canonical: https://jentic.com/apis/klarix.ai/klarix # Klarix Intelligence API The Klarix Intelligence API produces competitive and account intelligence for sales teams from public web sources, with a resolvable source URL on every factual claim. It writes competitor battlecards, head-to-head analyses, SWOTs, market landscapes, and displacement playbooks, scores a prospect's ICP fit on five axes, maps buying committees, detects account triggers such as funding or leadership changes, and tears down a company's tech stack. A semantic prospect search returns ranked lookalike accounts, and responses contain no emails, phone numbers, or licensed contact rows. ## For AI agents Generate cited battlecards, SWOTs, ICP fit scores, account trigger reports, tech-stack teardowns, and lookalike prospect lists from public web sources with Klarix. ## Scope Does not return contact emails or phone numbers, send outreach, or store CRM records. Use for cited competitive, account, and prospect research only. ## Capabilities - Write a competitor battlecard with SWOT, positioning seams, landmines, and talk tracks from a competitor_domain - Score a prospect's ICP fit on five axes with a 7+/10 pursue threshold and cited rationales - Search pre-profiled B2B companies for lookalike prospects with filters such as headcount, revenue, countries, and required_tech - Detect account triggers like leadership changes, funding, and hiring surges within a chosen timeframe_days - Tear down a target account's tech stack, cloud providers, and AI/data stack to find displacement openings - Map an account's buying committee with title patterns, pain points, and objections - Find peer-reviewed and preprint papers from Semantic Scholar and arXiv on a topic ## Use cases ### AI agent sales research through Jentic A sales agent preparing for a call searches Jentic for 'build a competitor battlecard', loads the Klarix battlecard operation with its input schema, and passes the competitor_domain plus your own company details. Your own Jentic One instance injects the Klarix key at call time, and every claim in the returned battlecard carries a source URL the rep can check. Example prompt: Call POST `/v1/intelligence/battlecard` with competitor_domain 'competitor.com', our_company_name 'Acme', and our_domain 'acme.com', then summarise the landmines and talk tracks ### ICP fit scoring before outreach Before a rep invests time, the agent scores the account on five ICP axes from 1 to 10 with cited rationales, using company_name and domain plus your icp_description. Accounts at or above the 7/10 pursue threshold go into an outreach sequence that opens on a researched, dated fact and writes to a role rather than a named person. Example prompt: Call POST `/v1/intelligence/prospect-fit` with company_name 'Globex' and domain 'globex.com'; if the score passes the pursue threshold, call POST `/v1/intelligence/outreach` with buyer_role 'VP Engineering' ### Lookalike prospect discovery A team expanding into a new segment describes its ideal customer in plain language and filters by headcount, revenue, countries, and required_tech. The prospect match operation returns ranked accounts with their tech stack, growth signals, and a suggested next move, and can exclude domains already in the pipeline. Example prompt: Call POST `/v1/prospects/match` with icp_or_query 'mid-market logistics SaaS using Snowflake', countries ['US'], and exclude_domains from the current pipeline ### Account trigger monitoring An account team checks named accounts for inflection points such as leadership changes, funding, hiring surges, product updates, or regulatory events within a set number of days, then pulls a tech-stack teardown for any account that shows a trigger. Example prompt: Call POST `/v1/intelligence/triggers` with target_domain 'initech.com' and timeframe_days 90, then POST `/v1/intelligence/tech-stack` for the same domain if any trigger is found ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/intelligence/battlecard` | Competitor battlecard | | POST | `/v1/intelligence/prospect-fit` | 5-axis ICP fit score | | POST | `/v1/prospects/match` | Semantic lookalike prospect search | | POST | `/v1/intelligence/triggers` | Detect account triggers | | POST | `/v1/intelligence/tech-stack` | Tech-stack teardown | | POST | `/v1/intelligence/company` | Company one-pager from cited sources | | GET | `/v1/whoami` | Key, plan, credits, and callable tools | ## Key resources - **Competitive intelligence** — Battlecards, head-to-head analyses, SWOTs, market landscapes, and displacement playbooks - **Account intelligence** — Company one-pagers, deep research, buying committees, account triggers, and tech-stack and product-spec teardowns - **Prospecting** — Lookalike prospect search, ICP fit scoring, and outreach sequences - **Utility** — Key and plan check, health status, and the tool listing ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 65 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 99 / 100 - Developer Experience & Jentic Compatibility: 67 / 100 - AI-Readiness & Agent Experience: 47 / 100 - Agent Usability: 94 / 100 - Security: 55 / 100 - AI Discoverability: 60 / 100 - **View full report:** https://jentic.com/apis/klarix.ai/klarix/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring Klarix by hand means choosing between bearer and X-Api-Key auth, tracking which operations need a PRO plan, and passing your own company context on every request. Through Jentic you install once, import Klarix from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** Klarix carries its targets, such as competitor_domain and target_domain, in the request body, so limit the agent to the operations it needs, such as battlecards and fit scores. Rules bound which operations your agent may call, not which company it researches, so credit-spending operations you have not picked are not included unless you add them. - **Credential handling:** Your Klarix key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'build a competitor battlecard' or 'find lookalike prospects', and Jentic returns the matching Klarix operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **BuiltWith API** — Website technology detection and lead lists by technology - **Clearbit API** — Company and person enrichment by domain or email - **Apollo API** — B2B contact database and sales engagement ## FAQ ### What authentication does the Klarix Intelligence API use? Per its OpenAPI spec, the Klarix Intelligence API accepts the same Klarix key either as a bearer token in the Authorization header or in the X-Api-Key header, for callers behind a proxy that strips Authorization. Keys on the query string are rejected. GET `/v1/health` and GET `/v1/tools` are open, and GET `/v1/whoami` works with or without a key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time. ### Does every Klarix call cost credits? The intelligence and prospect operations each spend one credit per call, and some need a minimum plan: the battlecard works on FREE, while prospect match and prospect fit need PRO. GET `/v1/whoami` shows your plan, remaining credits, and the tools your key can call. ### What are the rate limits for the Klarix Intelligence API? The OpenAPI spec does not specify rate limits. Check the Klarix documentation at https://klarix.ai/docs/api for current limits. ### Is there a Klarix MCP server? You don't need an MCP server to give your agent the Klarix Intelligence API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the battlecard, prospect, and research operations on demand without loading another server's tool definitions into its context. ### Can I limit what my agent is allowed to do with the Klarix Intelligence API? Yes. For example, write a rule that allows only POST `/v1/intelligence/battlecard` and GET `/v1/whoami`, so the agent can produce battlecards and check remaining credits but cannot run PRO-plan prospect searches that spend credits elsewhere. Every call it makes through your instance is logged. ### How do I score a prospect's ICP fit through Jentic? Search Jentic for 'score prospect fit', load the Klarix prospect fit operation, and call POST `/v1/intelligence/prospect-fit` with the required company_name and domain, plus an icp_description if you have one. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Does the Klarix Intelligence API return contact details? No. Klarix works from public web sources and returns no emails, phone numbers, or licensed contact rows. Buying committee maps and outreach sequences describe roles and title patterns, not named people.