own reviews first, manager views lead with aggregates, reviews coach and never auto-discipline, and disputes route to a human.
Visual: wireframes-ai.html