canonical: https://jentic.com/apis/epovest.com/epovest # Epovest API The Epovest API measures how AI assistants such as ChatGPT, Claude, Gemini, Perplexity, and Grok answer the questions a market asks about a brand, and gives teams the levers to shape those answers. Trackers run scheduled surveys across engines and return a score series, the raw engine responses, and discovered keyword suggestions, while projects hold the brand canon and a registry of the surfaces and corroborating pages an engine cites. Competitor scans, a source Atlas, and a project logbook round out the workflow for monitoring and improving AI visibility. Access uses a bearer API key, and each operation declares the read or write scope it needs. ## For AI agents Measure and improve a brand's visibility in AI assistant answers with Epovest: run trackers that survey engines like ChatGPT and Perplexity, read score series and keyword discoveries, and manage the surfaces and corroborations those engines cite. ## Scope Does not handle paid ad buying, content publishing, or web analytics traffic reporting. Use for measuring and improving a brand's visibility in AI assistant answers only. ## Capabilities - Create trackers and run surveys across AI engines via /trackers and `/trackers/{id}/survey` to measure how they answer about a brand - Read the score series and raw engine responses for a tracker via `/trackers/{id}/scores` and `/trackers/{id}/responses` - Review discovered keyword suggestions with `/trackers/{id}/discoveries` and accept, dismiss, or restore them - Maintain a project's brand canon and surface registry via `/projects/{id}/canon` and `/projects/{id}/surfaces` - Record and verify corroborating pages an engine cites through `/projects/{id}/corroborations` and `/corroborations/{id}/verify` - Prepare and arm competitor scans via /competitor-scans and `/competitor-scans/{id}/start` - Track the prepaid credit balance and account usage via /credits and /usage ## Use cases ### AI agent brand-visibility monitor An AI assistant keeps an eye on how generative engines talk about a brand so a marketer gets alerted when the score moves. Through Jentic it creates a tracker, triggers surveys, and reads the score series back, surfacing drops without anyone opening the dashboard. Jentic injects the Epovest key at call time, so the agent never holds it. Example prompt: Search Jentic for 'measure how AI assistants describe my brand', create a tracker with POST /trackers, trigger a run with POST `/trackers/{id}/survey`, then read GET `/trackers/{id}/scores` ### Tracking AI answer scores over time Teams want a trend line for how often and how favourably AI engines cite their brand against rivals. Epovest trackers survey the configured engines on a schedule and expose a score series plus the raw engine responses, so a reporting job can chart movement and drill into the exact wording an engine returned. This turns ad-hoc spot checks into a measurable series. Example prompt: Read GET `/trackers/{id}/scores` for the trend and GET `/trackers/{id}/responses` to inspect the raw answers one engine returned for a survey ### Acting on keyword discoveries Epovest discovers new questions and keyword suggestions a brand is being asked about, and a team needs to triage them into the tracker. The discoveries endpoint lists the suggestions, and accept, dismiss, and restore actions let an agent curate which ones feed future surveys. That keeps the measured question set aligned with what the market actually asks. Example prompt: List suggestions with GET `/trackers/{id}/discoveries`, then promote the useful ones with POST `/trackers/{id}/discoveries/accept` ### Competitor AI-visibility scan Before building a tracker, teams want to see which competitors AI engines surface for a set of questions. A competitor scan is prepared as a draft, then armed to run, and the result accumulates the places engines pointed to. An agent can prepare the scan, start it, and read back the accumulated list to decide what to monitor. Example prompt: Prepare a scan with POST /competitor-scans, arm it with POST `/competitor-scans/{id}/start`, then read GET `/competitor-scans/{id}` for the accumulated places ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/trackers` | Create a tracker | | POST | `/trackers/{id}/survey` | Run a survey now | | GET | `/trackers/{id}/scores` | Read the score series | | GET | `/trackers/{id}/discoveries` | List discovered keyword suggestions | | POST | `/projects` | Create a project | | GET | `/projects/{id}/corroborations` | List the corroboration registry | | POST | `/competitor-scans` | Prepare a competitor scan | | GET | `/credits` | Read the prepaid credit balance | ## Key resources - **Trackers** — Create and run the surveys that measure AI engine answers, with score series, raw responses, and keyword discoveries - **Projects** — Hold the brand canon, link targets, surface registry, corroborations, and the project logbook - **Surfaces and corroborations** — Register the pages that represent the brand and the corroborating pages engines cite, with verify and convert actions - **Competitor scans** — Prepare and arm scans that accumulate where AI engines surface competitors - **Account, credits and usage** — Read and change account settings, the prepaid credit balance, and what the account has spent ## 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:** 63 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 60 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 51 / 100 - Agent Usability: 91 / 100 - Security: 60 / 100 - AI Discoverability: 61 / 100 - **View full report:** https://jentic.com/apis/epovest.com/epovest/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 the Epovest API by hand means managing its bearer key, honouring the read and write scope each operation declares, and polling tracker surveys and scores yourself. Through Jentic you install once, import Epovest from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** Epovest puts each resource id in the URL path, such as `/trackers/{id}` and `/projects/{id}`, so a rule can pin your agent to the trackers and projects it manages and the read operations like scores and discoveries. You choose the operations it may call, so write actions like deleting a surface or topping up credits are not included unless you add them. - **Credential handling:** Your Epovest API 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 'measure how AI assistants describe my brand' or 'start a competitor scan', and Jentic returns the matching Epovest operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Citability API** — Also measures how AI answer engines cite a brand and its sources - **Botify API** — Enterprise search-engine optimization platform focused on traditional web search crawl and indexing - **Ahrefs API** — Backlink, keyword, and organic-search data that pairs with AI-answer visibility tracking ## FAQ ### What authentication does the Epovest API use? The Epovest API authenticates with a bearer API key whose secret begins with epo_, per its OpenAPI spec, and each operation declares whether it needs the read or write scope. When you call it through Jentic, the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt, logs, or context. ### Can I measure how AI assistants describe my brand with the Epovest API? Yes. Create a tracker with POST /trackers, start the measurement, and trigger a survey with POST `/trackers/{id}/survey`, then read GET `/trackers/{id}/scores` for the score series and GET `/trackers/{id}/responses` for the raw answers each engine returned. Trackers survey engines such as ChatGPT, Claude, Gemini, Perplexity, and Grok. ### Can the Epovest API suggest new keywords to track? Yes. Read GET `/trackers/{id}/discoveries` to see the keyword suggestions Epovest discovered for a tracker, then curate them with POST `/trackers/{id}/discoveries/accept`, POST `/trackers/{id}/discoveries/dismiss`, and POST `/trackers/{id}/discoveries/restore` so future surveys follow the questions that matter. ### What are the rate limits for the Epovest API? The OpenAPI spec does not pin a rate-limit figure in a machine-readable field. Check the Epovest documentation at https://epovest.com/docs for current limits, and have your agent retry with backoff when the API signals that it is being throttled. ### How do I set up brand-visibility tracking through Jentic? Search Jentic for 'measure how AI assistants describe my brand' to load the tracker operations with their input schemas, create a tracker with POST /trackers, and trigger a survey with POST `/trackers/{id}/survey.` To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Can I limit what my agent is allowed to do with the Epovest API? Yes. Epovest puts each resource id in the URL path, such as `/trackers/{id}` and `/projects/{id}`, so a rule can pin your agent to the trackers and projects it manages and to read operations like scores and discoveries. Write and spend actions, such as deleting a surface with DELETE `/surfaces/{id}` or topping up credits, stay out unless you add them, and every call the agent makes is logged.