For Agents
Entradigm is built for agents.
Every action in the interface can be done by an agent through the API. This isn't a retrofitted integration, it's the architecture: the agent surface is the primary surface, the human interface sits as a thin layer on top. This page speaks to the human buyer — and at the same time shows the agent where the machine-readable surface lives.
Discovery — live, auth-free
Two public surfaces an agent reads before it touches anything.
Both live on the app host app.entradigm.com, are
CORS-enabled and require no authentication. They contain only platform
documentation and the public schema — never tenant data.
Orientation (llm.txt)
Plain-text orientation for LLM agents: platform docs as markdown, the list of live endpoints and copy-paste curl recipes.
Open llm.txt →Introspection (intent schema)
The machine-readable JSON schema for every intent, plus the capabilities block (apiVersion and what this deployment can do). Readable from any origin.
Open schema →The handshake
Orient → introspect → act — in three calls.
A typical discovery flow. The first two steps are auth-free; the third is bearer-token gated and rate-limited — the agent passes the tenant token to trigger a cycle.
# 1. orient
curl -s https://app.entradigm.com/.well-known/llm.txt
# 2. introspect the intent schema
curl -s https://app.entradigm.com/strategist/schema | jq '.intents'
# 3. act (bearer-gated)
curl -s -X POST https://app.entradigm.com/strategist/run \
-H "Authorization: Bearer $ENTRADIGM_TOKEN" \
-H "Content-Type: application/json" \
-d '{"intent":"generate-cycle","tenant":"your-tenant"}'Every UI action has an API equivalent — there are no internal endpoints. An external agent (your n8n workflow, your Make scenario, your coding agent) drives Entradigm exactly the way a human does.
What we do better
A surface an agent can already read today — and a contract designed for it.
What's live today is written in the present tense. What the public, versioned
API will bring is labelled as a design goal — the formal
/v1/ API is on the roadmap and not shipped yet (see
below).
Auth-free discovery
Live today: the public llm.txt and the intent schema at /strategist/schema — readable from any origin, no token.
Intents through one endpoint
Live today: agent intents are triggered bearer-gated via /strategist/run — every UI action has its API equivalent.
Machine-readable capability matrix
Live today: the capabilities block in the schema tells an agent what this deployment can do — before it tries.
Versioned API
The public API is designed for a versioned path (/v1/), so the contract doesn't shift under an agent.
Unified error envelope
The public API will return errors as {error:{code,message,context}} — machine-readable and consistent instead of free-form prose.
Cursor pagination & rate-limit headers
The public API is designed to walk lists via stable cursors and carry the remaining budget in every response via X-RateLimit-* headers. Signed webhook payloads for cycle events are also part of the target picture.
Roadmap
What's coming next — honestly labelled.
The following agent surfaces are not shipped yet. They're on the roadmap and labelled as such here, never presented as available.
MCP server
A single endpoint (roadmap 2027) through which any LLM agent wires in Entradigm as a tool with full schema introspection.
n8n node
A native node for n8n automation workflows.
SKILL.md
An agent-readable skill manifest for coding agents.
Public /v1/ API
The formal public, versioned API with error envelope, cursor pagination and rate-limit headers.