►
Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
AI Engineer · 2026, coding agent security, sandboxing, least privilege
AI directory search
Search across educators, skills, and resources.
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
19 matches for "sandbox"
Video matches
Watch first when you want a fast feel for the topic before opening courses, docs, or profiles.
►
►
2,000 AI Agents Rewrote a Coding Agent in Rust
Bitwise AI · 2026, Prime Agent, Rust, multi-agent coding
►
The Lethal Trifecta Is Already on Your Laptops — Michael Patterson, Coder
AI Engineer · 2026, coding agent security, prompt injection, data exfiltration
►
AI Just Crossed the Terrifying Line - Now What?
Kurzgesagt – In a Nutshell · 2026, ai safety, agent security, reward hacking
Resources
Inspect AI
Model and agent evaluation harness · UK AI Security Institute · Intermediate to advanced
Rigorous, reproducible model and agent capability or safety evaluations involving tools, multi-turn interaction, coding, or sandboxed environments.
evals, llm evaluation, ai quality, open-source frameworks
Harbor
Agent evaluation and optimization harness · Harbor Framework Team · Intermediate to advanced
Running coding and computer-use agents against reproducible, sandboxed task suites at local or cloud scale.
evals, llm evaluation, ai quality, benchmarks and learning resources
Terminal-Bench
Terminal-agent benchmark · Harbor Framework and Laude Institute · Intermediate to advanced
Comparing agents on difficult, verifiable coding, systems, security, and scientific work inside sandboxed terminals.
evals, llm evaluation, ai quality, benchmarks and learning resources
Introducing the Agents API
Managed agent API launch and guide · OpenAI · Intermediate to advanced
You want OpenAI's September 10, 2026 launch guide for building long-running cloud agents with the managed Codex harness, context compaction, tool search, multi-agent delegation, and your choice of hosted or self-managed sandbox.
openai, agents, codex, context compaction, multi-agent
How Meta built safety into Muse
Agent security architecture guide · Meta AI · Intermediate to advanced
You want Meta's September 8, 2026 technical account of defense-in-depth for a long-running personal agent, including isolated runtime cells, credential surrogates, a separate permission authority, tainted-egress tracking, scoped approvals, browser controls, red teaming, and prompt-injection evals.
meta, muse, agent security, prompt injection, least privilege
OpenAI Sandbox Agents
Guide · OpenAI · Intermediate to advanced
You need the official beta guide to giving Python or TypeScript Agents SDK workflows isolated files, commands, packages, ports, snapshots, and resumable state while keeping the agent harness and sensitive control-plane work outside the execution container.
openai, agents sdk, sandbox, coding agents, containers
Codex Bootcamp
Official bootcamp · OpenAI · Intermediate to advanced
You want a current OpenAI learning series on agentic coding, shared team workflows, approvals, sandboxing, memory, subagents, and production automation.
openai, codex, coding agents, team workflows, automation
Anthropic Managed Agents
Guide · Anthropic · Intermediate to advanced
You want Anthropic's current managed-agent starting point, including the Agents, Sessions, and Environments APIs for autonomous sessions, built-in tools, and secure execution.
anthropic, managed agents, agents, sandboxing, tool use
Gemini Agents Overview
Guide · Google AI for Developers · Intermediate
You want the official overview of Gemini managed agents, sandbox behavior, and when to use agent workflows instead of plain model calls.
gemini, agents, interactions api, deep research, coding agents
Gemini Managed Agents quickstart
Quickstart · Google AI for Developers · Intermediate
You want Google's practical quickstart for building a managed Gemini agent that streams responses, keeps multi-turn state, uses the Antigravity sandbox, and can return files instead of reading only the higher-level overview.
gemini, managed agents, interactions api, tools, stateful workflows
Gemini agent environment
Guide · Google AI for Developers · Intermediate to advanced
You need Google's exact sandbox, source-mount, and network-control model before trusting a managed Gemini agent with code, files, or long-running work.
gemini, managed agents, sandbox, skills, hooks
Gemini AI Studio agents
Playground guide · Google AI for Developers · Intermediate
You want the visual Gemini playground for prototyping managed-agent instructions, tools, and environments before committing to API code.
gemini, ai studio, managed agents, playground, sandbox
Qwen Coder
Coding agent product page · Qwen · Intermediate
You want to see Qwen's hosted coding-agent workflow alongside the open-source Qwen Code docs before choosing between cloud and local agent setups.
qwen, coding agents, cloud sandbox, pull requests, software engineering
A Local-First Agent for Private and Cost-Effective Knowledge Work
Engineering study · Perplexity · Intermediate to advanced
You want a practical primary-source study of co-designing a compact local model and agent harness, including on-demand skills, context compaction, sandboxing, verification, and optional frontier-model escalation.
perplexity, local models, agent harnesses, privacy, sandboxing
Perplexity Computer MCP Server
Integration guide · Perplexity · Intermediate to advanced
You want Perplexity's August 15, 2026 hosted computer-use MCP guide for browser automation, OAuth-backed connectors, sandboxes, and tool-based workflow execution from MCP clients.
perplexity, computer use, mcp, automation, connectors