Developer Builds AI Tool Using 107 USCIS Appeal Decisions to Aid Visa Applicants

·1 views

A developer is building PetitionIQ, an AI-powered immigration case preparation platform aimed at reducing reliance on attorneys who charge $5,000–$15,000 per case. The tool uses a retrieval-augmented generation (RAG) pipeline trained on 107 real USCIS Administrative Appeals Office (AAO) non-precedent decisions spanning four visa categories, including EB-1A and EB-2 NIW. Because AAO decisions only cover denied-then-appealed cases, the corpus is inherently biased toward rejection, so the system avoids outputting approval probabilities and instead uses strength indicators with cited decisions. Every response includes a disclosure about the corpus bias, a deliberate design choice the developer frames as an ethical necessity for legal AI. The project comes amid rising USCIS denial rates, with EB-1A rejections reportedly climbing from 25.6% to 46.6% and NIW denials reaching 64.3% in recent data.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

College Student Builds Student Opportunity App Stulo, Now Live on Google Play

A college student with no software engineering background has developed Stulo, a mobile app designed to help students discover internships, hackathons, competitions, and campus events in one place. The app was built using AI-assisted tools like Emergent and Google AI Studio, with the developer relying heavily on debugging, Stack Overflow, and trial and error to overcome technical challenges. Stulo is currently available on the Google Play Store in closed testing, where real users are actively downloading it and submitting feedback. The project has also earned recognition at multiple hackathons and was named among the Top 5 startups at an IIT Roorkee startup event. The developer credits the experience with teaching patience and problem-solving skills that go beyond any formal tutorial or course.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Why C Programming, Over 50 Years Old, Still Matters for Developers

The C programming language, despite being more than five decades old, continues to power critical systems including Linux, embedded hardware, compilers, and device drivers. Its enduring relevance stems from a rare combination of speed, hardware-level control, and cross-platform portability, as C compiles directly to machine code with minimal overhead. Key features such as pointer-based memory management, modular function design, and a compact standard library make it well-suited for low-level and systems programming. However, C also comes with significant challenges, including manual memory management, no garbage collection, and limited runtime safety. Experts argue that learning C is less about using it for every project and more about building a foundational understanding of how software operates beneath modern high-level frameworks.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Apple and Google On-Device AI Models Make Cloud Inference Optional in 2026

Apple's third-generation Foundation Models, unveiled at WWDC on June 8, 2026, and Google's Gemma 4 family, released on April 2, 2026, mark a turning point for on-device artificial intelligence. Apple's model stores around 20 billion parameters in flash memory but activates only one to four billion per request using a technique called Instruction-Following Pruning, keeping RAM usage low. Google's Gemma 4 edge models apply similar efficiency tricks, including per-layer embeddings and mixture-of-experts architectures, to run capable AI within tight memory budgets. Because inference now happens entirely on-device, the marginal cost per query is effectively zero, removing the per-token billing that made agentic and high-frequency AI features economically impractical. The shift also delivers offline functionality and stronger data privacy, since user data never leaves the device to reach a remote server.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Anthropic, OpenAI, Cognition Wage All-Out War for Developer Coding Workflows in 2026

The coding-agent market shifted into an intense platform rivalry in the first half of 2026, with Anthropic, OpenAI, Google, and Cognition all aggressively competing for developer adoption. Anthropic reported annualized revenue near $30 billion by April 2026 and raised roughly $30 billion at a $380 billion valuation, while its Claude Code product line alone grew from $1 billion to $2.5 billion in annualized revenue within a single quarter. Cognition, maker of the Devin agent, raised over $1 billion at a $26 billion valuation in May 2026, citing 50% month-over-month enterprise growth and clients including NASA, Goldman Sachs, and Mercedes-Benz. The competitive edge increasingly lies in model release cadence, with Anthropic shipping new frontier models roughly every six weeks and OpenAI responding with GPT-5.5 in April 2026. Analysts and industry observers warn that developers choosing a coding agent today are effectively betting on which platforms will consolidate and survive the shakeout.

0 comments Read more at DEV Community