Fieldguide

An OpenAI enterprise web surface for financial-services workflows. It provides built-in access to SEC filings, delayed market data, news, private-company profiles, and earnings transcripts, along with finance plugins that combine reusable skills with MCP connections. The demonstrated workflow uses a wealth adviser’s portfolio-change analysis and client-deck preparation as an example, and can be extended with Codex, custom skills, internal-data connections, and plugin extensions.

Agent Control is an open-source library for creating steering rules that programmatically constrain and guide AI-agent behavior. In the demonstrated customer-service workflow, steering handlers check workflow order and response tone, providing explicit controls alongside skills and contextual instructions. The library can be hosted in a database.

The Agent Accountability Framework is an open governance framework for making AI agents accountable when they hold authority in production. Published and funded by Gravitee, it defines six principles organized around three stages: Assignment establishes an agent's identity, team, and named human sponsor; Alignment defines its role, mission, measurable boundaries, and least-privilege authority; and Administration provides oversight scorecards, guardian agents, and step-by-step recourse when an agent goes off course. The framework is published free for anyone to use, with a concept paper and an invitation for contributors.

Agency Agents is a collection of specialized AI-agent instruction files and a native desktop app for macOS, Linux, and Windows. Its agents define domain-specific identities, workflows, rules, deliverables, code examples, and success metrics across engineering, design, marketing, sales, testing, security, finance, game development, GIS, healthcare, and other divisions. The repository provides scripts that convert and install the agents into tools including Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Aider, Windsurf, Qwen Code, Kimi Code, Codex, Osaurus, and others; the app browses the roster, installs selected agents, and keeps them updated. The repository is distributed under the MIT License.

Guardian is OpenAI’s enterprise safety system for computer-use agents. A smart model reviews each action an agent takes and assesses whether it is safe and aligned, while businesses can control how much human approval the agent requires, including automatic approval.