Guide library
DESIGN / MEASURE / GOVERN
AI Coding Agent Architecture, Security, and Evaluation
Detailed guides to context engineering, cost, threat modeling, prompt injection, evaluation, multi-agent workflows, gateway routing, and observability.
LEARNING PATH
Follow the sequence or start from a problem
Every topic states its scope, operating path, evidence sources, and verification gates. Follow the sequence or enter at the problem you need to solve.
01Context Engineering for Coding Agents: Scope, Retrieval, and Durable StateHelp teams design repeatable context boundaries for long coding tasks and large repositories.14 min02Coding-Agent Cost Optimization Without Sacrificing VerificationGive teams a cost-control framework that preserves reviewability and engineering quality.13 min03Coding-Agent Security Threat Model: Assets, Trust Boundaries, and ControlsHelp engineering and security teams review coding-agent deployments before granting real capabilities.15 min04Repository Prompt-Injection Defense for Coding AgentsProvide maintainers with a concrete control sequence for handling instruction-like text from untrusted sources.14 min05Coding-Agent Evaluation Framework: Reproducible Tasks and Reviewable EvidenceHelp teams build an auditable evaluation before choosing or expanding a coding-agent workflow.15 min06Multi-Agent Coding Workflows: Delegation, Isolation, and IntegrationHelp teams parallelize coding-agent work without losing ownership, security, or reproducibility.14 min07LLM Gateway Routing for Coding Agents: Policy, Compatibility, and FailoverHelp platform teams design gateway routing without confusing text completion with full coding-agent compatibility.15 min08Coding-Agent Observability: Traces, Evidence, and Privacy BoundariesHelp platform and engineering teams diagnose agent workflows while preserving privacy and security boundaries.14 min