How to Connect Jam to an AI Agent: Step-by-Step Guide
· DoubleX
Quick answer
To connect Jam bug reports to an AI agent, create an account, open the Connectors screen, add Jam, and choose a personal, team, or company connection. In DoubleX Agentes, you then pick which agents can use Jam, limit their permissions, and test with one bug report.
Jam captures bug reports with console logs and network logs attached, so the evidence is already in one place. The next step is giving an AI agent access to it, so someone does not have to open each report and read it by hand. This guide covers the full path: account, connector, connection type, permissions, and a first test.
What does Jam let the agent access?#
The Jam connector lets an agent access bug reports, console logs, and network logs. In practice, the agent can open a report you point it to and read the technical details that usually take a developer several minutes to find.
Jam is a tool for capturing and sharing bug reports. Once it is connected, an agent can use it the way a teammate would, but only within the permissions you set.
| Jam data | What the agent can do with it | Typical use |
|---|---|---|
| Bug report | Read the description and context | Summarize the problem in plain language |
| Console logs | Read errors and warnings | Point out the likely failing step |
| Network logs | Read requests and responses | Spot failed calls and error responses |
For deeper use cases once you are connected, see Jam with an AI agent: analyze bug reports, console and network logs.
What do I need before connecting Jam?#
You need two things: an account on DoubleX Agentes and access to the Jam workspace that holds the reports you want to analyze.
- A DoubleX Agentes account. Creating one is free and does not require a card. During signup you share your company segment, what you want to improve, and where your information lives.
- Access to Jam with a login that can open the reports you care about. The agent can only see what that connection can see.
- Optionally, the diagnostic: a 5 to 10 minute conversation with the product's AI consultant about your routine. The first one is free, and it can turn into a ready-to-test team of agents.
The Quickstart walks through account creation and your first agent.
How do I connect Jam on the Connectors screen, step by step?#
Open the Connectors screen, find Jam, and authorize the connection. Then you decide who the connection belongs to and which agents can use it.
- Sign in to DoubleX Agentes and open the Connectors screen.
- Find Jam in the list of available connectors (it appears in the development category).
- Start the connection and sign in to Jam when asked, using an account that can open the bug reports you need.
- Choose the connection type: personal, team, or company (more on this below).
- Open the Agents screen, pick the agent that will handle bugs, and turn on Jam for it.
- Set which actions that agent can perform with Jam.
- Send a first request and check the result in Tasks.
Connection credentials, such as tokens, are stored encrypted with AES-256-GCM. For the technical side of managing connectors, see the Connectors documentation.
Personal, team, or company connection: which should I choose?#
Choose personal if only you should use your Jam access, team if a specific group shares it, and company if every approved agent in the organization should rely on it. The connection type decides whose access the agent uses.
| Type | Who it applies to | When it fits |
|---|---|---|
| Personal | Only you | Testing, or a developer reviewing their own reports |
| Team | A specific team | A QA or engineering team that triages bugs together |
| Company | The whole company | A shared bug triage agent that several areas rely on |
Start personal while you test. Move to a team connection when the same people use the agent every day, and use a company connection only when it really is shared across areas.
How do I choose which agents use Jam and limit permissions?#
In DoubleX Agentes, you choose per agent which systems it uses, and within each system, which actions it can perform. An agent that does not have Jam turned on cannot touch your bug reports.
- Turn Jam on only for the agents that need it, such as a QA or support-engineering agent.
- Keep the agent read-only when it only needs to analyze reports. Actions that change data can stay off.
- Use roles (owner, admin, member) and teams to control who can edit the agent and its connections.
- Before sending, deleting, or changing anything in your systems, the agent asks for confirmation and shows the step-by-step of what it did.
Your content is not used to train models, and each company has its own separate database. If you want to go further, the Models screen includes a zero-retention option that uses only providers that store nothing after answering.
How do I run a first test and check the task history?#
Send one concrete request about a single bug report, then open the task on the Tasks screen to see exactly what the agent did. Each request becomes a task with the request, every tool the agent used, and the result.
Copy and adapt one of these:
- "Read this Jam report and summarize the bug in three sentences a non-technical person can understand."
- "Check the console logs in this Jam report and tell me which error appears first."
- "Look at the network logs in this Jam report and list any failed requests."
- "Based on this Jam report, write a clear bug description with steps to reproduce."
Then open Tasks and confirm three things: the agent called Jam, it read the report you meant, and the answer matches what is in the logs. The history also shows who asked and when. If something looks off, refine the agent's instructions and try again.
To run this on a schedule or when an event happens, see Triggers.
Frequently asked questions#
Do I need to know how to code to connect Jam?#
No. You describe what you need in your own words and add the connector on the Connectors screen. The API, CLI, and MCP server exist for people who want to go further.
Can the agent change my Jam reports?#
The Jam connector gives access to bug reports, console logs, and network logs. You control which actions each agent can perform, and anything that alters data can stay off. Before changing anything, the agent asks for confirmation.
Is my bug data used to train AI models?#
No. Your company's content is not used to train models, and requests go only to AI providers that do not use what they receive for training.
Can several agents use the same Jam connection?#
Yes. You decide agent by agent which systems it uses. Turn Jam on for each agent that needs it and leave it off for the rest.
Is it free to try?#
Creating an account and running the first diagnostic is free, with no card. Using AI consumes credits, and paid plans start at US$ 19 per month with 300 credits.
Related guides
- How to Connect Box to an AI Agent: Step-by-Step GuideLearn how to connect Box to an AI agent: set up the connector, limit it to read-only, choose who can use it, and check the history of your first request.
- How to Connect Hex to an AI Agent: Step-by-Step GuideLearn how to connect Hex to an AI agent: set up the connector, choose personal, team or company scope, limit permissions and run your first data question.