EscalAI — Consumer Escalation Agent

A LangGraph-based case manager for consumer complaints, exposed as a self-hosted MCP server (Streamable HTTP) with a web-based simulator standing in for the Alexa+ voice experience.

It only drafts and tracks. It never sends anything on your behalf, and it is not legal advice.

What it does

Walks a consumer complaint through a four-stage escalation ladder:

1. Seller support — a direct complaint letter

2. The platform's grievance officer — required acknowledgment/redress under the Consumer Protection (E-Commerce) Rules, 2020

3. The National Consumer Helpline (1800-11-4000 / consumerhelpline.gov.in)

4. The Consumer Commission — a formal filing at e-Jagriti (e-jagriti.gov.in), tiered by claim value (District / State / National Commission)

At each stage it drafts a letter, tracks the real reply-window deadline, and pauses for you to confirm you've sent it. If the window passes with no reply, it escalates automatically. You can stop a case at any point, or reopen a stopped case to pick back up from where you left it — including a case stopped right at the filing decision.

Related MCP server: Passport Casework MCP Server

Why this architecture

Devpost's hackathon FAQ confirms Alexa+'s gated developer tools are not available to participants this cycle. A self-hosted MCP server plus your own web-based simulator is the explicitly sanctioned stand-in, judged on equal footing — so the "voice assistant" here is a browser page with mic input and speech output, talking to the same MCP tools an Alexa+ skill would call.

How it understands you

Free text goes through /api/understand, which tries Groq (an LLM) first for natural-language routing and field extraction, and silently falls back to deterministic regex matching if there's no GROQ_API_KEY set or the Groq call fails for any reason. The app is fully functional with zero API keys — Groq just makes it understand more varied phrasing.

While a case is in the waiting stage, a second Groq pass handles free-form check-ins — relative durations ("it's been 8 days"), absolute dates ("it's 23 nov"), and fact-grounded questions ("when will I hear back?") — by giving the model real callable actions instead of free-text generation, so an answer is only accepted if it's checkable against the case's actual known facts. Anything it can't safely answer falls back to "not sure, check back" rather than guessing.

Running it

python -m venv .venv
.venv\Scripts\activate        # Windows; use `source .venv/bin/activate` on Mac/Linux
pip install -r requirements.txt
python -m escalation_agent.mcp_server

Then open http://127.0.0.1:8000 in a browser.

Optional, for better natural-language understanding:

$env:GROQ_API_KEY="your-key-here"     # PowerShell
$env:GROQ_MODEL="openai/gpt-oss-120b" # optional override

MCP tools exposed

The simulator

Besides the chat and letter views, the simulator includes:

• Per-case delete — a trash icon on each case in the sidebar, with a confirmation step, that removes the case and its full LangGraph history for good.

• Inline message editing — hover a message you sent and a pencil icon lets you edit it in place, Claude-style: the bubble itself becomes editable, Cancel/Save appear underneath, and saving drops everything that followed in the log and resends. (This replays the chat visually; it doesn't rewind actions like "I sent it" that already moved a live case forward.)

• Copy message — a copy icon on every message, yours or the agent's.

• Resizable split panes, a light/no-signup voice mode with a selectable voice, and a landing page explaining how the agent works and what it does with your data.

Testing

pytest -v

Covers the full escalation ladder, real-clock vs. simulated-clock behavior, the MCP Streamable HTTP endpoint end-to-end, the HTTP API's security hardening (origin checks, content-type checks), and regression tests for every bug found during development (see FRICTION_LOG.md).

Disclaimer

This tool drafts messages and tracks deadlines. It is not legal advice. Stage windows in rules.yaml are verified against public sources as of the dates noted there — always confirm current rules/fees on the official sites (e-jagriti.gov.in, consumerhelpline.gov.in) before relying on a deadline or filing.

License

MIT — see LICENSE.

Repo: https://github.com/shrutijagadale0725-rgb/EscalAI