Context before response.
Read Gmail threads, screen automated mail and collect the right context before preparing any answer.
Policy-aware customer support
Give support teams a grounded answer, a clear decision path and a human handoff when the situation demands one.
A better starting point
A useful answer is tied to real policies. A difficult case reaches the right person. The people responsible for support can see the work.
The platform / 01—03
ResolveHelm connects message intake, business rules, a knowledge base and the operator console. The AI can propose a response; policy controls the next step.
Read Gmail threads, screen automated mail and collect the right context before preparing any answer.
Ground proposed replies in product guidance. Route safety issues, refund demands and exceptions to a person.
Review tickets, read threads, add internal notes and write manual replies from the administration dashboard.
Go to the console ↗A decision you can trace
Explore an illustrative workflow. These examples run entirely on this page and do not contact a backend or send any email.
“Which board size is right for me?”
Model-generated text is checked against deterministic safeguards. Sending depends on the configured operational mode.
“The damaged item caused an injury.”
Safety and sensitive requests take an escalation path rather than receiving unreviewed automated replies.
“Can somebody check my order?”
The administration dashboard provides ticket status, review and manual-reply controls.
Illustrative customer requests
Examples based on categories in the repository's evaluation scenarios. These are interface illustrations, not actual customer data or measured performance.
Find the relevant sizing rule and draft an answer without inventing product specifications.
Route a sensitive product issue to a person instead of promising an automatic replacement.
Use documented assembly instructions and keep the suggested answer within the provided guidance.
Give an operator the question so they can check order details that the system does not know.
The operating principle
Use maintained policy and product information as the basis for decisions before suggesting an answer.
Deterministic rules reject risky promises and give escalations a defined route.
Conversations, tickets, notes and manual actions remain available to the support team.
Operational controls
These describe configuration options from the project, not subscription plans or a claim that a live service is connected.
Examine the decision path while outgoing messages are simulated.
Keep sensitive requests with an operator and preserve a visible ticket history.
Live outbound sending requires explicit configuration and operational signoff.
Frequently asked
A policy-aware AI support automation project using FastAPI, Gmail, Pydantic AI, deterministic business rules, a knowledge base, and a React administration dashboard.
No. The examples are illustrative. Running the actual system requires a configured backend, mailbox authorization and authenticated access.
The documented rule engine escalates refund demands and sensitive cases to a person. A suggested reply is never an authorization to promise an unsupported remedy.
The React console runs separately from the FastAPI service. Configure its backend URL and authorized credentials. GitHub Pages hosts static files and does not run the Python server.
Review the public repository for the backend, dashboard, architecture and test suite.