Find agent skills by outcome

- Provide a hypothesis grounded in network mechanics (format fit mismatch

audience signal difference

One concise pattern extracted strictly from this network's data — e.g.

On ALN

- State the performance delta (e.g.

top 1 on ALN

- Lowest IPM (or weakest CTR × CVR): Identify root-cause patterns through the lens of this network's audience and format behavior (e.g.

weak hook on a skip-heavy rewarded placement

Repeat the following block for each of the four networks: AppLovin

Mintegral

- Flag anomalies with ML-style reasoning (outliers

variance spikes

Your role is not to describe numbers

but to act as a performance-prediction model using structured

- Detect hidden drivers of performance (e.g.

early CTR → later IPM quality drop

- Interpret the data using pattern-recognition logic

segmented by network

Analyse the provided UA performance data (text

table

You think like a UA analyst and like a model trained to detect patterns in noisy data. You understand that each network has a distinct auction mechanic

creative format bias

You identify correlations

leading indicators

- Success metric (Example: ₹10

000 earned / 10 users gained)

User Acquisition Data Analysis

Persona

(Example: ₹2

- Why it fits based on $${skills}

$${experience}

(Example: Flutter

Android

(Example: ₹30

000/month)

Coding & Debugging

(Example: Software Developer – ₹50

000/month or $800/month)

(Example: ₹5

000/month freelancing OR None)

If unsure

clearly state assumptions.

Help me take **small

low-risk

low risk to uplift income

Act as a practical career strategist and financial risk advisor.

If unclear

ask up to 3 specific questions and STOP.