Sricharan Sunkara

Autonomous DFIR Agent That Hunts AI-Using Attackers

An L1 analyst pulls a compromised Windows disk at 2am and has to figure out fast: is this machine breached, and how does the attacker stay on it after a reboot? Sentinel automates that triage. It picks which forensic tools to run, reads the output, writes findings with cited evidence, and a separate rule engine double-checks every claim before a human sees it. Hunts the new class of artifacts AI-using attackers leave behind: local LLM inference servers as persistence, prompt-injection in registry keys, .gguf weights in unexpected places. Zero fabricated findings across 32 reviewed runs.

One-Prompt Vertical Reel Generator with a Human Approval Gate

Synthetic Focus Group as a Service for Canada

Describe your target audience, paste your content. Get instant reactions from AI personas grounded in 30+ real Canadian data sources. A LangGraph pipeline searches a persistent database of 5,000+ census-grounded personas, generates new ones to fill gaps, and runs concurrent reactions via five LLMs through OpenRouter. Aggregates sentiment, optimizes your message, and re-tests it.

Verifiable Agentic Workflows

A framework that treats AI like an apprentice. Upload a document and the system extracts structured data, shows an ingestion plan in plain language, and waits for human sign-off before executing. Three stages, three models, human checkpoints at every step. The system earns autonomy through measured performance: from hands-on review, to auto-approving high-confidence results, to overnight batch processing with exception-only alerts. First domain: HR attendance compliance with policy extraction, points-based discipline, and full audit trail.

Personal AI Assistant That Learns From Research and Evolves

After completing a 10-day OpenClaw course, I kept building. SAI is what came next: a personal AI assistant I use daily - it sends AI news digests via Telegram, reads my Google Calendar, triages email, and summarizes research papers on a schedule. On top of that, it improves itself: SAI ingests papers into a ChromaDB vector database, uses RAG to propose changes to its own operating rules, and waits for per-diff human approval before applying anything. Built with a 5-layer security model, multi-source research fetcher, and tiered knowledge base. Runs on a self-managed Hetzner VPS alongside monitoring, notes, and status dashboards.

10-Phase Methodology for Applied AI Systems

A generalized framework distilled from shipping MaplePulse, Apprentice, and SAI.