# DEV Submission Build With Hermes Agent

Submission Template Challenge: Build With Hermes Agent Project: CompliScore AI compliance health checks for Indian startups Repo/live-demo: https://github.com/nehaprasad-dev/hermes-scout What I built CompliScore gives Indian startup founders a compliance score out of 100 in under a minute - overdue GST filings, MCA returns, penalty exposure, and a plain-English action plan. The upgrade for this challenge: I replaced the one-shot Groq summary with a Hermes Agent reasoning loop that plans an investigation, calls deterministic compliance tools, and writes a prioritized report - with a collapsible agent trace so judges can see the agentic work. Why an agent loop fits here Compliance analysis is conditional. A company with overdue GST needs a filing-calendar deep dive; one with active notices needs notice triage; a clean company needs a light touch. A single prompt guesses all of this at once. An agent that calls tools based on what it finds produces tighter, grounded reports. Hermes Agent integration Scan → computeHealth (deterministic score) → Hermes Agent loop (plan → tool calls → report) → agent trace in UI ↓ on failure Groq one-shot → static fallback Four tools exposed to Hermes (scores never hallucinated): Tool Purpose score_company Canonical score, risk level, pending tasks estimate_penalty GST / MCA / notice penalty breakdown filing_calendar GSTR-3B, GSTR-1, MCA deadlines (90-day horizon) classify_notices Severity labels for pending government notices The agent runs over Hermes's OpenAI-compatible /chat/completions API with function calling — self-hostable via vLLM, LM Studio, Ollama, etc. Transparency: Every successful agent run returns an agentTrace — plan steps, tool names, compact result previews — rendered in a collapsible panel under the AI action plan. Reliability: Three-tier fallback (Hermes → Groq → static). Scans never break. Tech stack Next.js 16 (App Router), TypeScript, Tailwind v4 Hermes Agent (OpenAI-compatible tool-calling loop) Groq fallback ( ll