01
Agent demo
Make this concrete enough that another engineer can understand what you built and why.
CAREER PROJECT · Advanced · 3 weekends
AI Agent Operations Console
Build a tool-using agent with permissions, traces, retries and explicit human approval points.
AgentsTool useSafetyTracingEvaluation
DEFINITION OF DONE
Leave artifacts a reviewer can inspect.
02
Tool permission model
Make this concrete enough that another engineer can understand what you built and why.
03
Trace viewer
Make this concrete enough that another engineer can understand what you built and why.
04
Failure tests
Make this concrete enough that another engineer can understand what you built and why.
05
Eval suite
Make this concrete enough that another engineer can understand what you built and why.
RESUME / PORTFOLIO FRAMING
Describe what you actually did.
Built a tool-using AI agent with constrained permissions, approval gates, tracing and failure evaluation.
Use this as a starting structure, then replace it with your real implementation details, metrics and constraints. Do not claim outcomes you did not measure.
STRETCH GOALS
Go deeper if the core is already solid.
Sandboxing
Add only if it strengthens the engineering story instead of delaying a finished, deployable core.
Policy tests
Add only if it strengthens the engineering story instead of delaying a finished, deployable core.
Multi-agent handoff
Add only if it strengthens the engineering story instead of delaying a finished, deployable core.