← Back to main spec FUTURE SCOPE

AI Fleet Analyst

Email-First Intelligence Platform · Workerline Q1–Q2 2026 Vision

This document captures the vision for replacing the traditional dashboard paradigm with an AI analyst that communicates via email—proactively briefing customers, answering questions on demand, and surfacing insights no chart could reveal. This is out of scope for the current Workerline Enhancements sprint and is documented here for future planning.

The core shift: from "display data" to "deliver understanding." Customers aren't data analysts—they're operational people who need to know what to do, not what to look at.

1. The Concept

Instead of a dashboard that passively shows data, the primary interface becomes a conversation over email. A fleet manager asks: "How are crews doing on my Asia-Pacific vessels this month?" and receives a direct, contextualized answer with evidence—no clicking through filters, no interpreting charts.

"You're hiring an analyst, not buying software. They monitor every vessel 24/7, speak 200+ languages, and never take a day off."

This reframes the product from a SaaS subscription into an intelligence service—a framing that resonates with maritime companies accustomed to paying for services (P&I clubs, classification societies, crew management) rather than software access.

2. Three Layers of Access

📬

The Brief

Pushed to you weekly (daily for large fleets). A narrative summary covering what changed, what needs attention, what's trending. Serves 80% of the "checking in" use case.

💬

The Conversation

Reply to any email to ask follow-up questions. "Compare sentiment between my tanker and bulk carrier fleets." The analyst responds with data-backed answers.

🔍

The Evidence Layer

Every claim includes a one-time link to a focused evidence page—no dashboard, no login. Shows the underlying data, anonymized excerpts, and trend lines.

3. The Weekly Brief

The primary product touchpoint. A narrative email that reads like an intelligence report from a trusted advisor—not a data dump.

Structure

Monthly Deep Read

A longer, more reflective fleet wellbeing analysis—the difference between a daily news briefing and a monthly magazine feature. Covers bigger-picture trends, benchmarking, and strategic recommendations.

Visual Elements in Email

Charts rendered server-side as inline PNG images (not attachments). Compact trend lines, comparison bars, RAG status tables, and mini heatmaps—woven between written analysis. Styled HTML elements (colored status indicators, progress bars, metric tables) for lightweight data without images. Consistent visual templates the customer learns to read quickly.

4. The Conversational Reply

Customers reply to any briefing email to dig deeper. The analyst maintains thread context and handles ambiguity naturally.

Example Interactions

Customer ReplyAnalyst Response
"What about the Pacific fleet?"Contextual breakdown of Pacific vessel sentiment, cases, and engagement
"More on that second point."Expanded analysis of the referenced insight with supporting evidence
"Send this to my DPA at john@osm.com"Forwards a clean, shareable summary to the specified recipient
"Send me a Q4 fleet report"Generates a narrated PDF with executive summary, findings, trends, and recommendations
"Send audit-ready summary for MV Nordic Spirit"Compliance packet: engagement rates, case history, escalation response times, wellbeing trends
Forgiving replies. The AI handles messy, incomplete replies—asking clarifying questions naturally when needed: "Do you mean the Pacific tankers or the full Asia-Pac fleet?"

5. Evidence Cards (One-Time Links)

Every substantive claim in an email includes a small link that opens a single-purpose evidence page. Not a dashboard—a focused, read-only page that exists to answer one question: "Where did this insight come from?"

What an Evidence Card Contains

Properties

Technical simplicity: A lightweight web app with a single route that takes a token, looks up pre-generated content, and renders it. No user sessions, no state management, no frontend framework. Content is generated at the same time as the email.

6. Meeting Integration

The analyst can be invited to Teams meetings (crew welfare reviews, safety committees) and participate via chat—surfacing data, answering questions in real time, and providing meeting summaries afterward.

How It Works in Practice

Maritime fit: Welfare meetings are often mandated (MLC compliance, company policies, P&I requirements). This doesn't change workflow—it makes an existing meeting dramatically more productive.

7. Analyst Personality & Onboarding

Identity

Onboarding as Relationship-Building

The first week isn't a product walkthrough—it's the analyst introducing itself:

"I've been assigned to your fleet. Here's what I've observed so far. Here are the kinds of things I can help you with. What matters most to you?"

This first exchange calibrates ongoing behavior—one customer cares about retention risk, another about compliance readiness, another about mental health specifically. The analyst remembers and adapts.

8. Challenges & Mitigations

ChallengeRiskMitigation
Discoverability Email becomes a confirmation machine—only tells people what they expect Editorially opinionated briefings with a "something you might not have noticed" section. Suggested questions at the end of each email. Monthly deep-read for bigger patterns.
Depth on demand Email format strains for deep, open-ended exploration Generated PDF reports on request. Temporary evidence pages with richer data. Depth feels like escalation within the same conversation, not a different tool.
Proof & credibility "An AI email told me" won't cut it in a boardroom Inline evidence attribution with specific numbers. One-click evidence cards behind every claim. Forward-friendly design so emails work up the chain.
Trust Maritime industry is conservative and compliance-heavy Every claim traceable to actual conversations/data points. Evidence layer exists as a verification backstop. Measured, understated tone builds credibility.

9. Competitive Advantage

10. Technical Architecture (High-Level)

Three components, intentionally simple:

ComponentPurposeNotes
Email composition engineGenerates data-rich HTML emails with inline chart images and styled metricsScheduled (weekly/daily) + on-demand. Reusable chart templates (trend line, bar chart, RAG table, mini heatmap).
Conversational reply handlerInterprets customer replies, maintains thread context, generates follow-up emailsHandles ambiguity, asks clarifying questions. Generates PDFs for report requests.
Evidence card rendererServes single-purpose web pages behind expiring tokensNo login, no sessions, no frontend framework. Server-rendered. Content pre-generated alongside emails.

11. Foundation Analysis — What Already Exists

The current Workerline Enhancements sprint (§4.1–4.7 of the main spec) builds the data layer that makes the AI Analyst viable. The table below references both the existing production schema (sessions with summaries, sentiment scores, cases with messages/actions, departments, survey_instructions) and the new tables being added in the current sprint. The main spec's ERD is simplified to show only new/changed fields — the existing production tables are more comprehensive.

CapabilityStatusRelevance to AI Analyst
Session data with AI summaries✅ Exists (production)Each conversation already produces a GPT-4 summary, sentiment breakdown (positive_pct, negative_pct, neutral_pct), and risk analysis fields. These exist in the production sessions table (not shown in the main spec's simplified ERD). This is the raw material for briefings.
Risk scoring (0.0–1.0)✅ ExistsSeverity level, category, warning signs, follow-up timeline — all stored per session. Directly feeds "vessels of concern" and anomaly detection.
Cases with messages & actions✅ Exists (production)Full case lifecycle (open → assigned → resolved) with cases, case_messages, and case_actions tables in production schema. Provides the "case updates" section of briefings.
Org/site/department hierarchy✅ Exists (production)Multi-vessel fleet structure: orgssitesdepartments already modeled in production schema. Enables fleet-level and vessel-level queries.
Resend email integration✅ ExistsAlready used for escalation emails and notifications. Outbound email infrastructure is ready.
Bull queues (Redis-backed)✅ ExistsAsync job processing for risk analysis, email, push. New briefing generation jobs slot in naturally.
OpenAI GPT-4 integration✅ ExistsChat completions, structured outputs, streaming — all working. The analyst's synthesis and reply generation use the same infrastructure.
Escalation system🔧 Current sprintAuto-escalation with configurable thresholds. Feeds "proactive alerts" in the analyst's briefings.
Org settings & feature flags🔧 Current sprintPer-org configuration. Briefing preferences (frequency, focus areas) would live here.
Inbound email processing❌ NewResend supports inbound webhooks but it's not wired up. Needed for conversational replies.
Server-side chart generation❌ NewNeeded for inline email visuals. QuickChart API or chart.js + canvas → PNG.
Teams bot framework❌ NewMicrosoft Bot Framework registration, webhooks, adaptive cards. Significant new surface area.
Key insight: The core data (sessions, sentiment, risk analysis, cases, org hierarchy) and infrastructure (OpenAI, Resend, Bull queues) already exist or will exist after the current sprint. The main new engineering efforts are the email composition pipeline, inbound reply handling, server-side chart generation, and the evidence card renderer. Meeting integration (Phase 4) is the largest net-new effort, requiring Microsoft Bot Framework and Azure AD integration.

12. Implementation Phases & Estimated Cost

Broken into four phases that can be delivered incrementally. Each phase is independently useful—the client doesn't need to commit to all four at once.

PhaseScopeBuilds OnEffortEstimate
Phase 1: Email Briefings Scheduled Bull job for weekly/daily briefing generation. GPT-4 synthesis across sessions, cases, and risk data. HTML email templates with inline chart PNGs (QuickChart or canvas-rendered). Fleet overview, vessels of concern, anomaly narratives. Existing sessions, risk analysis, cases, Resend, Bull queues 1 week $4,400
Phase 2: Conversational Reply Resend inbound webhook handler (SPF/DKIM validation). Thread context management with deduplication. Natural language → data query → GPT-4 synthesis. On-demand PDF report generation. Phase 1 email engine + existing GPT-4 integration 1–1.5 weeks $5,500
Phase 3: Evidence Cards Single Express route with signed token auth. Server-rendered evidence page — trend line, anonymized excerpts, fleet comparison. Pre-generated alongside emails. Expiring links, access logging. Phase 1 content generation 2–3 days $1,800
Phase 4: Meeting Integration Microsoft Teams bot registration + Azure AD auth. Real-time chat participation via Bot Framework. Meeting context tracking. Auto-generated post-meeting summaries and action items. Tenant governance and app policy setup. Phase 2 query engine + existing data layer 2–3 weeks $9,900

Full AI Analyst — All 4 Phases

$21,600

5–7 weeks · agentic coding workflow · incremental delivery · each phase independently deployable

Phases 1–3 (Email-Only)
$11,700

Briefings + replies + evidence cards · ~2.5 weeks

Phase 4 Add-On
$9,900

Teams meeting integration · 2–3 weeks

Pricing note: These estimates assume the same AI-driven development workflow used in the base Workerline Enhancements sprint ($13,200 for 7 features / 2–3 weeks). Phases 1–3 heavily reuse existing infrastructure (Resend, Bull, GPT-4, existing session/case data), keeping scope tight. Phase 4 (Teams) is the exception — Microsoft Bot Framework integration involves external platform complexity that agentic workflows can accelerate but not eliminate.
Recommended starting point: Phase 1 alone ($4,400) delivers immediate value—customers receive weekly AI-generated fleet briefings without any workflow change. It validates the concept before committing to the full build. Phase 2 adds the conversational dimension that makes it feel like a real colleague. Phase 4 (Teams) can be deferred or scoped separately.

Ongoing Costs (Client Responsibility)