# IKAG

> IKAG (I Know A Guy) is building one connection that gives the AI apps and agents people already use paid tools and data they can’t reach on their own, such as lead data, AI video and web data, paid per call instead of a subscription to each service. IKAG is opening to early users and data partners first. Its first tool covers company legal identity from official registries.

- Name: IKAG, short for I Know A Guy
- Founder: Ronit Ahuja
- What it is: Pay-per-call tools and data for AI agents: one connection between the AI apps and agents people already use and the paid tools and data they cannot reach on their own. Not an AI model or an assistant: a service the AI you already use calls.
- What it will do: Let the AI apps and agents people already use call paid tools and data (lead and work contact data, AI video, web data, local business listings, social media data and company records) through one connection, paid per call instead of a subscription to each service, with each result returned with what it cost and where its data came from.
- Limits: Tools and sources can be wrong or out of date, so IKAG cannot promise an answer is right. It returns where each result came from; the assistant using it decides whether and how to show it.
- Status: Early access. IKAG is opening to early users and data partners first. Its first tool covers company legal identity from GLEIF, SEC EDGAR and Wikidata; lead data, AI video, web data and the other tools come next, and no provider is named until one is agreed.
- Who it is for: AI power users, vibe coders and anyone building AI apps, automations or agents, with or without code; developers; and data and API providers
- Ways it will reach tools and data: Public sources (the first tool), managed integrations with providers (each depends on an agreement with that provider) and your own provider keys
- Pricing direction: Pay per call, with no subscription to each service. Managed calls would be quoted before they run. With your own provider key, that provider’s plan and charges still apply, and IKAG may charge separately for its part. No prices have been published.
- Announced partners, customers or live integrations: None
- Website: ikag.dev
- Not to be confused with: Other businesses that use the names IKAG or I Know A Guy. IKAG at ikag.dev is not affiliated with them.
- Contact: hello@ikag.dev

The pages below are linked as Markdown. Each is also published as HTML at the same address without ".md" (the home page is https://ikag.dev/).

## Pages

- [Home](https://ikag.dev/index.md): What IKAG is building: pay-per-call tools and data for the AI apps and agents people already use (leads, AI video, web data and more), with an illustrative example, how it will work, why it helps, the pricing direction (pay per call, no subscription to each service; no prices yet), and common questions.
- [For builders](https://ikag.dev/agents.md): Real calls to the first tool, company legal identity, to try; then the request and result, seven real runs, rules, errors, limits, cost semantics and the interfaces it is reached through. Also how to describe IKAG.
- [Partners](https://ikag.dev/partners.md): For data and API providers: why partner with IKAG, what an early pilot involves, the rights agreed before any integration, and three ways to work together. Also how to enquire.

## Blog: Pay per call

The subscriptions you pay for and barely use, and what paying per call changes. Written by [Ronit Ahuja](https://ikag.dev/authors/ronit-ahuja), founder of IKAG. Each post opens with an overview and key points, and lists its sources.

- [Subscription fatigue: paying for tools you use twice](https://ikag.dev/blog/subscription-fatigue-tools-you-use-twice.md): Subscription fatigue in numbers: firms leave 36% of software licences unused on average, and UK consumers spend 1.6 billion pounds a year on unwanted subscriptions. (updated 2026-10-17)
- [Do you need a subscription for every AI tool?](https://ikag.dev/blog/do-you-need-a-subscription-for-every-ai-tool.md): Not one per AI app: a single account at a service can work in ChatGPT, Claude and Cursor. What adds up is a subscription to each service your AI uses. (updated 2026-10-17)
- [Pay per call vs monthly plans for AI tools](https://ikag.dev/blog/pay-per-call-vs-monthly-plans-for-ai-tools.md): Monthly plans suit steady use and pay per call suits bursts. How they compare for AI tools: quotes before a call, spending limits, receipts and your own keys. (updated 2026-10-17)

## Blog: AI agents and tools

What today’s AI agents can do, how they connect to tools, and how to set them up.

- [ChatGPT Dots, Grok Bot and Meta Muse explained](https://ikag.dev/blog/chatgpt-dots-grok-bot-meta-muse-explained.md): ChatGPT Dots, Grok Bot and Meta’s Muse are AI agents with their own cloud computers. What each one does, who can get it and what none of them can reach. (updated 2026-10-17)
- [How to add a tool to ChatGPT, Claude and Gemini](https://ikag.dev/blog/how-to-add-a-tool-to-chatgpt-claude-gemini.md): Step by step: add a custom connector or MCP server in ChatGPT, Claude, Gemini, Cursor, VS Code, Claude Code and Codex, with plan limits as of October 2026. (updated 2026-10-17)
- [What is MCP? A plain-English guide for AI users](https://ikag.dev/blog/what-is-mcp-plain-english-guide.md): MCP, the Model Context Protocol, lets ChatGPT, Claude, Gemini and other AI apps use outside tools. What it is, how connecting works and how to stay safe. (updated 2026-10-17)
- [Tool routers and data networks: what agents need](https://ikag.dev/blog/tool-routers-and-data-networks-for-ai-agents.md): Two ways to connect AI agents to outside data: a router that offers many paid tools behind one key, and a data network that returns the record behind each value. (updated 2026-10-15)
- [How AI agents get live data and tools, and how to choose](https://ikag.dev/blog/how-ai-agents-get-live-data.md): Search, page extraction, specialist data APIs, generation models and MCP: how an AI agent reaches the outside world, with a worked example on real records. (updated 2026-10-10)
- [What to ask before you connect an agent to a data gateway](https://ikag.dev/blog/questions-before-you-connect-an-agent.md): Eight questions for any agent data gateway, applied to IKAG in early access: provenance, failures, routing, cost, own keys, retention, terms. (updated 2026-10-10)
- [What is an intelligent data network for AI agents?](https://ikag.dev/blog/what-is-an-intelligent-data-network.md): What IKAG, in early access, means by an intelligent data network for AI agents, and how it compares with single APIs, marketplaces and MCP servers. (updated 2026-10-10)

## Blog: Data your AI can call

Leads, AI video, local businesses, social media and the web, without a plan for each.

- [Bulk AI video without a subscription: what to know](https://ikag.dev/blog/bulk-ai-video-without-a-subscription.md): How AI video is sold in 2026, from monthly credits to per-second API pricing, how to make 20 ad takes without a plan, and the quality, rights and labelling checks. (updated 2026-10-17)
- [How AI agents find B2B leads, and what to check](https://ikag.dev/blog/how-ai-agents-find-b2b-leads.md): Where an AI agent’s list of businesses and decision makers comes from, why models alone get work emails wrong, the UK and US email rules, and what a good list includes. (updated 2026-10-17)
- [Local business data for AI agents: sources and rules](https://ikag.dev/blog/local-business-data-for-ai-agents.md): How an AI agent can list local businesses with ratings, reviews, websites and opening hours: map platforms, open data and business websites, their terms and freshness. (updated 2026-10-17)

## Blog: Answers you can check

Where an answer comes from, what its source record holds, and how to check it.

- [Do AI summaries send people to their sources?](https://ikag.dev/blog/do-ai-summaries-send-people-to-sources.md): Pew Research found Google users clicked a result in 8% of visits with an AI summary and 15% without. What that means for answers you need to check. (updated 2026-10-15)
- [How to look up a company’s LEI with an AI agent](https://ikag.dev/blog/how-to-look-up-a-company-lei-with-an-ai-agent.md): What a Legal Entity Identifier is, how an AI agent should query the GLEIF register, and why “no match” or “lapsed” never means a company is gone. (updated 2026-10-15)
- [LEI, CIK or Wikidata ID: which company identifier?](https://ikag.dev/blog/lei-cik-wikidata-company-identifiers-for-ai-agents.md): A practical guide for agents and developers: what LEIs, SEC CIKs and Wikidata IDs identify, who issues them, how to resolve each, and when to link them. (updated 2026-10-15)
- [What should the source record behind an AI answer contain?](https://ikag.dev/blog/what-the-source-record-behind-an-ai-answer-contains.md): Seven parts that make an AI answer checkable, from the source and record ID to attestation dates and unknowns, shown on seven real company lookups. (updated 2026-10-15)
- [How to check where an AI answer came from](https://ikag.dev/blog/how-to-check-ai-answers.md): A five-step check for any AI answer, worked through on real public records, and what good provenance looks like when you need to rely on a fact. (updated 2026-10-10)
- [What IKAG’s first capability does, and won’t do](https://ikag.dev/blog/what-our-first-capability-does.md): Seven offline requests to IKAG’s first capability, in early access: what it answers, what it leaves unknown, and why a shared name never joins two records. (updated 2026-10-10)

## Optional

- [Pages and posts in one file](https://ikag.dev/llms-full.txt): The home, developer and partners pages and every post above, as one Markdown file. The privacy notice is not included.
- [Company facts as JSON](https://ikag.dev/facts.json): Status, the first capability and its captured records, the pricing direction and links.
- [Blog feed](https://ikag.dev/blog/rss.xml): RSS 2.0, newest first.
- [Contact](https://ikag.dev/contact): Who to contact about what: early access, partner enquiries from data and API providers, builders and questions about your information. (HTML only.)
- [Privacy notice](https://ikag.dev/privacy): What the website collects, why, how long it is kept, and your rights. (HTML only.)
- [Terms of use](https://ikag.dev/terms): The terms for using the website: what it offers, how you may use its content, links to other sites and the limits of what we promise. (HTML only.)