this+that for engineers
Bug reports reach your coding agent. You stop writing the tickets.
A bug arrives as an email to support, or a message in a thread. It becomes a task, routes to whoever owns that code, and goes to an agent, in the browser or on that engineer’s own machine through Claude Code or Codex. A draft pull request comes back for review, and the person who reported it gets an answer when it ships.
Connections are ordinary OAuth, with scopes you approve and can revoke. SOC 2 Type I as of July 31, 2026, with Type II underway, and CASA Tier 2. Your data never trains a model, whichever provider runs the inference. How we handle your data →
The work doesn’t start in the tracker
A coding agent takes a well-specified issue and returns a pull request, and it does that well. But the well-specified issue has to come from somewhere, and on most teams it comes from a person reading a support inbox and translating.
The report needs translating
Three sentences, a screenshot and a guess at the cause, with the repro in the fourth reply. Turning that into an issue takes ten minutes and knowledge of the codebase, which is why it lands on an engineer.
The reporter hears nothing
The fix ships, but closing the loop means finding the original thread, and it’s in a system nobody has open. So the same bug gets reported twice, and the second report goes through triage from the start.
Message in, reply out, agent in the middle
Delegation itself needs no setup: open a task, pick an agent, send it. The pipeline below is what you build around it, and it’s the version we run against our own support inbox. Which inbox, who owns what and where a person approves are your call.
- 1
The report lands
The AI reads every message and tells a bug report from a billing question. Point the workflow at one address or one channel and its job gets easier.
- 2
It becomes a task, or an issue in your tracker
A task in this+that, or a Linear or Jira issue, with the original thread attached either way. No engineer typed any of it.
- 3
It routes to whoever owns the code
Assignment comes from what you’ve written in the Brain about which engineer owns which area. We ship no opinion about who owns your code.
- 4
The owner hands it to an agent
A cloud agent starts in the browser. A local one goes through our desktop companion to Claude Code or Codex on the owner’s machine, in its own git worktree, so their branch stays untouched.
- 5
A draft PR comes back
The review request goes wherever your workflow sends it. Nothing merges without a person deciding to commit it.
- 6
The reporter gets an answer
Once the review is approved, a workflow replies to the original email.
You describe the loop, you don’t wire it
The steps above are one workflow, and you get it by saying what you want. The assistant builds the flow, picks the actions and asks about the parts it can’t infer.
Hi, tell me what you’d like to automate, in plain words. I’ll ask a couple of quick questions, set it up, and you can run it right here.
Prefer to build it yourself? Create manually
When an email arrives at support@, work out whether it’s a bug. If it is, open a Linear issue with the thread attached and assign it to whoever owns that area of the code in the Brain. If the report has no reproduction steps, reply asking for them first.
It comes back as steps you can read, reorder and edit, and you review every step before it runs.
Automate one step, or all of them
Every step in that loop is optional, and each one below is a complete workflow on its own. Keep the judgment calls with a person and automate the parts around them.
Just the routing
“When a bug report arrives, assign it to whoever owns that area of the code and leave it in my tracker.” Nothing is drafted or sent, and you still decide what to do about it.
Just the missing details
“If a report has no screenshot or reproduction steps, reply and ask for them before it reaches anyone.” The clarification round happens without an engineer.
Just the reply when it ships
“When the fix goes out, reply to whoever reported it.” The part everyone means to do and nobody does, and it needs no agent touching your code at all.
The whole loop
Report to routed issue to draft pull request to reply. Worth building once you trust the pieces, rather than on day one.
On your machine, on your subscription
A cloud agent is the right pick when nobody wants to install software. Or the agent works in your own checkout, on your hardware, through Claude Code or Codex, under the AI subscription you already pay for. Your repository stays where it is.
If even the model calls have to stay home, point delegation at a Qwen model served by Ollama on the same machine. Then the code, the model and the work never leave the laptop. That works today.
The engineering tools it already connects to
Each one is reachable from a workflow as an action step, so the loop doesn’t stop at the tracker.
Browser automation
For the internal tool with no API. A workflow drives your signed-in browser in a tab you can watch, refuses credential fields, and confirms each click or keystroke the way you set it up.
Learn more →GitHub
A built-in MCP server: create issues, check PR status, comment and query issues by label or assignee. Triggers scope to one repository, so a flow for one service ignores the rest.
Learn more →Linear
Find, create and update issues, projects and comments through Linear’s own MCP server.
Learn more →Jira and Confluence
Through Atlassian Rovo, an email or a Slack message becomes a Jira ticket, a Confluence page or an assignment.
Learn more →
Notion
Release notes draft themselves from the descriptions on merged PRs.
Learn more →Sourcegraph
Built-in code search that finds where a reported bug lives and hands that context to the engineer with the ticket.
Learn more →Glean and Snowflake
Built-in search and warehouse queries against your own instances, answered in the thread that asked.
Learn more →DoBox over MCP
It runs the other way too: your own agents read and write DoBox over MCP from your terminal.
Learn more →
The channels reports arrive on
A bug flagged in chat gets the same treatment as one sent to support.
Learn more →The same loop without a repository
Hand an agent a report, an analysis or a piece of research and it works on the real file and comes back for review, with the result attached to the task. It’s the same pipeline: it arrives as a message, a person approves what comes back, and whoever asked gets an answer.
Point it at the inbox your bugs actually arrive in.
Connect an account and watch the reports already buried in it become tasks. Free for 30 days, no credit card required. Then $35 per user per month, or $29 billed annually.