canonical: https://jentic.com/apis/deepsearch.app/deepsearch # Deepsearch App DeepSearch API The DeepSearch API researches a person's public online footprint for AI agents and applications. It looks someone up by name, phone, email, or username, builds a sourced dossier of social accounts, contact details, work history, relatives, and web mentions, and answers follow-up questions about them. It also searches companies, builds company profiles, decodes a vehicle by VIN, and runs reverse-image lookups, with async jobs and a public sandbox for testing. The research endpoints are authenticated with a bearer API key, while discovery, health, and sandbox endpoints need no credential. ## For AI agents Look up people by name, phone, email, or username, build sourced dossiers, run reverse-image and company lookups, and ask follow-up questions. Research endpoints use a bearer API key; several discovery endpoints need no credential. ## Scope Does not handle private or non-public records, background-check adjudication, or identity verification decisions. Use for researching a person's public online footprint only. ## Capabilities - Look up a person by name, phone, email, or username - Build a sourced dossier of social accounts, contact details, work history, and web mentions - Ask follow-up questions about a researched person - Run reverse-image lookups to find where an image appears online - Search companies and build a company profile, and decode a vehicle by VIN - Run up to 10 operations in one batch request and track them as async jobs ## Use cases ### Public-Footprint Dossier A due-diligence agent researches an individual from a single identifier. It looks the person up by email or username, builds a sourced dossier of social accounts, contact details, work history, and web mentions, and asks follow-up questions to fill gaps, keeping to public information only. Example prompt: Call POST `/api/v1/search` to find the person, then POST `/api/v1/dossier` to build their sourced profile ### Reverse-Image Investigation An agent investigating a profile photo runs a reverse-image lookup to find where the image appears online and which visually similar images exist. Paired with a person lookup, this corroborates or challenges an identity claim from public sources. Example prompt: Call POST `/api/v1/reverse-image` with the image, then POST `/api/v1/search` to corroborate the identity ### Batched Research as Async Jobs To research many subjects at once, an agent submits up to 10 operations in a single batch and tracks them as async jobs. It lists jobs, fetches a job by id, replays its events, and cancels an account-owned job that is no longer needed, so large research runs proceed without blocking. Example prompt: Call POST `/api/v1/batch` with up to 10 operations, then GET `/api/v1/jobs/{id}` to fetch each job's result ### AI Agent Integration via Jentic An AI agent reaches the DeepSearch API through Jentic without wiring the bearer key itself. It searches by intent, receives the matching operation and its input schema, and executes with the credential injected at run time, chaining a lookup into a dossier and follow-up questions in one research flow. Example prompt: Search Jentic for 'look up a person by email', load the POST `/api/v1/search` schema, and execute it with Jentic-managed credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/api/v1/search` | Find people by name, phone, email, or username | | POST | `/api/v1/dossier` | Build a full public-footprint profile for a person | | POST | `/api/v1/chat` | Ask follow-up questions about a person | | POST | `/api/v1/reverse-image` | Find where an image appears online | | POST | `/api/v1/entity/search` | Find companies by name | | POST | `/api/v1/vin` | Decode a vehicle by VIN | | POST | `/api/v1/batch` | Run up to 10 operations in one request | | GET | `/api/v1/jobs` | List async jobs, newest first | ## Key resources - **People research** — Search, dossier, chat, and reverse-image lookups under `/api/v1` - **Entities** — Company search and company dossier under `/api/v1/entity` - **Async jobs** — Create, list, fetch, replay, and cancel research jobs under `/api/v1/jobs` - **Platform** — Public index, health, sandbox, and developer status endpoints ## 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:** 56 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 83 / 100 - Developer Experience & Jentic Compatibility: 61 / 100 - AI-Readiness & Agent Experience: 32 / 100 - Agent Usability: 94 / 100 - Security: 60 / 100 - AI Discoverability: 88 / 100 - **View full report:** https://jentic.com/apis/deepsearch.app/deepsearch/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 DeepSearch by hand means sending its bearer API key on research endpoints, leaving the public discovery and sandbox endpoints unauthenticated, and polling async jobs yourself. Through Jentic you install once, import DeepSearch from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** A rule can confine your agent to the research operations it needs, such as person search and dossier building, because job cancellation and company research are separate operations you choose to include. Those stay out of reach unless you grant them. - **Credential handling:** Your DeepSearch 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 'look up a person by email' or 'build a dossier', and Jentic returns the matching DeepSearch operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **People Data Labs** — Person and company datasets for enrichment and lookup - **FullContact** — Identity resolution and person enrichment from an email or profile - **RocketReach** — Find professional emails and phone numbers for a person - **Hunter** — Email finder and verifier for a domain ## FAQ ### What authentication does the DeepSearch API use? The research endpoints authenticate with a bearer API key created in the developer portal, per the OpenAPI spec, while discovery, health, and sandbox endpoints need no credential. The sandbox exposes a public test key for trialling the flow. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time. ### What identifiers can I look someone up by with the DeepSearch API? The search endpoint accepts a name, phone, email, or username and returns matching people from public sources. From a match an agent can build a sourced dossier and ask follow-up questions, all limited to public information. ### Can I run many research lookups at once with the DeepSearch API? Yes. The batch endpoint runs up to 10 operations in one request, and results can be tracked as async jobs that an agent lists, fetches by id, and cancels. Cached results and idempotent replays are not re-billed, so repeated reads are efficient. ### How do I look up a person through Jentic with the DeepSearch API? Search Jentic for 'look up a person by email', and it returns the DeepSearch search operation with its input schema. Load the schema and execute POST `/api/v1/search` with the credential injected at run time. 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 DeepSearch API? Yes. Write a rule that allows only the research operations the agent needs, such as person search and dossier building, while leaving out job cancellation or company research unless you add them. Each call runs through your own instance and is logged for review.