canonical: https://jentic.com/apis/fodda.ai/fodda # Fodda Context & Research API The Fodda Context & Research API returns expert-curated knowledge graphs, brand and expert intelligence profiles, and autonomous research results, so an application can ground answers in structured, cited context instead of raw web text. You search and traverse knowledge graphs, launch a deep-dive research job or a streaming research search, and pull brand, domain, and expert intelligence along with earnings-call analysis. Supplemental endpoints add public-source snapshots from agencies such as the FDA, FRED, the Census, and clinical-trials registries, each returned with evidence you can trace. ## For AI agents Search knowledge graphs, launch autonomous research jobs, and pull brand, expert, and earnings intelligence with cited evidence in Fodda. Authenticates with an API key in the X-API-Key header, with a Stripe payment token as a bearer token on metered endpoints. ## Scope Does not host documents, train models, or execute trades. Use for curated knowledge-graph, research, and intelligence retrieval only. ## Capabilities - Search and traverse expert-curated knowledge graphs and fetch node properties - Launch an autonomous research deep-dive and poll its status, or run a streaming research search - Pull a brand intelligence profile and domain or expert intelligence for a subject - Read earnings-call snapshots, analyst concerns, and management themes - Retrieve evidence and source chunks that back a returned figure - Fetch public-source snapshots from the FDA, FRED, Census, and clinical-trials registries ## Use cases ### Agent-Grounded Research An AI agent connected through Jentic answers a hard question by launching a deep-dive research job, then returning the result with the evidence and source chunks that back it, so the answer is auditable rather than a bare assertion. Because Fodda exposes the knowledge graph directly, the agent can traverse related entities to widen the context before it concludes. Example prompt: Launch a deep-dive research job on a company, wait for it to finish, and return the summary with its evidence chunks ### Brand and Expert Intelligence A market-intelligence workflow pulls a brand intelligence profile and expert intelligence for a subject, then discovers adjacent trends in the graph, so a team builds a briefing without manually combing sources. Fodda returns cited evidence with each profile, so the briefing can link every point back to where it came from. Example prompt: Get the brand intelligence profile for a brand and list the adjacent trends its graph reveals ### Earnings-Call Analysis An analysis job reads the earnings-call snapshot for a company, then pulls the top analyst concerns and management presentation themes, so an analyst sees what mattered on the call without listening to the whole recording. Each theme carries the evidence behind it, so the analyst can verify a point before acting on it. Example prompt: Pull the latest earnings-call snapshot for a company and summarise the top analyst concerns with their evidence ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/research/deep-dive` | Launch an autonomous research deep-dive | | POST | `/v1/research/chat` | Run a research chat turn | | POST | `/v1/graphs/{graph_id}/search` | Search a knowledge graph | | POST | `/v1/brand-intelligence/{brandName}` | Get a brand intelligence profile | | GET | `/v1/graphs` | List available context graphs | | POST | `/v1/search/expert` | Run an expert intelligence search | | GET | `/v1/supplemental/earnings/snapshot` | Get an earnings-call snapshot | ## Key resources - **Knowledge Graphs** — Searchable, traversable graphs with nodes, neighbors, and evidence - **Research** — Deep-dive jobs, streaming search, research chat, and scheduled briefings - **Intelligence** — Brand, domain, and expert intelligence profiles and parallel search - **Supplemental Sources** — Public-source snapshots from the FDA, FRED, Census, and clinical-trials registries ## 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:** 41 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 46 / 100 - Developer Experience & Jentic Compatibility: 56 / 100 - AI-Readiness & Agent Experience: 24 / 100 - Agent Usability: 61 / 100 - Security: 55 / 100 - AI Discoverability: 44 / 100 - **View full report:** https://jentic.com/apis/fodda.ai/fodda/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 Fodda Context & Research API by hand means handling X-API-Key auth, knowing which endpoints are public, carrying a Stripe payment token on metered calls, and polling long research jobs to completion. Through Jentic you install once, import Fodda from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** You choose which operations your agent may call, so you can allow graph search and research deep-dives while leaving destructive ones like cancelling a scheduled briefing or upgrading an account out. Rules bound which operations run, so the agent researches within the surface you grant. - **Credential handling:** Your Fodda 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 'research a company in depth' or 'search a knowledge graph', and Jentic returns the matching Fodda operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Exa API** — Neural web search API that returns relevant pages and their contents for research - **Tavily API** — Search API built for AI agents that returns ranked, citation-ready results - **Perplexity API** — Answer engine that returns synthesised, cited responses to natural-language questions ## FAQ ### Is there a Fodda MCP server? You don't need an MCP server to give your agent the Fodda Context & Research API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can search knowledge graphs, launch research jobs, and pull intelligence straight away, with no extra server to run and no tool definitions sitting in the agent's context. ### Can I limit what my agent is allowed to do with the Fodda API? Yes. Write a rule that allows only the operations the agent needs, such as searching graphs and launching research deep-dives, and leave schedule deletion and account changes out. Every call the agent makes is logged, so you can see exactly which research and lookups it ran. ### What authentication does the Fodda Context & Research API use? The Fodda API authenticates with an API key sent in the X-API-Key header per its OpenAPI spec. A number of endpoints are public and need no credential, while metered payment operations accept a Stripe Shared Payment Token presented as a bearer token. Through Jentic the key is stored encrypted by your own instance and added at call time, so it never appears in the agent's prompt or logs. ### Can I get cited evidence with the Fodda API? Yes. Research and intelligence results carry evidence, and dedicated operations return the evidence and the underlying source chunks for a graph or query. An agent can fetch those chunks to show exactly which source backs each figure before it reports an answer. ### What are the rate limits for the Fodda Context & Research API? The OpenAPI spec does not state request rate limits for the Fodda API. For current limits and fair-use guidance, check the provider documentation at https://www.fodda.ai. ### How do I run a research deep-dive through Jentic? Import the Fodda Context & Research API from the Jentic API Directory, then have your agent issue a request such as 'research this company in depth'. Jentic matches the intent to the deep-dive operation and returns its input schema so the agent builds the correct request, with your stored key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.