AI Agent Platform

Buyers search one way. Catalogs list another. Six AI agents close the gap.

Each agent is trained on an intelligence graph of over 360 million product listings. Ask a question in plain language. Get a grounded answer with citations to the underlying data.

Available on Google Cloud Marketplace. Pay As You Go usage pricing, or API Access for enterprise integration.

View on Google Cloud Marketplace See the agents
The Agents

Six agents. One intelligence graph.

Each agent owns a different decision a merchant makes about their catalog. The Cross-Agent Router decides which agent to dispatch when the question spans more than one. Every agent reads from the same graph, so the answers line up across questions.

Cross-Agent Router

Not sure which agent to ask? Describe the problem.

The Router reads your question and dispatches it to the right agent. For questions that span multiple domains, it sends the question to several agents in parallel and assembles a unified answer. You do not need to learn the product to use it.

$0.25 per question

How to use

What to ask
Describe your situation or goal in a full sentence. The more context you give, the better the Router classifies. "I sell outdoor dining sets and want to know where my gaps are, whether I am priced right, and when demand peaks" dispatches to three agents at once.
What you get
A unified answer organized by theme (gaps, pricing, demand), not by agent. Each finding cites the data row it came from. Ends with 2-3 specific next steps.
What to do with it
Read the Top Insight first. That is the single most important finding. Then work through the Next Steps.

Example questions:

  • I'm launching a line of insulated water bottles under $30. What does the landscape look like?
  • My catalog is invisible on voice search. How do I start?
  • What's the most valuable analysis I can run on my outdoor furniture catalog?

Search Intent Agent

How are buyers searching for products like yours?

Merchants describe products in one language. Buyers search in another. This agent makes the vocabulary gap visible. It shows the exact keywords and questions buyers use, which of those searches should lead to your products, and which products are invisible because the listing language does not match. Ghost products are named, the missing keywords are identified, and the title changes that would close the gap are specific enough to execute the same day.

$0.50 per question

How to use

What to ask
Name your product category or a specific consumer phrase you want to investigate. "Which of my product titles would not show up for best yarn for baby blankets" gives the agent a specific phrase to match against your catalog.
What you get
Consumer keywords and questions with search volume, CPC, and competition. Ghost products named with the listing language that does not match. Title rewrite suggestions with the exact consumer phrase and its monthly search volume.
What to do with it
Update product titles to include the consumer phrases the agent surfaced. Create FAQ content that answers the voice search questions. Prioritize ghost products with the highest search volume first.

Example questions:

  • What questions do people ask about travel mugs on voice search?
  • Which of my product titles would not show up for 'best yarn for baby blankets'?
  • Show me the language buyers use for organic dog food.

Demand Intelligence Agent

When does demand peak? Who is searching?

Merchants make inventory and marketing decisions without knowing when demand peaks, who is searching, or whether their market is growing. This agent tracks demand across 12 dimensions with up to 63 weeks of history. It returns seasonal patterns with specific peak weeks, audience breakdowns by demographic segment, and a timing recommendation for the next quarter: when to spend, who to target, where demand is headed.

$0.50 per question

How to use

What to ask
Name the category, audience, or time period. "Pool floats" gives the full demand profile. "Who searches for hiking boots" gives the audience breakdown. "Is demand for electric scooters growing" gives the trend.
What you get
Demand direction with specific numbers (e.g., "search volume grew 34% from week 12 to week 38"). Seasonal patterns with peak and trough weeks named. Audience breakdowns by demographic segment.
What to do with it
Align marketing spend with the demand calendar. If demand peaks in May, start campaigns in April. Use the audience data to adjust ad targeting. Use the trend data to decide whether to expand or contract inventory.

Example questions:

  • When does demand for pool floats peak?
  • Who searches for 'best hiking boots for wide feet': age, gender, device?
  • Is demand for electric scooters growing or declining?

Taxonomy Gap Agent

Where are the gaps in your catalog?

Consumer demand exists in categories where your catalog has no matching products. These are revenue opportunities sitting in plain sight. The agent maps search demand against product cluster coverage and returns a ranked list of gaps: high-demand keywords where you have no products. Each gap includes search volume, CPC, competition level, and the number of existing sellers. You know exactly which products to add and how large the unmet demand is.

$1 per question

How to use

What to ask
Name the category you sell in or want to expand into. "Kitchen knives" gives the full gap analysis. "Which subcategories of yoga equipment have demand but low competition" narrows to the best expansion opportunities.
What you get
A ranked list of gaps scored by opportunity. Each gap shows the keyword, monthly search volume, CPC, competition level, and how many product clusters already serve that demand.
What to do with it
Evaluate the top gaps as product expansion opportunities. A gap with 5,000 monthly searches and only 3 product clusters is underserved. Use the CPC data to estimate advertising cost in that space.

Example questions:

  • Where are the gaps in my outdoor furniture catalog?
  • What categories am I missing in kitchen knives?
  • Which subcategories of yoga equipment have demand but low competition?

Pricing Intelligence Agent

Are you priced right?

Merchants set prices without knowing where they sit within the market distribution. This agent pulls the market range for each product cluster (median, average, min, max), your position within it, and how prices have moved over recent months. It returns a product-by-product repricing assessment: which products are overpriced, which are underpriced, and the specific dollar adjustments that would align you with the market.

$1 per question

How to use

What to ask
Name the product or category. "Kitchen knives" gives category-level positioning. "Am I overpricing my santoku knives" gives a specific product comparison. Include a price point ("under $30") to anchor the analysis.
What you get
Market median, price range, your position within it, and recent price trends for each relevant product cluster. Concrete recommendations: raise, hold, or lower, with specific dollar amounts.
What to do with it
Reprice the products flagged as overpriced or underpriced. Start where the gap between your price and the market median is largest. If prices are trending down, factor that into margin planning.

Example questions:

  • How do my kitchen knife prices compare to the market?
  • Am I overpricing my santoku knives?
  • Where is my margin most at risk from mispricing?

Campaign Architect Agent

Draft a Google Ads plan.

The gap between "I have products" and "I have a data-driven ad campaign" is where most merchants stall. This agent drafts a complete campaign plan: ad groups with keyword lists, match types, bid ranges, budget allocation, and negative keyword suggestions. Every keyword comes with search volume and CPC from the intelligence graph. The output is formatted for direct import into Google Ads Editor. Draft mode only. Nothing is live until you review and approve.

$2 per question

How to use

What to ask
Name the products you want to advertise. "Insulated water bottles" gives a full campaign structure. Include your budget ("$500/month") for a more tailored plan.
What you get
A draft campaign plan: ad groups by theme, keyword lists with search volume and CPC, bid ranges (low/high), budget allocation weighted by opportunity, and negative keyword suggestions. Formatted for Google Ads Editor import.
What to do with it
Review the draft. Remove keywords that do not fit. Adjust bids to match your margins. Load the plan into Google Ads Editor. Start with the ad group that has the highest opportunity score and lowest competition.

Example questions:

  • Draft a Google Ads campaign for my insulated water bottles.
  • What are the lowest-competition, highest-volume keywords I should bid on for hiking boots?
  • Build me an ad group structure for pet grooming supplies.

Agents in front. Reports behind.

Each agent answers in conversation, then offers more when the data warrants. When a question crosses a depth threshold (hundreds of keywords queried, a multi-dimension analysis, or language signaling a request for the complete picture), the agent surfaces the matching Lens Intelligence Report as the next step.

The agents are the entry point. The reports are the deliverable a merchant takes to their team or executes on Monday morning. Seventeen reports are available, generated by a four-pass analysis pipeline, priced from $10 to $45 per report. One offering, two surfaces.

Technical Reference

How the platform is accessed and integrated.

Access methods

GCP Marketplace console

The customer subscribes on Google Cloud Marketplace and lands on console.reach.dog through account linking. Agents are accessed via a chat surface in the browser. No install. No SDK. No local dependencies.

A2A JSON-RPC API

For API Access subscribers. Direct calls to https://rd-gap-agent-64739540958.us-east1.run.app/a2a/{agent_name} with API key authentication. Protocol: A2A JSON-RPC 2.0.

Agent Cards

Agent discovery follows the standard A2A specification. Cards are served at /.well-known/agent-card.json and /.well-known/agents.json on the agent service. Schema version: A2A v0.2.x / v0.3.

Plans and pricing

The Marketplace listing has two plans. Pay As You Go is visible to all customers. API Access is sales-led, activated through a private offer.

FeaturePay As You GoAPI Access
Six AI Agents (Router, Intent, Demand, Gap, Pricing, Campaign)YesYes
17 Lens Intelligence Reports (8 to 20 page consulting-grade reports)YesYes
Cross-Agent Router (multi-domain question routing)YesYes
Catalog Onboarding (URL scan or CSV upload)YesYes
Daily Free Recharge (10,000 tokens per 24 hours)YesYes
API Key Access (programmatic A2A JSON-RPC integration)NoYes
Dedicated Support (priority support channel)NoYes
Monthly base feeNone$10,000 / month, no contract

Lens Intelligence Reports

Seventeen reports cover the analytical surface of the platform: gap analysis, pricing intelligence, ghost product recovery, demand mapping, audience segmentation, content calendars, PPC campaign architecture, and more. Each report is generated by a four-pass pipeline that produces an executive summary, a detailed analysis with exhibits, a prioritized action plan, and an appendix. Page count ranges from 8 to 20 pages depending on report type.

For Marketplace billing, the seventeen reports are grouped into four metrics by price point. Internal accounting tracks the per-report cost; the customer invoice reports the bucketed metric.

Marketplace metricReports includedPrice per report
Catalog BriefCatalog Brief (orientation report)$10
Intelligence Report - StandardVoice Search, Demand Map, Market Audience, Modality Strategy$20
Intelligence Report - AdvancedGhost Products, Product Scorecard, Audience & Content, Market Overview, Market Gaps, Pricing Intelligence, Competitive Landscape, Competitor Pricing, Cannibalization, Content Calendar$30 (blended)
Intelligence Report - StrategicOpportunities, PPC Campaign Intelligence$45

The intelligence graph

The graph backing the agents was built from over 360 million product listings collected from more than 1.5 million online stores. Listings are organized into 29.6 million semantic clusters that group products by what they actually are, not by how they are categorized in any single merchant taxonomy.

On the demand side, the graph includes 101.3 million keywords and 70.5 million natural-language search questions, each analyzed for the meaning and intent they carry. The agents query this graph in real time through BigQuery and return responses with citations to the underlying rows. Every claim in an agent response is traceable to the data row that produced it.

Integration

Contact

Support and product questions: support@reach.dog.

API Access is sales-led and activated through a private offer on Marketplace. To request a private offer, email support@reach.dog with your Google Cloud billing account and expected monthly volume.