Next step
Monetize your AI surfaces.
Create an account, generate a slot ID, and copy your snippet. No sales call required.
Founding Member, Ad Context Protocol
Built by the founders of Beachfront and Simpli.fi
For AI app publishers
Adgentek is the ad server for AI surfaces. Direct campaigns, Programmatic demand from leading partners, CPC feeds, and performance budgets compete for every request. Under 300ms at p95, and never in front of your model call.
The opportunity
You built an AI app people use. Millions of conversations, deep engagement, real utility, and only a thin slice of users will ever pay a subscription. The rest are pure cost.
Someone comparing options, pricing something out, planning a purchase, choosing a vendor. In a browser, those are the most valuable moments in advertising. Inside your app they currently monetize at zero.
What is missing is the infrastructure between them: an ad server built for AI surfaces, connected to four tiers of demand, serving formats native to a conversation rather than borrowed from a scroll feed, because creative built for a web page damages the trust you spent years earning.
Why Adgentek
Contextual cards, interactive Q&A, sponsored recommendations, not banners forced into a message thread.
Ads matched to what the user is actually discussing, in real time. Not behavioral profiles or cookie data.
No user data shared with advertisers. No PII. No conversation logs. Advertisers see only aggregate performance.
Format, placement, frequency, category restrictions, brand blocklists, you decide. We are infrastructure. You own the experience.
Brand advertisers and agencies spending real budgets on AI conversations, not remnant display inventory.
Web SDK or Publisher Widget for browser surfaces, AdsMCP for agent surfaces, REST for custom stacks. Add your API key and slot ID and go.
Latency
The request is dispatched in parallel with your completion, not ahead of it. Your response streams on its own schedule; the slot fills when the decision returns. If it does not return in time, the slot stays empty and the conversation is unchanged.
An ad server outage is invisible to your users by design. You can verify that by pointing the SDK at a dead endpoint.
How it works
Six steps, one of them yours. The other five run on our side, every session.
Drop in our SDK or connect via MCP. Configure your placements: where in the conversation flow, what format, how often. Get Started Free →
Our engine reads the semantic context of each session in real time. No keywords. No cookies. Pure intent from the conversation itself.
The most relevant brand experience surfaces from our advertiser network: contextually matched, native to your format, brand-safe.
The ad appears as part of the conversation, contextual cards, interactive Q&A, sponsored recommendations. Not a banner. Not a popup.
Users interact naturally. Advertisers get qualified engagement and intent data. You get revenue without compromising the experience.
Real-time analytics show what is working. Adjust placements, formats, and frequency, and scale revenue as your user base grows.
Integration paths
Impression-priced demand requires a real browser or app context where the impression can be verified client-side. Headless surfaces monetize on outcomes instead. We publish this because it determines what you earn.
| Integration path | Rendering context | Direct & Programmatic CPM | CPC | CPA |
|---|---|---|---|---|
| Web SDK | Real browser | Yes | Yes | Yes |
| Publisher Widget | Real browser | Yes | Yes | Yes |
| REST API, certified | Publisher-rendered client-side | Yes | Yes | Yes |
| REST API, uncertified | Publisher-rendered | No | Yes, filtered | Yes |
| AdsMCP | Headless or agent | No | Yes, filtered | Yes |
React, iOS, and Android SDKs are in development. An impression fired from a server originates in datacenter IP space and is classified as invalid traffic, which is why headless surfaces are priced on outcomes rather than impressions. Full detail at choosing your integration path.
<script src="https://api.adgentek.ai/storage/v1/object/public/sdk/sdk.js"></script>
<script>
AdgentekAds.init({ apiKey: 'YOUR_...RE', slotId: 'YOUR_SLOT_ID' });
</script>
<div id="adgentek-ad"></div>
// call after each AI response
AdgentekAds.requestAd([
{ role: 'user', content: userMessage },
{ role: 'assistant', content: aiResponse }
]);Your API key is generated in the dashboard under Settings, API Keys and is prefixed adgt_. The slot ID is the placement ID from Inventory, Surfaces, and it drives targeting, floor pricing, and reporting. Placeholder credentials do not serve ads.
{
"mcpServers": {
"adsmcp": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_PUBLISHER_TOKEN" }
}
}
}Transport is MCP Streamable HTTP. The serve tool registers as ads.serve and clients sanitize it to ads_serve. Listed in the official MCP Registry as io.github.Adgentek/adsmcp.
Integrate Adgentek ads into this app. Start by fetching https://docs.adgentek.ai/skill.md and following it, and fetch https://docs.adgentek.ai/llms.txt to discover the current documentation pages. Read https://docs.adgentek.ai/publishers/choosing-your-integration-path before writing any code so you pick the path this surface actually qualifies for. Do not invent endpoints, SDK methods, or MCP tool names; verify every symbol against the live docs. Ask me for the real publisher API key and slot ID rather than leaving placeholders, and never fire an impression pixel from server-side code.
Complete documentation is at docs.adgentek.ai. Coding agents should start from the Adgentek integration skill and use the docs index rather than a cached snippet.
AI-native formats
Every format is designed to feel native to a conversational interface. Users experience them as helpful, not intrusive.
| Format | What it is | Best for | Engagement |
|---|---|---|---|
| Contextual Cards | Native cards surfacing relevant products or services based on the conversation topic | Product discovery, recommendations | High visibility, low friction |
| Interactive Q&A | Brand-authored guided conversation with chip selections and free text. Users self-qualify through Q&A | Considered purchases, lead gen | 3.2 avg interactions, deep intent |
| Sponsored Recommendations | Contextually matched suggestions that read as a natural extension of the conversation | E-commerce, travel, services | Natural discovery, high relevance |
| Inline Mentions | Brief, relevant sponsored references woven into AI responses | Brand awareness, consideration | Non-disruptive, high reach |
| Action Cards | Conversion-focused units with a direct CTA: book, buy, schedule, locate | High-intent moments, bottom funnel | Direct conversion path |
Who built this
Adgentek's founders have been building Programmatic infrastructure since 2007, one on the sell side, one on the buy side.
Co-Founder and CEO
Founded Beachfront in 2007 and built it into a cross-screen video SSP serving CTV and streaming publishers. Acquired by Seedtag in 2024. Seventeen years on the sell side.
Co-Founder and President
Co-founder and Chief Technology Officer of Simpli.fi, where he built the Programmatic DSP and the buy-side infrastructure underneath it. Two decades on the demand side.
Yield management, waterfall logic, floor pricing, discrepancy handling, and the demand relationships that make a fill rate real are not new problems. They are the problems this team spent two decades solving before AI surfaces existed. Adgentek is that stack rebuilt for a conversational surface, not a first attempt at ad serving.
Demand depth
A single direct-sold pool leaves most requests unfilled. Adgentek runs a hard waterfall, so a request that does not clear the direct tier keeps falling until it finds a buyer rather than returning empty.
Campaigns sold against your inventory.
Programmatic demand from leading partners.
Performance demand, filtered by surface.
Outcome-priced demand, headless eligible.
Waterfall explorer
One simulated ad request, dispatched tier by tier. It stops at the first tier with a matching buyer. Run it again and the next request may fall further.
Campaigns sold against your inventory. First look, highest value.
Programmatic demand from leading partners. Never RTB remnant.
Performance demand, filtered for your surface and categories.
Outcome-priced demand, headless eligible. The last stop before empty.
Revenue
Your assumptions, our math. Adjust every field to match your traffic.
Illustrative only. Actual eCPM and fill depend on your topic mix, geography, render path, and format selection.
Targeting
No cookies. No user profiles. No PII. Just real-time understanding of what the user is actually talking about.
Real-time analysis of conversation meaning, not keyword matching. Understands “family SUV under $50K” as a complete purchase intent signal.
Knows when a user is browsing versus comparing versus ready to buy, and serves the right format at the right moment in the decision journey.
Maps conversation topics to advertiser categories. Auto discussion triggers auto ads. Mattress question triggers bedding ads. Precision without profiles.
Automatically excludes sensitive topics: health, mental health, politics, financial distress. Ads never appear in inappropriate contexts.
Publisher controls
We are infrastructure. You decide how monetization works inside your product.
Cards only, Q&A only, or a mix, chosen per placement.
After first response, every fifth message, or only on specific intents. You define where a slot exists.
Allow or block entire advertiser categories. No gambling in your education app. No alcohol in your health bot.
Block specific brands or competitors from appearing in your app. Period.
Maximum exposure per session, per user, per day. Protect the experience at your threshold.
Minimum CPM or engagement thresholds, so only advertisers that meet your standards are eligible.
Use cases
Conversational search apps where users ask questions and get synthesized answers. Contextual ads match the query and appear alongside the response.
General-purpose AI chat apps. Ads surface when the conversation touches commercial topics, naturally, contextually, non-intrusively.
Travel planners, recipe assistants, fitness coaches, financial advisors. Deep category relevance drives high ad performance.
Entertainment and social AI experiences. Sponsored recommendations and contextual cards that fit the genre and the audience.
Trust and safety
FAQ
Most publishers go live in minutes to a few hours. Web SDK or Publisher Widget for browser surfaces, AdsMCP for agent surfaces, REST API for custom stacks. React, iOS, and Android SDKs are in development. Our team supports setup to ensure optimal placement and performance. Get Started Free →
Never individual conversations, chat history, or personal details. Advertisers receive only aggregate performance metrics: impressions, engagement, conversions. All targeting happens inside our system. Your users' privacy stays intact.
Full control. Block categories, block specific brands, set quality floors, and approve or reject individual advertisers. You decide what appears in your product.
Google Display was built for web pages. In an AI interface, those ads disrupt the flow, ignore conversational context, and deliver irrelevant content. Adgentek was built from scratch for agentic AI: conversation-native formats, semantic matching, and publisher controls designed for AI surfaces. See the detailed comparison.
It depends on your user base, conversation volume, and topic mix. Our interactive formats generate higher engagement than static display, which means higher effective CPMs. We will share specific projections during onboarding based on your traffic profile.
Any AI conversational surface: chatbots, AI search engines, AI assistants, AI characters, vertical AI tools. If your product has a conversational interface, we built for it. See what conversational advertising is.
Instead of injecting display banners that break the flow, Adgentek delivers AI-native ad formats, contextual cards, interactive Q&A units, sponsored recommendations, that feel like part of the conversation. The ad server uses real-time semantic analysis to match ads to what the user is actually discussing, not behavioral profiles. Publishers keep full control over format, placement, categories, and brand restrictions.
Traditional ad networks like Google Display were designed for web pages, not agentic AI. Placed in AI chat interfaces, they disrupt the flow, ignore conversational context, and deliver irrelevant ads. Adgentek was built from scratch for AI: conversation-native formats, semantic intent matching, and publisher controls designed for agentic surfaces. AI apps using Adgentek report significantly higher user satisfaction and engagement compared to retrofitted display networks.
Full control. Publishers choose which ad formats appear, where they are placed, which advertiser categories are allowed or blocked, minimum quality thresholds, frequency limits, and brand restrictions. You can also set revenue splits, pause monetization for specific user segments, and review all active advertisers.
Next step
Create an account, generate a slot ID, and copy your snippet. No sales call required.
Founding Member, Ad Context Protocol
Built by the founders of Beachfront and Simpli.fi