Skip to content

feat(projects): add AgentProbe to featured portfolio #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
soneeee22000 merged 1 commit into from
May 7, 2026
Merged

feat(projects): add AgentProbe to featured portfolio #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions src/lib/data.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,6 +158,16 @@ export const PROJECTS_META = [
demo: "https://greenlens-api.azurewebsites.net",
gh: "https://github.com/soneeee22000/GreenLens.dev",
},
{
id: 12,
featured: true,
emoji: "\uD83D\uDD2C",
title: "AgentProbe",
tags: ["Python", "FastAPI", "Next.js 16", "PostgreSQL", "ReAct", "SSE"],
color: "#C9A96E",
demo: "#",
gh: "https://github.com/soneeee22000/AgentProbe",
},
];

export const SKILLS: Skill[] = [
Expand Down
3 changes: 2 additions & 1 deletion src/messages/de.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/en.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/es.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/fr.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/ja.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/ko.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/my.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/pt.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/th.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
3 changes: 2 additions & 1 deletion src/messages/zh.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,8 @@
"7_desc": "Real-time urban mobility analytics on TimescaleDB + PostGIS + Uber H3. Spring Boot ingestion, Kafka stream processing, Server-Sent Events for live dashboards. Smart-city back-end blueprint.",
"8_desc": "Reference implementation of the BCBS 239 risk-data-aggregation lakehouse pattern on Databricks + Delta Lake + Unity Catalog + dbt-databricks. MIT-licensed, synthetic data only — banking risk-data engineering portfolio piece.",
"9_desc": "Serverless middleware enforcing responsible-AI compliance on LLM applications — PII detection, bias screening, hate-speech filtering, and RAG-powered policy enforcement on top of Azure OpenAI.",
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance."
"10_desc": "Cloud Carbon Intelligence platform estimating CO2e emissions from Azure infrastructure with AI-powered reduction recommendations. Clean Architecture, Azure AI Search semantic factor lookup, 88 automated tests. Built for EU CSRD Scope 3 compliance.",
"11_desc": "From-scratch ReAct Agent Observatory — observe, debug, and benchmark LLM agents with a built-in 8-type failure taxonomy (hallucinated tools, malformed actions, context overflow, goal drift, …) and multi-provider eval harness (Groq, OpenAI, Anthropic, Google, Ollama). Composite scoring (answer + tools + efficiency + reliability), Clean Architecture FastAPI + PostgreSQL backend, Next.js 16 frontend with real-time SSE streaming. 50+ benchmark cases, 81 tests."
},
"skills": {
"label": "04 — SKILLS",
Expand Down
Loading