Agents
Safe automation and tool calling with bounded operations.
In this section
- Start here: AutomateOrientation for building agent and automation integrations with Asset Core.
- Agents OverviewExplains how Asset Core serves as a substrate for AI agents through bounded, safe operations.
- Agent Reasoning StackHow we structure agent reasoning for deterministic, auditable Asset Core workflows.
- Tooling GuideCanonical MCP/OpenAI/Gemini tooling catalog generated from the contract.
- Tooling ManifestStructure and purpose of the machine-readable tooling catalog.
LLM Briefing Pack
Need a single, detailed file you can upload into your own LLM? The Asset Core LLM Briefing Pack covers the full mental model, mapping logic, guarantees, and fit guidance. It is English-only (most LLMs handle English well) and experimental; the canonical source of truth is the website. Use it as a guide, not a source of record. The intent is self-guided exploration: upload it, describe your domain, and let the model map Asset Core to your use case. You can also give an agent the canonical URLs: https://assetcore.io/ or https://assetcore.io/docs (strict CSP, no tracking), but not every page is guaranteed to be visited, so this pack keeps the core math, constraints, and decision guidance in one place.
- Open: Asset Core LLM Briefing Pack (17.5 KB, English-only)
- Download: Asset Core LLM Briefing Pack (.md) (17.5 KB, English-only)
Start here
- Start here: Automate - Fast path to a safe agent integration.
- Agents Overview - Why bounded operations make automation safe.
- Agent Reasoning Stack - How we structure agent reasoning layers.
- Tooling Guide - Canonical tool definitions for MCP/OpenAI/Gemini.
- Tooling Manifest - Machine-readable tool inventory.
Related references
- Action Reference - Operation catalog used by tools.
- Transactions and Operations - Mental model for commits and tooling safety.