Agents: Omni

Overview

Omni is a dealer-facing, secure GPT environment built by Fullpath. Unlike public LLMs, Omni is trained on the dealership's own data, integrates with the dealership Customer Data Platform (CDP), and uses the Model Context Protocol (MCP) to leverage dealership agents (inventory, incentives, OEM offers, Shopper data, etc.).

Omni uses what's called Deep Thinking, which means it has enhanced context for more accurate, nuanced responses, as well as:

• Ability to draw intelligent insights and recommendations
• Can handle multiple queries simultaneously and step-by-step
• Can aggregate and analyze data across the full shopper space, not just individual records
• Can elucidate the reasoning and logic behind shopper merges and presumed Identity Resolution

Omni is accessible via the Fullpath Dashboard and is positioned to preserve customer privacy, reduce per-user costs compared to individual accounts, and improve team performance while minimizing PII leakage risk.

How It Works

Omni isn't just a chat window bolted onto the Dashboard — it actively surfaces things it thinks you should know, before you even ask. That behavior is organized into a few distinct areas of the expanded Omni view. Here's what each one does and why it's there.

The "For You" Section

"For You" is Omni's personalized feed — a running list of AI-generated reports and proactive messages tailored to the person who's logged in, not a generic dashboard summary. It lives in the Omni panel underneath your conversation history, so it's the first thing you see alongside past chats when you open Omni.

What shows up in "For You" depends on who you are and what's enabled on your account:

• A General Manager typically sees a daily pulse-check briefing — a "morning coffee" style report on how the store is trending.
• A Sales Manager sees content oriented around team performance and pacing.

• A Sales Rep sees opportunity-oriented items — things like hot leads from the day before, or shopper activity worth following up on.

   

Behind the scenes, Omni scores and ranks these items by relevancy before deciding what to surface, so the most useful item for that person and that moment lands at the top rather than a flat chronological list. Clicking into any "For You" item opens it as a full conversation in the main Omni chat window, with the underlying data and reasoning already loaded — there's no need to re-ask the question Omni already answered for you.
 

Top Insights Bar

Across the top of the Omni interface sits a bar of AI-generated insights, analysis, and suggested next-best actions — a higher-level companion to the conversational chat window below it, meant to be scanned at a glance rather than asked for.

Conversation History & Upper-Left Controls

The familiar GPT-style chat window is the core of Omni. Above it, in the upper-left corner, you'll find:

• New chat / Quick start — start a fresh conversation
• Bookmark and save — keep important chats for later so they don't get lost in your history

Chat Features

• Attach files to a conversation (up to 5 uploads per message)
• File types supported: txt, csv, json, pdf, png, jpg, jpeg
• File size supported: up to 5MB per file
• Use supported toolsets (e.g., code interpreter, web/file search) if enabled

Dashboard Push Notifications

• Prompts daily proactive insights
• Suggests further topics or deeper dives

Inventory Analysis

Omni can perform detailed analysis of dealership inventory data, including:

• Analyzing a subset of inventory (e.g. used vehicles only, a specific make or model) rather than aggregating across the full lot
• Comparing inventory metrics by body class, electrification level, and drive type
• Counting inventory broken down by any supported criteria (e.g. "how many of each make do we have on lot?")
• Standardized make data — variations like "KIA" and "Kia" are treated as a single make

Shopper Analysis

Omni can scan a client's entire shopper space and compute aggregated metrics across all shoppers, rather than reviewing shoppers one page at a time, including:

• Aggregating and ranking shoppers by attribute (e.g., zip code distribution)
• Filtering by engagement or behavioral thresholds (e.g., marketing engagement score under a given value)
• Comparing cohorts (e.g., owned-vehicle vs. non-owned-vehicle shoppers) across a metric like VDP views
• Computing averages across a filtered shopper set (e.g., average equity, average engagement score)
• Explaining individual Shopper Identity Resolution logic and reasoning, with visual aids to map out exactly why and how multiple entities may have been merged

Where to Find It / Navigation

Technical Eligibility

Available for Fullpath Dealer customers who have CDP Pro or the Fullpath Agentic CRM.

Roles and Permissions

Omni is available for Admin, Edit, or Read Only profiles.

• Omni can talk about any products that are enabled on the store account and which the profile using Omni has access to.
• Omni cannot access group-level metrics (at this stage).

Navigation

Omni is included in the CDP Pro package as well as the Fullpath Agentic CRM, and therefore doesn't sit as a separate product in the Dashboard. Omni is enabled by default on all live CDP Pro accounts and is accessible via the Dashboard side menu across all pages.

Privacy, Security, and PII Handling

Omni is privacy-preserving and trained on dealership data to reduce reliance on public LLMs. It is designed to prevent PII leaks and protect customer information when used correctly.

Omni Data and MCPs

Omni has several built-in Model Context Protocols (MCPs), or context bundles, that it can use to ground its responses in dealership-specific data. Fullpath is constantly adding more MCPs to the mix; some typical MCPs include (but are not limited to):

Omni Use Cases

A sample of suggested prompts:

Tier 1: Executive / GM Questions (High-Impact Decisions)

Performance & Pacing

• "How are we pacing month-to-date versus the same point last month? Can you also help explain what is driving the increase or decrease by looking at lead sources, traffic sources, shopper behavior, and any other relevant contributing factors?"
• "What is our projected month-end sales/gross if the current pace continues?"
• "Where is the store leaking in the lead-to-sale funnel? Are we converting enough leads into appointments and shown appointments?"
• "Which lead sources or vendors are actually producing sales?"
• "Which zip code is the highest number of our shoppers from?"

Inventory & Demand

• "Do we have enough inventory for the vehicles shoppers are demanding? Which makes/models have demand but not enough stock?"
• "Which aged or promoted VINs need attention? Are VINs Acceleration units getting more VDP views after promotion?"
• "Which models are getting the most engagement?"

Store Health

• "How is my store doing today?" (morning briefing: sales, inventory, service, CRM workload)

Tier 2: Marketing Director Questions (Campaign ROI)

Traffic & Conversion

• "Which traffic sources are driving website conversions?"
• "How are my traffic sources performing relative to their benchmarks?" (close rate vs. industry standard by source)
• "Perform a website audit" (traffic quality, engagement paths, drop-off analysis)

Channel Performance

• "How did paid media perform this month by channel and objective? What did we spend, and are we on pace with budget?"
• "Which channels are efficient or inefficient by CPC, CPL, CTR, and conversion rate?"
• "Which campaigns should we scale, pause, or reallocate budget from?"
• "Are we getting enough VDP views from paid campaigns? What is the estimated CPL after accounting for calls and lead events?"

Audience Activation

• "Are Audience Activation campaigns producing opens, clicks, leads, and sales? Which AA campaigns are causing unsubscribes?"
• "Is unsubscribe rate spiking for any campaign, store, or time period?"
• "Which shoppers were reactivated or influenced by marketing?"
• "What's the average marketing engagement score of all shoppers who clicked an ad this month?"

Tier 3: Sales Manager / BDC Questions (Team Efficiency)

Funnel & Follow-Up

• "Which lead sources are producing appointments, shown appointments, and sold units?"
• "Where are leads getting stuck between lead received, appointment set, appointment shown, and sold?"
• "Are appointment show rates improving or declining?"
• "Which CRM leads need better follow-up? Are close rates different by source, vendor, make, or campaign?"

Prioritization

• "Which shoppers should sales prioritize right now?"
• "Who's in the sales lane today that I might be able to upsell to?" (equity + recent activity)
• "Show me five people to call today who were active yesterday on VDPs but haven't submitted a lead."
• "How many leads were left this month by shoppers with a marketing engagement score under 4?"

Tier 4: Compliance / CX Questions (Risk Mitigation)

• "Which campaigns are causing unsubscribes? Are unsubscribe rates unusually high?"
• "Are SMS/email opt-outs increasing? Are communication preferences being respected?"
• "Which campaigns risk list fatigue? Are shoppers receiving too many messages?"

Tier 5: Data Quality / CRM Ops Questions (System Health)

• "Are emails, phone numbers, addresses, VINs, and deal numbers usable? Where do CRM and DMS records disagree?"
• "Which clients or stores have data quality problems? Are shopper records merging correctly?"
• "Are opt-in and opt-out statuses accurate? Are lead sources mapped consistently?"