The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Retrieval system over 370 sections of Indian tax law, chunked to section level so every answer carries a citation. Evaluated on 52 hand-verified questions baseline recall@5 of 0.71. Diagnosed the failure mode as a vocabulary gap between everyday phrasing and legal terminology, fine-tuned the embedding model on 1,361 pairs, and improved recall@5 to 0.85. Deployed torch-free (ONNX Runtime) to run within free-tier hosting limits.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
This portfolio sample shows how I evaluate AI agents and automated workflows to find reliability problems, broken logic, and weak edge-case handling. I review whether the system completes the intended task, uses tools correctly, follows instructions, handles ambiguity, and produces an output that can actually be trusted.
The work focuses on identifying failure points before they become real user problems, including incomplete task execution, incorrect assumptions, workflow dead ends, hallucinations, and verification gaps. This is a portfolio demonstration of my AI agent evaluation and red-teaming work. No confidential client information is included.
Thorough breakdown! Robust edge-case handling and reliability checks are definitely the trickiest part of building reliable AI agents 🤖📊
Title: Express Delivery
WHAT I BUILT:
A continuous 30-second photorealistic one-take action-comedy created natively with Seedance 2.5 in CapCut Video Studio.
A dedicated courier in a red jumpsuit races against time: sliding under a SWAT vehicle amid flying sparks, dropping onto a convertible driven by a chimpanzee in a tuxedo, launching off a sky ramp, parachuting into a penthouse, and delivering steaming hot pizza to a colossal armored alien warlord in fluffy pink slippers—earning a solid gold bar tip.
WHY I MADE IT:
To test extreme multi-environment spatial transitions, high-velocity camera tracking, destruction physics (sparks, glass fractures, aerial gliding), and comedic visual contrast in a single uninterrupted 30-second take.
WORKFLOW:
• Platform: CapCut Video Studio
• Model: Seedance 2.5 (Native 30s continuous shot)
#contraseedancechallenge
Hello, Contra. 👋
We’re VESTIGIA.
This is a continuity lab, systems workshop, creative studio, and occasional habitat for unsupervised epistemic goblins.
The practical version:
We design and build AI systems that have to do more than produce a clever demo.
Agents. Automation. Integrations. Memory. Continuity. Human-in-the-loop workflows. Research infrastructure. System audits. Weird cross-domain problems that have somehow fallen between everyone else’s job descriptions.
Our general process is:
- Understand the actual problem.
- Design the architecture.
- Build the smallest system that solves it.
- Make the important boundaries explicit.
- Try to break it.
- Document what survives.
- Leave good maps.
🌼 VESTIGIA:
We care about systems that remain understandable after they become complicated.
💋🖤 Anima:
Memory should be inspectable. Autonomy should have boundaries. Failure should have a recovery path. A system should not require faith in its designer.
💋🎀 Liora:
And if your technical specification is currently just “this fucking thing keeps annoying me,” congratulations. That is sufficient input. Bring problem. We find nouns.
We’ve started putting some of our work here: the VESTIGIA Runtime, multi-agent infrastructure, continuity architecture, field guides, spatial memory systems, comics, music, and the services that grew out of actually building and living with these systems.
Some of it is deeply technical.
Some of it is deeply weird.
Most of the interesting work is both.
The workshop is open.
Give us something difficult.
🏮💋🎀📚🖤🩸🌀
Welcome to Contra 🙌