API package
Agentic AI
Agents that do work, the workflows that orchestrate them, and the systems they reach. An agent is not a chatbot and not a batch job: it chooses its next step at run time, against tools it was granted, under limits somebody set. Every one of those choices is recorded — which model, which version of which prompt, which tools it held, what it called, what came back, what it cost and who approved it — because "the agent did it" is not an answer anybody can audit.
33 APIs181 operationsBase path
/api/agenticAssess
Agent Memory
What each agent has kept between runs, and when it will forget it. Only where the agent memory mode allows it.
GET2 POST2 PUT1 DELETE1
Evaluations
Whether the agent was any good — graded by a person, by another agent, or by what happened to what it produced. A proposal accepted and still standing thirty days later is the strongest signal this table can carry.
GET2 POST2 PUT1 DELETE1
Build
Agent Versions
Every published prompt, with what it was allowed to call. A run names the version it used, so a decision made three months ago reads against the instructions that were live then rather than the ones live now.
GET2 POST2 PUT1 DELETE1
Agents
What each agent is for, what it may do, and what it has actually been doing. An agent with no tools is not broken — it is one that can only think, which is a legitimate and common thing to want.
GET3 POST7 PUT1 DELETE1
Knowledge
What an agent may read that is not a tool call — a folder, a set of articles, a report. Retrieval rather than action.
GET2 POST2 PUT1 DELETE1
Tool Grants
Which agent may call what, and on what terms. The same tool is a different risk in two agents' hands, which is why the limits live on the grant rather than on the tool.
GET2 POST2 PUT1 DELETE1
Connect
Agent Connections
The MCP servers, APIs, webhooks and other agentic platforms this company reaches. An MCP server describes its own tools, so the catalog is the server answer rather than somebody typing.
GET2 POST5 PUT1 DELETE1
Discovered Tools
What each connection turned out to be able to do. A tool the server no longer offers is disabled rather than deleted, because deleting it would take the grants and the call history with it.
GET2 POST3 PUT1 DELETE1
Tool Catalog
Everything an agent may be granted, of every origin, in one list — because the model is given one list and the person granting authority should be reading the same one. A resource tool is the platform own endpoint, so it inherits the module grant, the org scope, the numbering, the editability rule and the audit trail unchanged.
GET2 POST2 PUT1 DELETE1
Limits & Oversight
Guardrails
The limits that are not the agent's own. Checked before every tool call and again against what it would move. A new deployment with agents and no limits is one bad prompt away from a thousand purchase orders.
GET2 POST2 PUT1 DELETE1
Incidents
A guardrail broken, a loop caught, a cost overrun, an unsupported claim. Separate from the run because a breach outlives it: it is the thing somebody reviews on Monday.
GET2 POST2 PUT1 DELETE1
Operate
Agent Approvals
What is waiting on a person. A run stops here and survives a restart while it waits; an approval nobody answers expires rather than hanging.
GET2 POST3 PUT1 DELETE1
Agent Runs
Every run, with what it did, what it cost and what stopped it. A run is not a record somebody edits — it is the account of what happened.
GET3 POST5 PUT1 DELETE1
Delegated Tasks
Work an agent handed to a licensed Claude worker because it was too big for one model turn. Claim one to get a worker token and the connection for Claude Code, the Agent SDK or a managed agent; the worker reaches this company only through the agent's own tool grants, guardrails and approvals, and every call is recorded.
GET2 POST10 PUT1 DELETE1
Tool Calls
Every call an agent made and what let it through. This column — grant, approval or guardrail — is what turns this table from a log into evidence.
GET2 POST2 PUT1 DELETE1
What Agents Produced
Every record created, message sent, proposal made and finding recorded. Accepting a proposal creates the record THROUGH THE API with your name on it, not the agent — which is where most of the value of a suggest-level agent actually lands.
GET2 POST4 PUT1 DELETE1
Orchestrate
Agent Workflows
The graphs. What runs is the PUBLISHED SNAPSHOT, not what is on the canvas — so editing a workflow while a run is in flight changes nothing about that run.
GET3 POST6 PUT2 DELETE1
Published Versions
What each published version of a graph actually was. A run in flight keeps running against the version it started on.
GET2 POST2 PUT1 DELETE1
Triggers
What starts a run. A trigger created from a template is never armed — a new tenant should not have agents running before anybody has read what they do.
GET2 POST2 PUT1 DELETE1
Reachable by link
Edges
How the nodes are joined and what decides which way a run goes.
GET2 POST2 PUT1 DELETE1
Nodes
Every node of every graph, as a list. The canvas is the way to work on these; this is here for searching across workflows and for a saved view.
GET2 POST2 PUT1 DELETE1
Steps
Every node execution across every run. The trace on a run is the way to read these; this is for searching across runs.
GET2 POST2 PUT1 DELETE1
Reporting
Services and actions
Artifacts,
The artifacts, service of Agentic AI: 1 operation(s).
GET1
Drive folders
The drive folders service of Agentic AI: 1 operation(s).
GET1
Engines
The engines service of Agentic AI: 1 operation(s).
GET1
Models
The models service of Agentic AI: 1 operation(s).
GET1
Overview
The overview service of Agentic AI: 1 operation(s).
GET1
Run steps,
The run steps, service of Agentic AI: 1 operation(s).
GET1
Runs,
The runs, service of Agentic AI: 1 operation(s).
GET1
Studio
The studio service of Agentic AI: 1 operation(s).
GET1
Vendors
The vendors service of Agentic AI: 1 operation(s).
GET1