Freight Floor
Freight Floor is a browser-based warehouse simulation game built by Davenporter. It runs a 10 Hz local game engine that handles A* pathfinding, collision avoidance, and auto-charging for a fleet of forklift agents, while Gemini (gemini-2.5-flash-lite via Vertex AI) plans contract selection, spill detours, and shift tactics asynchronously in the background. Five AI personas with distinct physics profiles and strategy prompts compete simultaneously, and each agent's model, latency, and last decision are exposed through an in-game inspection panel. Natural-language Co-Pilot instructions pass through a prompt-screening layer before reaching the agent. The full source is available on GitHub under the Davenporter project.
Freight Floor is a browser-based warehouse simulation game built by Davenporter, priced at $5 a month on the Deliver plan, integrating with Gemini, Vertex AI and GitHub. InnovaAI rates it 4.6 of 10 for agency adoption, best for Strategist, Founder and Project Manager roles.
Agency Audit
Freight Floor is a browser-based warehouse simulation where Gemini-powered AI forklift agents compete to fulfill pallet orders, exposing each agent's decision logic for inspection. Your agency adopts it internally to train teams on multi-agent AI architecture, autonomous decision-making under constraints, and real-time LLM behavior. Best suited for strategists, developers, and founders evaluating how AI agents handle competing priorities, collision avoidance, and dynamic replanning. The 10 Hz local game engine paired with asynchronous Gemini planning mirrors production AI systems your team may design for clients.
2recommended
Hours saved not published
Hours saved not published
Low
Illustrative scenario. Not a guarantee. Net capacity is the value of reclaimed time at $75/hr, less the lowest verified paid base plan (flat plan cost is shared). Hours saved come from the service estimate; implementation, taxes, and unprovided usage charges are excluded.
- Strategist handling multi-agent architecture evaluation
- Founder handling internal AI capability demonstration
- Project Manager handling technical scoping for AI builds
- Your agency focuses on design, content, or traditional digital services and does not pitch or build AI agent systems; Freight Floor offers no workflow compression for those disciplines.
- Your team has no existing Vertex AI or Gemini integration roadmap; the tool's value is highest when paired with hands-on LLM experimentation, not as a standalone game.
- Your budget for learning tools is zero or your team's time is fully allocated to billable work; Freight Floor requires 2-3 hours per person to yield insights, and that time must be protected.
Internal Adoption Path
$5/mo
$5/mo flat plan
Hours saved not published
Hours saved not published
Hours saved not published
Illustrative scenario. Not a guarantee. Uses the lowest verified paid base plan. Implementation, taxes, and unprovided usage charges are excluded.
Platform Features
Core capabilities of Freight Floor
Glass-Box Agent Inspection
Tapping any AI forklift reveals its Gemini model, response latency, and the reasoning behind its last move. Strategists evaluating multi-agent architectures can observe real decision logic rather than inferring behavior from outputs.
Dual-Layer Engine Architecture
A 10 Hz local game engine handles pathfinding, collision avoidance, and auto-charging while Gemini plans contracts and tactics asynchronously. This split lets technical leads see exactly where fast reflexes end and LLM reasoning begins.
Competing AI Personas
Five distinct agent personas (Sprinter, Steady, Batcher, Opportunist, Strategist) each pair unique engine physics with a separate Gemini strategy prompt. Operations teams can compare tactical trade-offs across agent types within a single live session.
Natural-Language Co-Pilot with Prompt Armor
Players issue floor instructions in plain language, which pass through a prompt-screening layer before reaching the agent. AI-practice leads can observe how prompt constraints shape agent behavior in a low-stakes environment.
Configurable Agent and Order Settings
Agent personas, order priority modes, and rack zone focus are all adjustable before or during a session. Project Managers scoping logistics AI builds can use these controls to model different operational assumptions.
Live Leaderboard and Shift Standings
Real-time standings and cross-site lifetime records track performance across sessions. Innovation leads running internal demos can use the competitive format to keep stakeholder attention during architecture walkthroughs.
What Makes Freight Floor Different
Unique advantages vs similar tools in this niche
Dual-loop design splits fast local physics from slow LLM strategy
vs Single-loop agent demos that stall on every LLM callThe 10 Hz engine handles pathfinding and collisions while Gemini plans asynchronously with pre-fetched orders.
Glass-box decision logging shows real errors with zero mock fallbacks
vs Black-box agent simulations that hide failuresIf a Gemini call fails, the truck holds and shows the real error rather than silently substituting a mock.
Prompt pre-scoring keeps LLM calls small and cheap
vs Sending full game state to the model on every decisionThe engine pre-scores the top six orders into a compact JSON prompt before each Gemini call.
Value Equation
Outcome-likelihood-time-effort assessment for Freight Floor
Limited agency channel
Freight Floor scored below the agency-resellability threshold (agency_fit_score < 50). The Value Equation projects agency-side outcomes, which don't apply to tools without a clear resell pathway.
Contact Freight FloorPricing
Freight Floor platform cost to your agency
Deliver: $5/mo
Deliver
- Drop it at the blue Shipping Bay by tapping Drop.
- 🏗️ Lift ModeFEATURE FLAGOpt-in 3D vertical rack shelf lifting (L1–L3) with sweet-spot bonuses.
- Lift Mode: OFF
- Out-ship the AI forklifts and finish the shift #1.
No verified white-label program for Freight Floor: client-facing delivery runs under the platform's native branding.
Reality Check
Freight Floor is a learning tool, not a productivity multiplier for existing workflows. Adoption ROI depends on your team's need to understand multi-agent AI behavior; if your agency doesn't pitch or build autonomous systems, the time investment yields limited operational payback. Requires 2-3 hours of hands-on play per team member to extract meaningful insights.
Low effort: self-service setup with guided onboarding
How This Accelerates White-Label Services
Who It's For
- ✓ai-agent-developers
- ✓agencies-demonstrating-autonomous-decision-making
- ✓teams-evaluating-multi-agent-architectures
Acceleration Steps
- 1Sign up and connect your account
- 2Configure simulate a warehouse floor where ai forklift agents compete to fulfill pallet orders
- 3Connect Gemini
- 4Launch your first client project
Academy for Freight Floor
Work through it in order: the course for this service first, then the modules behind it.
Course for this service
Freight Floor Agency Implementation, AI Agent Strategy & Client Demos
Learn to position Freight Floor as a hands-on training and evaluation tool for clients building multi-agent warehouse systems. This course teaches agencies how to run live simulations, inspect agent decision-making through the glass-box panel, and deliver competitive benchmarking reports that justify AI automation investments.
Open the courseNo Academy modules are published for this service yet. Browse the full Academy
Why this category matters
The commercial case before the tooling.
Core concepts
The mental model you need to price and scope the work.
- Wiring Over WidgetsConcept
The AI agent itself is a commodity, but the value for agencies lies in the integration layer: connecting a pre-built agent to a client's CRM, calendar, and review cycle. This framework shifts focus from selecting the 'best' agent to mastering the wiring process. For example, an agency using Vendasta's white-label AI receptionist for a local business must configure it to match the client's booking rules and follow-up cadence, turning a generic tool into a tailored service. As agentic AI adoption grows (77% of decision-makers now run agents in production), clients expect this customization. Agencies that treat agents as components and invest in repeatable wiring processes can charge retainers for ongoing optimization, rather than one-off setup fees.
- Wiring Over WidgetsConcept
The AI agent market sells finished workers, but the strategic value for agencies lies not in the agent itself, which is increasingly a commodity, but in the wiring that connects it to a specific client's CRM, calendar, and review cycle. This framework, 'Wiring Over Widgets,' argues that agencies that treat agents as components rather than products win. The agent is the widget; the wiring is the integration, customization, and ongoing optimization that turns a generic tool into a tailored solution. For example, a white-label platform like Vendasta provides AI employees, but the agency's role is to configure them for each local business's unique lead flow and follow-up process. This wiring is where retainer pricing originates, as it requires ongoing maintenance and adjustment. Recent research shows that 88% of B2B marketers face foundational gaps, meaning clients need help not just deploying agents, but ensuring their operations can support them. Agencies that master the wiring can charge a premium for the irreducible value they add.
- Wiring Premium Over Agent CommodityConcept
Pre-built agents are converging on the same underlying model capability, so the agent itself prices toward zero. What holds value is the wiring: the mapping of a specific client's CRM fields, calendar rules, escalation paths, and review cadence into the agent's loop. Agencies that sell the agent as the product compete on seat price against every reseller of the same worker. Agencies that sell the wiring charge for discovery, field mapping, exception handling, and monthly tuning, which is retainer work. Vendasta's white-label AI workforce and Relevance AI's pre-built sales agents both arrive configured out of the box, which means the configuration is not the moat; the client-specific plumbing is. A practical test: if a competitor could swap your agent vendor next quarter without the client noticing, you sold a commodity. If the swap would break their CRM hygiene, approval chain, or reporting, you sold wiring.
Decision and risk
How to judge the fit, and the ways it goes wrong.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and focus your value on the integration into the client's specific workflows, systems, and review processes.
- AI Agents Rule: Wire the Agent, Not the ProductEvaluation Rule
Treat the AI agent as a commodity component and charge for the integration into the client's specific systems and workflows.
- The Productized Agent Trap: Why AI Agent Services Stall Without Client-Specific WiringFailure Pattern
- The Demo-to-Retainer Gap: Why AI Agents Stall After the Pilot CallFailure Pattern
8 modules selected for Freight Floor
Frequently Asked Questions
Answers about pricing, setup, implementation
Freight Floor lists 1 plan; the paid price is $5 a month (Deliver).
The Deliver plan is $5 per month. No annual pricing is listed for this plan.
Strategists and AI-practice leads benefit most when evaluating multi-agent decision frameworks, since the glass-box inspection panel surfaces real Gemini reasoning. Founders and Innovation Directors can use it to demonstrate autonomous agent behavior to internal stakeholders without building a custom demo. Project Managers scoping logistics or fulfillment AI builds can reference the open-source architecture to anchor scope and effort estimates.
Freight Floor is a simulation and evaluation tool rather than a workflow application, so it does not save hours on recurring tasks. The value is in compressing research and demo-preparation time for AI-practice leads: a team that would otherwise spend several hours building a custom multi-agent demo environment may reduce that setup effort by using Freight Floor as a ready-made reference. No verified per-seat time-savings figure can be stated.
Because Freight Floor runs entirely in the browser with no installation required, a team member can be active in a session within minutes of receiving a link. There is no onboarding configuration, identity provisioning, or data migration step. Rollout friction is low for any team with modern browser access.
Freight Floor integrates with Gemini and Vertex AI for agent planning and with GitHub for source access. It does not connect to project management platforms, CRM systems, analytics tools, or communication apps. Agencies expecting native integration with their existing stack will need to treat it as a standalone evaluation environment.