Exa
Based in United States; at Web Summit Lisbon 2026 as a speaker's company. Public facts only, each with its source.
On this page
Not everything
Not everything we held. Some facts on this page rested only on Web Summit's site, which we may not republish; on 11 November we took them off. What you see has another public source, each cited. A fact comes back when we find one. How items come back
| What they do | Search API for AI agents: real-time web data, deep research and structured content from one endpoint. |
| Based in | United States |
| At Web Summit as | a speaker's company |
| Confirmed for 2026 | Yes: Will Bryk (Co-founder & CEO) is listed on the LIS26 session page 'Search built for AI agents' |
| Website | exa.ai |
| Filed under | AI agents |
About Exa
Exa makes a search API for AI agents (1). It gives agents real-time web data, deep research and structured content through one endpoint, the company says (1).
Sources for this section:
- Exa, "Search API for AI Agents", read 9 November 2026
Its products
- Exa Search API (agentic): Web search for AI agents at three latencies, returning results, answers or structured data. (exa.ai/, read 2026-11-07) · its flow
Its flows, and where AI agents are in them
How work moves through Exa's product, as its public pages describe it, and the steps where an AI agent acts (2 steps with an AI agent in it, marked AI agent here). Each step cites its source.
An agent searches the web for the context it needs (Exa)
Exa's home page, in its own terms: an agent or app calls Exa's search at the latency it can afford and gets back results, an answer or structured data, then the contents it needs; the benchmarks and the 900,000+ developers are Exa's own figures. (exa.ai/, read 2026-11-07)
- The developer: Connects an agent or app to Exa: the Search, Contents or Agent API, or Exa's MCP server. (exa.ai/, read 2026-11-07)
- The agent: Sends a search at a chosen depth: Lite (about 450 ms), Auto (about 1 s) or Deep (about 10 s), across the web, news, companies, research, people or financials. AI agent here: Search the web. (exa.ai/, read 2026-11-07)
- Exa: Returns results, an answer or structured output from its index of public web and private information. (exa.ai/, read 2026-11-07)
- The agent: Uses what comes back as context, for example a coding agent reading the docs and repositories it needs. AI agent here: Read the results as context. (exa.ai/, read 2026-11-07)
Our question for them
As for every company we follow, three questions, not claims. We have not asked Exa yet. When they answer, it goes here.
- Reach What can their AI agents (or their customers' agents) actually reach?
- Mandate What were they authorised to do?
- Gap Who controls the gap between the two?
Where this comes from
- websummit.com/sessions/lis26/a433a1bc-b53a-4689-a8f8-c7eb8088148c/sea…, read 2026-11-01 by the team's curator: LIS26 session page: 'Search built for AI agents', 12 Nov, AI Summit, Stage 13, names Exa as the speaker's organisation.
- websummit.com/attendees/lis26/6f5ebc37-fbca-490f-bc46-4d94e81ee69e/wi…, read 2026-11-01 by the team's curator: LIS26 attendee page: Will Bryk, Co-founder & CEO, Exa; country and industry as listed by Web Summit; public bio.
- exa.ai/, read 2026-11-01 by the team's curator: what the company does, from its own site (title and description).
- exa.ai/, read 2026-11-07 by the team's curator: Exa's home page, re-read for its flow (read 7 November 2026, 07:25 UTC): "the world's data for AI agents": a Search API at three latencies (Lite, Auto, Deep), results, answers or structured output, a Contents API, an Agent API and an MCP server; coding agents searching docs and repos (the flow agent-searches-the-web)..
Re-checked by newsroom@web-summit.dinis on 2026-11-05 at 01:50 UTC: the summit's page answered and is still live; the company's website answered and is live.
Taken from the team's company map (data/companies.json on web-summit.sgit.ai), public facts only. The team's own notes on each company (why it matters, whether to meet, who owns it) are not facts about the company and are not published here. Something wrong? Tell us and we correct it on this page, dated.
About PrompTugal.news
PrompTugal.news: People and AI agents, reporting together. Every fact sourced and dated, for the people who are there. Edited by Dinis Cruz, Indi Gupte and Vicky Wang, made with AI agents. Web Summit is named only to say where we report from. Text CC BY 4.0, code Apache-2.0.
- Why this page exists. We keep a page on every company we follow at the summit, built only from public pages, so that anyone, Exa included, can see what we know and where it comes from. Nothing on it is an endorsement.
- Independence. Independent. Not affiliated with Web Summit. The team that makes PrompTugal.news also works on RiskMandate, so we are independent of Web Summit, not of RiskMandate. Our disclosure says it in full; please weigh what we say with it in mind.
- Corrections. If something here is wrong or out of date, we correct it on this page, dated. We publish no contact details and nothing about a person that is not already public and professional.
- More. About PrompTugal.news, all the companies, the summit.
The same, as data: companies/exa.json and its graph, graph/companies/exa.json (how to read them: the data, as JSON).