Features
26 features across support, bug capture, the fix loop, product feedback and the platform underneath. 26 are working today; the rest are marked, not hidden.
Support
Shared inbox
Every conversation, one queue
One place for everything customers send you, whichever way they sent it. Assign it, tag it, snooze it, and see what everyone else is doing without talking over each other.
Email
Your support address, properly handled
Point your support address at Tore and every reply threads correctly, from your own domain, with the bounces and complaints handled rather than silently swallowed.
Chat widget
Support inside your product
A widget that sits in your app, matches your branding, and knows which customer is using it, so nobody has to ask who they are or what plan they are on.
Slack
Work the queue where your team already is
Conversations reach your team in Slack, and replies from Slack land back in the conversation. Nobody has to keep a second tab open all day.
Routing and response targets
The right person, inside the time you promised
Rules decide who gets what. Response targets track whether you are keeping the promises you made, and tell you before you break one rather than after.
Satisfaction and surveys
Find out whether that actually helped
Ask after a conversation, or ask a wider question whenever you want. Ratings attach to the conversation, the agent and the product, so the number always has a story behind it.
Saved replies
Stop typing the same paragraph
The answer your team has already written, keyed to a shortcut and filed where somebody else can find it. Personal drafts stay yours, shared ones belong to the team, and each can be scoped to a single product so the wrong wording never reaches the wrong customer.
Insights
What is actually happening in the queue
Volume, resolution, response times, satisfaction and AI spend in one place, and a risk score that flags a customer drifting toward the exit before they go.
Capture & fix
Bug capture
The whole story, attached automatically
Your customer clicks the thing that is broken and Tore pins it. The report arrives with the replay, the console, the network trail, the browser and the exact element, and it tells them, in plain words, what it stripped out before sending.
Error monitoring intake
Start before anyone complains
Connect your error tracker and Tore starts work on a new error the moment it appears, often before the first customer notices, and usually before anyone writes in.
AI investigations
It reads your code, not just the ticket
Connect your repository and Tore works from the code as it is right now, the file that threw, the commit that last touched those lines, the callers around it. Not a snapshot it memorized months ago, and not a guess from the ticket text.
Fixes and approvals
A change your engineer approves, or doesn't
Tore keeps one registry of risk classes, authentication, billing, migrations, tenant isolation and secrets, and those are locked. A change that touches a locked class is clamped to human review, whatever any other setting says.
Autopilot
Decide what it may pick up on its own
You set what gets worked automatically and what waits for a person, in numbers you can read before you turn it on. Everything else queues quietly rather than acting on a guess.
Product feedback
Feature requests
One board instead of forty conversations
Customers post what they want, other customers vote, and duplicates collapse into one. A support conversation can graduate into a request without retyping it.
Product roadmap
Show people where it is going
A public roadmap fed by the same requests your customers voted on, so the board and the plan can never disagree with each other.
Changelog
Tell them it shipped
Release notes that go out to the people who asked for it, drafted from the fix that actually shipped, then sent once a human approves the wording.
Self-serve
Help center
Answers people can find themselves
Build it three ways: write it, upload what you already have, or pull it in from a URL. Then it is searchable, on your own domain, and used as the source when a reply cites where an answer came from.
Customer portal
Where your customers see their own requests
A signed-in space where a customer can see everything they have reported and what happened to it, alongside your roadmap, changelog and help center.
Guided walkthroughs
Show them, rather than telling them
Step-by-step guides that run inside your product, so the answer to 'where do I find that' is a walkthrough rather than a paragraph.
Status page
One place to say what's wrong
A public page for when something is broken, so your inbox does not fill up with forty people telling you the same thing.
Platform
Integrations
Connect what you already run
Your code host, your error tracker, your issue tracker and your chat tool. The ones that are built are marked; the ones that are not say so.
API and webhooks
Webhooks today, the full API next
Webhooks push events out as they happen, signed and retried. API keys are real, with scopes, live and test modes, and rotation. The public read and write API is versioned and opening next.
Workflows
The repetitive parts, done for you
Rules that act when something happens: tag it, route it, notify someone, escalate it, or reply with something you have already written.
Security and audit
Separated at the database, not by hopeful code
Each organization's data is isolated by the database itself rather than by application logic remembering to filter. Everything consequential is recorded.
For agencies
Many clients, one account, nothing leaking
Run support for several client products from one login, each with its own branding, its own portal and its own data, which cannot cross between them.
AI controls and spend
Know what it is doing, and what it costs
Every piece of AI work is metered and attributed. You can bring your own provider key, cap what may be spent, and stop it entirely without breaking support.