Overview
What this challenge is about.
Build an internal-tools agent from OpenAPI specs with budgets and deny-lists, then write a CIO design memo. Earn a verifiable certificate.
The scenario
The startup (Series B, around 110 staff, around 40 mid-cap customers) sells per-seat licenses and wins or loses renewals on whether the agent is trustworthy enough to put in front of non-technical staff.
The Brief
What you'll do, and what you'll demonstrate.
Ship a tool-using LLM agent that resolves 80%+ of reference questions safely, with budgets and guardrails the customer's CIO can sign off on.
Earning criteria — what you'll demonstrate
- Design tool-using LLM agents with explicit budgets and guardrails
- Build an evaluation harness for agent task success
- Reason about failure modes specific to tool-use agents
- Communicate agent architecture to a non-engineering executive
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
AI Agents and LLM-Based Agents
Master · Ai Systems
Strong alignment
This challenge maps to AI Agents and LLM-Based Agents at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Llm Agents
Apply llm agents to solve real industry problems and demonstrate production-level capability.
- Tool Use
Apply tool use to solve real industry problems and demonstrate production-level capability.
- Agent Evaluation
Apply agent evaluation to solve real industry problems and demonstrate production-level capability.
- Prompt Engineering
Apply prompt engineering to solve real industry problems and demonstrate production-level capability.
- Guardrails
Apply guardrails to solve real industry problems and demonstrate production-level capability.
- Python
Write clean, efficient Python for data processing, automation, and backend services.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Engineer
Building a tool-using agent for an enterprise customer end-to-end is the canonical AI-engineer project at agent-platform startups.
This challenge sharpens
- llm-agents
- tool-use
- guardrails