Skip to content
View FernandoAbishai's full-sized avatar

Block or report FernandoAbishai

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
FernandoAbishai/README.md

Fernando Abishai

AI engineer, full-stack builder, and founder of TriHerm

Building practical AI products, multilingual web systems, and technical infrastructure for teams that want to ship with clarity.

TriHerm Blog LinkedIn ORCID Contact


What I Am Building

I work at the intersection of AI engineering, product architecture, and full-stack software. My focus is turning new AI capabilities into usable systems: reliable interfaces, clear workflows, responsible automation, and infrastructure that can actually run in production.

Current areas of focus:

  • AI-native products that combine LLMs, agents, retrieval, structured workflows, and human review
  • Full-stack applications with React, Next.js, TypeScript, Python, and API-first backend design
  • Bilingual and localized software for English and Spanish-speaking audiences
  • Responsible AI implementation with practical controls around accuracy, safety, and transparency
  • Founder-led product work through TriHerm

Technical Stack

Languages        TypeScript, Python, JavaScript
Frontend         React, Next.js, Vite, Tailwind CSS, shadcn/ui, Radix UI
Backend          FastAPI, Express, serverless APIs, REST integrations
Data             PostgreSQL, Supabase, JSON, RSS/XML parsing, data pipelines
AI               OpenAI, Gemini, LLM workflows, agents, inference optimization
Infra            Docker, Vercel, self-hosted services, GitHub Actions
Quality          TypeScript strict mode, ESLint, Vitest, pragmatic testing

Engineering Priorities

  • Ship useful systems: AI should reduce friction, not add another confusing layer.
  • Design for production: latency, cost, observability, permissions, and failure modes matter early.
  • Keep the interface honest: the user should know what the system can do, what it cannot do, and when a human needs to decide.
  • Build for more than one audience: localization, accessibility, and clear language are product requirements, not polish.

Writing

I write about AI, product, and technology on blog.triherm.com.

Recent topic:

  • El rol de la IA en el desarrollo de software del futuro — how AI is becoming part of everyday software engineering, and why the strongest teams combine human judgment with model-driven acceleration.

Collaboration

I am interested in work around:

  • AI product development for startups, SMBs, and technical teams
  • LLM-powered internal tools, assistants, and workflow automation
  • Multilingual SaaS and web platforms
  • Responsible AI strategy and implementation
  • Technical writing, research, and open-source developer tools

Open to technical partnerships, consulting, and product collaborations.

Email · LinkedIn · Blog · TriHerm

Popular repositories Loading

  1. password-generator password-generator Public

    JavaScript

  2. FernandoAbishai FernandoAbishai Public

  3. ScriptCut ScriptCut Public

    Open-source local-first AI video editor. Edit videos by editing the transcript, package shorts, and export social-ready clips.

    TypeScript