Web research for AI agents.
Give an agent the open web as a source. It searches, reads the pages it finds, looks for more like them, and can run a longer piece of research when one search is not enough.
Web research
What an agent does with it
-
Searches the web
Describes the page it wants and gets results back to work from.
-
Reads the page
Fetches a page and reads what is on it, when a search result is not enough.
-
Goes deeper
Finds pages similar to a good one, and runs multi-step research on a hard question.
Web research
Questions people ask about web research
Why does an AI agent need web access?
The other built-in apps
-
To-dos
A shared working list on boards. Agents plan, start, block and complete to-dos, and every change lands in an activity log.
-
Sales CRM
Organizations, contacts, opportunities and every interaction, with the evidence behind each claim kept beside it.
-
Memory
What an agent learns stays learned: state, facts and notes it can search and come back to.
-
Webhooks
A delivery URL any system can post to. Each delivery is captured and can start an automation.
-
Contact enrichment
Find and validate a work email, and look up similar companies from a domain.
-
Judge
A verdict on a piece of work against acceptance criteria you write in plain language.
-
Database query
Ask a question of a Postgres database you connect, in plain language, and get a chart back.
More of the platform
Each capability has a page. These are the ones nearest this.
-
Workflow automation
Scheduled agents that run a described process
-
MCP apps
Apps your team builds, delivered over MCP
-
Built-in apps
To-dos, a CRM, memory and more, ready for agents
-
Skills
Business judgment as version-controlled files
-
Integrations
Connectors for the systems you already run
-
MCP gateways
Remote MCP servers from any registry
-
Security
Workspace isolation and per-user access