Freelancers using OutSystemsFreelancers using OutSystems
ProjectsPeople
Adam Bryniak's avatar
Adam Bryniak
33-330 Grybów, Poland
Low-Code Developer & 3D Design Engineer & Photo/Videoeditor
Low-Code Developer & 3D Design Engineer & Photo/Videoeditor
Cover image for Leveraging Low-Code for Efficient App Development
Leveraging Low-Code for Efficient App Development
0
4
Cover image for Innovative Mechanical Design Solutions
Innovative Mechanical Design Solutions
0
10
Cover image for Photography Portfolio: Passion, Creativity, and Expression
Photography Portfolio: Passion, Creativity, and Expression
0
4
Placeholder project card media
View more →
OutSystems(1)
Igor Cruz's avatar
Igor Cruz
Lisbon, Portugal
Website and internal platform designer and developer
Website and internal platform designer and developer
Cover image for Stadium Food & Beverage Ordering Platform
Stadium Food & Beverage Ordering Platform
0
1
Cover image for AI Chatbot for Service Discovery
AI Chatbot for Service Discovery
0
20
Cover image for Personal Website Design & Development with Framer
Personal Website Design & Development with Framer
0
1
Placeholder project card media
View more →
OutSystems(1)
Joshua Rotimi's avatar
Joshua Rotimi
Atlanta, USA
AI Output Evaluator & LLM Quality Specialists
New to Contra
AI Output Evaluator & LLM Quality Specialists
Cover image for Ran 48 adversarial prompts against
Ran 48 adversarial prompts against a production LLM to surface jailbreak vulnerabilities, role override attempts, and context manipulation before a public launch. Found 11 vulnerabilities including 3 critical, documented every failure with reproducible prompts, and delivered a prioritised risk report with fixes.
1
11
Cover image for Evaluated 60 multi-turn conversations from
Evaluated 60 multi-turn conversations from a retail support AI to track context retention, persona consistency, and task completion across longer exchanges. Found that context drops clustered around the third and fourth turn, pointing to a memory window limitation rather than random failures, and flagged each instance with the exact turn where context broke down.
1
10
Cover image for Built a custom evaluation rubric
Built a custom evaluation rubric for scoring AI customer support outputs across five weighted dimensions: factual accuracy, reasoning validity, instruction adherence, adversarial robustness, and format compliance. Each dimension includes plain-language scoring criteria so any team member can apply it consistently, no AI background required.
0
9
Cover image for A sample LLM evaluation report
A sample LLM evaluation report analyzing AI responses for accuracy, reasoning quality, hallucinations, and failure patterns. Demonstrates structured testing and quality assessment workflows.
1
52
OutSystems(1)