AI directory search
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
4 matches for "sandboxing"
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
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
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
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