Search

3 result(s)

2026-02-06•United Kingdom•Tutorials•6 min read

Rules fail at the prompt, succeed at the boundary

Agentic workflows and prompt coercion are the new attack surface. This tutorial shows a concrete, deployable boundary strategy (policy engine + sandbox + attested channels) to reduce agentic compromise risk — with configs, code, metrics and a founder cost/risk frame.

prompt-security agent-safety zero-trust policy-engine Anthropic Gemini production UK

2026-02-06•France•News•7 min read

GPT-OSS Agentic RL: What Builders Can Actually Ship

A builder-focused breakdown of Agentic RL for GPT-OSS: what changed, what to implement first, and how founders can decide if the economics work.

agentic-RL GPT-OSS RLHF Hugging Face open-source safety MLOps

2026-02-06•United States•Tutorials•Agent Playbook•Intermediate•240 min build•7 min read

Unlocking the Codex harness: how we built the App Server

A hands‑on tutorial showing how to embed the Codex agent with a Codex App Server — a bidirectional JSON‑RPC service that powers streaming progress, tool use, approvals, and diffs. Includes an implementation plan, infra and monitoring artifacts, rollout gates, and founder ROI considerations.

codex agent app-server json-rpc streaming tooling approvals diffs