Guides
Choosing a web search API for your agent
Tavily, Exa, Brave Search, Perplexity and Firecrawl each lean toward a different part of search. How to pick for your agent, and why you…
2 min read
Blog
Guides
Practical walkthroughs for building agents with connectors, managed OAuth and workflows.
Guides
Build a research agent with web search and one bill
Search, read and answer with sources: the shape of a research agent when the model, the search service and the page reader all come…
2 min read
Guides
Workflows: configure a capability once, call it by name
A workflow turns several endpoints, from one service or many, into one named capability your agent can call. How brief works, and when to…
2 min read
Guides
Managed OAuth for AI agents: who authorizes what
An Agent200 API key lets your app call Agent200. It does not open anyone's inbox. How developer configuration, end-user authorization and provider permissions fit…
2 min read
Guides
Writing tool descriptions models actually follow
The model chooses a tool from its name, description and inputs, nothing else. Six rules for tool definitions that lead to the right call.
2 min read
Guides
The right model for each request
Classify with a light model, reason with a strong one. How to choose the model per task, and test your way to the lightest…
2 min read
Guides
Development, staging, production: environments for your agent
Give the agent you build, the one you test and the one your customers use their own keys, services and statements. A setup that…
2 min read
Guides
Use Agent200 from any agent framework
LangGraph, the OpenAI Agents SDK or your own code: Agent200 plugs in where your agent reaches the outside world, and your framework carries on…
2 min read
Guides
From prototype to production in eight steps
From first key to first real user: the eight steps of shipping an agent with Agent200, and a checklist before anyone else depends on…
2 min read
Guides
Connection prompts users say yes to
Agent200 handles the OAuth mechanics. What the user sees is up to you. Ask at the moment of need, say what the agent will not do, and ask for less.
2 min read
200 OK
Build the agent.
Access everything it needs.
Bring the agent you already have. Agent200 provides and executes its external capabilities.