Skip to main content
POST
/
api
/
v1
/
agents
/
from-website
curl --request POST \
  --url https://{subdomain}.mihu.ai/api/v1/agents/from-website \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "source_url": "https://mihu.ai",
  "language": "en"
}
'

Authorizations

​
Authorization
string
header
required

Use a Bearer token to access these API endpoints. Example: "Bearer {your-token}"

Body

application/json
​
source_url
string<uri> | null

Website or documentation URL to crawl and analyze. Required unless analysis_prompt is provided. Prefer this over prompt-only research: it anchors the analysis to the right company.

Example:

"https://example.com/docs"

​
language
string

Optional output language (ISO 639-1, e.g. en, tr, fr, de). The analysis and generated agent texts are written in this language. Defaults to the workspace language.

Example:

"fr"

​
analysis_prompt
string | null

Optional extra analysis instruction. Use it to request pricing analysis, documentation summary, or market positioning on top of the standard website analysis. The result is returned inside additional_analysis. Can also be used alone (without source_url) for prompt-only research, but results are better when a URL anchors the analysis.

Maximum string length: 4000
Example:

"Summarize the product documentation, pricing pages, and FAQ in detail."

​
search_country
string | null

Optional ISO 3166-1 alpha-2 country code (TR, US, DE, FR, GB...). Localizes the web search to that market. Use when the company mainly operates in one country.

Example:

"TR"

​
search_region
string | null

Optional state, province, or administrative region for finer localization. Use together with search_country.

Example:

"Istanbul"

​
search_city
string | null

Optional city for local-business analysis. Use together with search_country.

Example:

"Istanbul"

​
search_latitude
number<float> | null

Optional latitude for precise location-based search. Use with search_longitude and search_country.

Example:

41.0082

​
search_longitude
number<float> | null

Optional longitude for precise location-based search. Use with search_latitude and search_country.

Example:

28.9784

​
search_language_filter
string[] | null

Optional ISO 639-1 language codes. Restricts which source languages are searched — e.g. ['tr'] to analyze only Turkish sources. Independent from the output language.

Maximum array length: 10
​
search_domain_filter
string[] | null

Optional domain allow/deny list, maximum 20 entries. Plain domain includes it ('mihu.ai'), '-' prefix excludes it ('-wikipedia.org'). Use to keep the analysis pinned to the company's own sites.

Maximum array length: 20
​
search_preset
enum<string>
default:fast-search

Analysis depth. When to use each value:

  • fast-search (default): fastest and lowest cost. Small websites and quick agent setup. Typical response in seconds.
  • pro-search: balanced speed and quality with better page coverage. Recommended for most production agent creation.
  • deep-research: slow, deep crawl and research. Large or complex websites, or when analysis_prompt asks for extra research. Can take minutes.
  • advanced-deep-research: slowest and most exhaustive. Use only when maximum coverage matters more than speed.
Available options:
fast-search,
pro-search,
deep-research,
advanced-deep-research
Example:

"pro-search"

​
agent_name
string | null

Optional override for the agent's name. If omitted, the system derives it from the company name.

Example:

"Support"

​
role
string | null

Optional override for the agent's role. If omitted, the system decides from the discovered business context.

Example:

"Customer support agent"

​
objective
string | null

Optional override for the agent's objective. If omitted, the system builds it from the discovered services, audience, and automation opportunities.

Example:

"Answer questions and route customers"

Response

Agent created from website successfully. Returns the created agent and the analysis it was built from.