Your AI identity and your AI team, portable to every AI platform.
Sign in Get Started
Menu
Build an Agent of Me Explore Styles Professional Agents Community Agents Leaderboard AI News
AI Platforms Directory Model Matrix Compare Which AI should I use? Integration Guides Set up OpenClaw Prompt Fit
Learn & Tools Learn Ask the Data Agent Builder API
About About us Contact Disclaimers
Sign in Get Started
Account
Your AI identity, portable

Create a free account to build your profile. Private by default. Nothing is shared unless you publish it.

Get Started Sign in
Dark mode

🧭 Guided View
New to prompts, system instructions, context windows, tokens? We explain every term as you browse, in plain English. Same pages, with the help built in.

⚡ Expert View
You already know how prompting works. Just the substance, clean and compact, with no extra explanations. This is the default view.

Interface language

Final test · Prompt Systems & Agents

Final test: Prompt Systems & Agents

Ten questions covering every section, a fresh, balanced draw from the whole bank each attempt. Pass with 60%; a retake always brings different questions.

1. The Persistent Layerrevisit 2. Designing a Specialistrevisit 3. Composing Profile + Specialistrevisit 4. Robustness and Honestyrevisit 5. Portability and Testingrevisit

Final test

10 questions, drawn fresh from the bank every attempt. Pass mark 60%. Unlimited retakes.

Capstone: Your Personal Agent System

Design one complete specialist for a job you actually repeat: role, workflow, required inputs, output contract, and guardrails (including any disclaimers the domain demands). Add a composition note stating how it combines with your own profile, the full precedence order, plus two conflicts you expect and how the order settles them. Finish with a test plan: five representative tasks, each with a written pass criterion, including at least one ambiguous input and one task whose honest answer is 'unknown'.

Rubric: Specialist prompt 50 points: 10 each for role, workflow, required inputs, output contract, guardrails. Composition note 20: the precedence order stated correctly (10), two concrete conflicts settled by it (10). Test plan 30: five representative tasks including the ambiguous and the 'unknown' case (15), pass criteria an outsider could judge (15).

Before you start: Pick a job you do at least weekly, real stakes produce real guardrails. Have your profile from earlier courses open beside you, and collect two or three real inputs from that job to build your test tasks from.

The capstone is self-assessed against the rubric. It's the part you keep: a real artifact, built with everything the course covered.

Back to the Academy →

Business

Business AnalystChief of StaffExecutive AssistantM&A AnalystManagement ConsultantOperations AnalystProject ManagerRecruiter

Finance

AccountantDue Diligence AnalystEquity Research AnalystFamily Office AnalystFinancial AnalystFixed Income AnalystInvestment Banking AnalystPortfolio Analyst

Legal

Contract Review AssistantLegal Due Diligence AssistantLegal Research AssistantParalegal

Marketing

Brand StrategistContent StrategistGEO AnalystMarketing StrategistSEO AnalystSales Strategist

Personal

Career CoachLearning TutorReflection AssistantResearch AssistantTravel PlannerWriting Assistant

Real Estate

Acquisition AnalystAsset Management AnalystCommercial Real Estate AnalystDevelopment AnalystLease AnalystProperty Financial Analyst

Research

Competitive Intelligence AnalystDeep Research AnalystIndustry Research AnalystJournalist ResearcherMarket Research AnalystMedical Research Assistant

Technology

AI Strategy AdvisorCybersecurity Research AssistantData AnalystProduct ManagerSoftware Engineer