Record or screenshot in a click
Capture your screen or a screenshot with the Chrome extension, while the details are fresh. There are iOS and Mac apps too.
Jam is a strong bug capture tool: a recording with logs, network requests and device details, sent to your tracker in a click. Tore captures the same evidence from the chat widget, then answers the customer and takes the bug to a fix.
Tore opens soon. Join the waitlist and we'll email you the day you can start.
Jam is built to make bug reports clear, fast to file and easy to act on. If what you need is better reports landing in the tracker you already use, it does that job well.
Capture your screen or a screenshot with the Chrome extension, while the details are fresh. There are iOS and Mac apps too.
Each recording carries the available logs, network requests, user events and device details.
Jam AI suggests a title, a summary and repro steps, so the report is ready to triage.
Route reports to Linear, Jira or Slack, or into AI tooling so a coding agent can investigate.
Pick Jam when
Both capture the evidence an engineer needs. The difference is what happens next: Tore also answers the customer, works in your code and tells them when it is fixed.
| Step | Jam | Tore |
|---|---|---|
| Answers customers | Not part of it | Answers from your help center with the article cited, across email, chat widget and Slack. |
| Hands over to a person | Not part of it | Hands over with the full conversation when it is not confident. Anyone can take over at any moment. |
| Bug capturereplay, console, network | Recordings with logs, network requests, user events and device details. | Reports from the chat widget arrive with replay, console and network attached. Bug capture |
| Investigation in your code | Can send a report into AI tooling so a coding agent investigates. | Reads the repository you connect and finds the root cause, down to the file and line. |
| Fix and tests | Not part of it | Writes the fix and runs your tests. Your engineer can request changes in plain words. |
| Pull request for approval | Not part of it | Preps the pull request. By default it waits for your engineer's approval. |
| Customers told it is fixed | Not part of it | Everyone who reported it is told automatically when the fix is live. |
| Model choice | Jam AI writes titles, summaries and repro steps. | The right model for each job, from Claude, Codex, Gemini, Grok and more. You can set it per task. |
| Proactive errors | Not part of it | Errors from your error tracker are grouped by fingerprint and can open an investigation before anyone writes in. |
Based on Jam public pages (jam.dev), checked 2026-10-30. Products change: if we have something wrong, tell us and we will correct it. For plans and pricing, see Tore pricing.
Most teams keep support conversations in one tool and the code in another, joined by a person copying between them. A good bug report makes that hand-off clearer, but someone still carries it across.
Support desk
Intercom, Zendesk and help desks like them. Great at the conversation, then the bug leaves the thread.
Tore
The conversation, the investigation and the reply live together, so nothing is retyped.
Coding agent
AI engineers that start from an issue. Strong at the fix, but the customer never hears from them.
Where Jam fits: it sits between the two sides. It makes the report clear and sends it on to your tracker or a coding agent, and the conversation and the fix happen elsewhere.
The engineering half
Tore reads the repository you connect, finds the root cause down to the file and line, writes the fix and runs your tests. By default it waits for your engineer's approval.
For teams whose QA and engineers file most bugs, Jam makes reports quick to record and clear to read, with a browser extension and iOS and Mac apps. Tore captures the same kind of evidence from your customers, through the chat widget.
You can keep using Jam inside your team. Tore covers the customer side: reports from the chat widget arrive with replay, console and network, and the same thread carries the fix and the reply.
By default it waits for your engineer's approval. Your engineer can request changes in plain words, and Tore revises the fix and re-runs the tests. You set how much it does on its own, per repository, in AI controls.
The right model for each job: a fast model for quick answers, deep reasoning for root causes, a coding model for fixes. You can let Tore choose or set it per task. During early access, you can also bring your own AI keys.
Plans, what is included and how the AI is billed are on the pricing page.
Tore captures the bug from your customers, finds the root cause, preps the fix for your engineer to approve and tells everyone who reported it.