AI Agent Tester - Real-World Tasks

micro1; United States; Remote; USD 34,000 - 62,000; Part time

Job summary

micro1 is seeking an AI Agent Tester to evaluate real-world tasks performed by AI agents. This contractor role is US-based and requires testing from your own phone and accounts, with screen recording and detailed feedback on agent performance.

You will run scenarios such as paying bills, making bookings, and shopping, approving steps, and scoring outcomes. No coding background is required.

Qualifications

• Bachelor's degree required, US-based preferred.
• Experience with AI tools and real-world tasks is beneficial.
• Detail-oriented with strong instruction-following and documentation skills.
• Clear written communication is essential.
• Generalists welcome; domain experts preferred; no coding background required.

Responsibilities

• Run real-life scenarios: bills, returns, email follow-ups, bookings, shopping, groceries, travel, family logistics, outings, and forms.
• Approve or stop the agent at key steps.
• Screen record every attempt.
• Score each run on completion, quality, control issues, satisfaction, and time.
• Share clear written feedback on the agent experience.

Skills

ChatGPT

Muse

AI agents

Attention to Detail

Following Instructions

Screen Recording

Education

Bachelor's degree

Job description

pay

Required Skills
ChatGPT
Muse
AI agents
Attention to Detail
Following Instructions
Screen Recording
About micro1
micro1 is a data lab that helps AI labs & Enterprises train foundational models and agents. We provide frontier evaluations and reinforcement learning environments to improve LLM capabilities, as well as contextual evaluations to monitor and improve AI agents in enterprise settings.

Our AI recruiting agent sources and vets domain experts for our data platform that enables rapid production of high-quality training data. Our research spans high-value, specialized domains (legal, medical, finance, coding, etc.), where expert-level data is the hardest to produce and most valuable for advanced model performance. Our pipeline performance system ensures both quality and velocity.

Role Title: AI Agent Tester — Real-World Tasks

Role Type: Contractor

Location: U.S based

Opportunity Snapshot

Pay: $25-45/hour

Time per task: ~1.5 hours per run (evidence and scoring included)

Project kickoff: Already active.

Onboarding: Within 24–48 hours of being selected, you’ll receive the offer and complete onboarding. You’ll begin tasking as soon as tasks are assigned.

You’ll need: An active personal AI assistant account (Plus tier), active Muse and Dots access, a smartphone that can screen record, and a payment card you can use for test purchases that are reimbursed afterward

Your tasks: Run everyday errands with two AI agents, approve key steps, screen record, and score the results

About the role

AI agents are starting to handle real-life errands: paying bills, booking trips, doing the groceries. We want to know how well they actually do it, from the point of view of a real user. That’s you.

You’ll test two AI agents side by side, using your own accounts on your phone, and tell us what worked, what didn’t, and how it felt.

What you’ll do
Run real-life scenarios: bills, returns, email follow-ups, bookings, shopping, groceries, travel, family logistics, outings, and forms
Approve or stop the agent at key steps
Screen record every attempt
Score each run on
completion, quality, control issues, satisfaction, and time
Share clear written feedback on the agent experience

Who we’re looking for
US-based
, with a Bachelor’s degree
Someone who already uses
AI in daily life
2-3 years
of experience, preferably in engineering, business management, or office/operations
Detail-oriented, great at following instructions and documenting each step
Clear written communication
Generalists welcome, domain experts preferred
No coding or AI background needed

Why you’ll like it
Get paid to use the AI tools you already use
Work entirely from your phone, on your schedule
Have a direct say in how next-generation AI agents get built and improved

How the selection process works
Complete the screening questions
Interview
: 15-30 minutes max
Profile review:
if everything looks good, we present you to the client
Onboarding:
our Talent Ops team will contact you to get you started
Email

Have any questions? See FAQs

Refer and Earn
$100