Project mgmt × CRM
JiraSalesforceAGNT

Automate Jira + Salesforce

The ticket system of record for engineering work. The enterprise system of record for revenue. Put an agent between them and the hand-off stops being manual: it reads, decides, acts, and shows its work.

Install Meeting Follow-Through → Get AGNT free

Meeting Follow-Through is a ready-made agent built around Jira; point its last step at Salesforce to finish this hand-off.

Automations teams run

Unlike field-mapping automation, the step in the middle is an agent: it can summarise, classify, judge and draft, not merely copy values from Jira into Salesforce.

When an issue is created or transitions in Jira…

…an agent can update records and fields in Salesforce — after reading the context and deciding it should.

When a sprint starts in Jira…

…an agent can create tasks and notes in Salesforce — after reading the context and deciding it should.

When a priority changes in Jira…

…an agent can extract report data in Salesforce — after reading the context and deciding it should.

When a lead or opportunity changes in Salesforce…

…an agent can create and update issues in Jira — with the reasoning recorded in the run’s receipt.

When a task is due in Salesforce…

…an agent can transition tickets with comments in Jira — with the reasoning recorded in the run’s receipt.

When a report cycle begins in Salesforce…

…an agent can summarise sprint state in Jira — with the reasoning recorded in the run’s receipt.

The Jira and Salesforce hand-off, in full

The two ends are a custom-api call to {yoursite}.atlassian.net and a custom-api call to {instance}.my.salesforce.com. What makes this different from a zap is the middle node — it forms a view about the Jira item before anything reaches Salesforce.

Jira to Salesforce: poll jira → read it and decide → call salesforce TRIGGER trigger-timer Poll Jira Every fifteen minutes. ACTION agnt-agent Read it and decide Judged against your own rules. ACTION custom-api Call Salesforce POST · oauth 2.0 bearer
Neither Jira nor Salesforce credentials leave your machine — both live in a local vault.
Jira → Salesforcepaste into a new workflow
{
  "id": "0baeae76-3b56-4c43-a697-712b88a9c15e",
  "name": "Jira → Salesforce",
  "nodes": [
    {
      "id": "f2c49904-3663-4488-aadc-8db466318af8",
      "text": "Poll Jira",
      "x": 512,
      "y": 144,
      "isEditing": false,
      "type": "trigger-timer",
      "icon": "connect",
      "category": "trigger",
      "isSelected": false,
      "parameters": {
        "interval": "15",
        "unit": "minutes"
      },
      "description": "Checks Jira on a schedule.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "6793c2d5-1aca-4538-af69-58a1e2b09ba4",
      "text": "Read it and decide",
      "x": 512,
      "y": 336,
      "isEditing": false,
      "type": "agnt-agent",
      "icon": "connect",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "instructions": "Read the Jira item. Decide whether it warrants action in Salesforce, and explain why."
      },
      "description": "Decides whether this Jira item warrants anything in Salesforce.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "c04c4767-f0fd-4fd0-acb6-3373ea6b5de0",
      "text": "Call Salesforce",
      "x": 512,
      "y": 528,
      "isEditing": false,
      "type": "custom-api",
      "icon": "connect",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "url": "https://{instance}.my.salesforce.com/services/data/v59.0/sobjects/Contact",
        "method": "POST"
      },
      "description": "Writes into Salesforce over its API.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    }
  ],
  "edges": [
    {
      "id": "1f944b3e-d474-42c9-aef9-86119df3d32e",
      "start": {
        "id": "f2c49904-3663-4488-aadc-8db466318af8",
        "type": "output"
      },
      "end": {
        "id": "6793c2d5-1aca-4538-af69-58a1e2b09ba4",
        "type": "input"
      },
      "startX": 800,
      "startY": 168,
      "endX": 512,
      "endY": 360
    },
    {
      "id": "abc050f5-7924-47e4-ad9a-a46101944f38",
      "start": {
        "id": "6793c2d5-1aca-4538-af69-58a1e2b09ba4",
        "type": "output"
      },
      "end": {
        "id": "c04c4767-f0fd-4fd0-acb6-3373ea6b5de0",
        "type": "input"
      },
      "startX": 800,
      "startY": 360,
      "endX": 512,
      "endY": 552
    }
  ],
  "zoomLevel": 1,
  "canvasOffsetX": 0,
  "canvasOffsetY": 0,
  "isTinyNodeMode": false
}

Install Meeting Follow-Through

Meeting Follow-Through is a working agent built around Jira. Install it, point its last step at Salesforce, and you have this hand-off without building it from an empty canvas.

Runs on your own machine · See what it does

Build it in AGNT

  1. Get AGNT Community Core. Free, local, no sign-up needed to run a workflow.
  2. Add both connections to the vault — Jira takes one OAuth sign-in, Salesforce takes one OAuth sign-in.
  3. Build the three nodes above, or start from a marketplace workflow and edit it. The agent in the middle is the part worth spending time on.
  4. Run it once with an approval gate in place. The receipt tells you what it read, what it concluded, and what it changed in Salesforce.

Jira and Salesforce — common questions

Can I connect Jira to Salesforce without writing code?

Yes. Jira connects with one OAuth sign-in and Salesforce with one OAuth sign-in, both from the local credential vault. You then describe the job in plain language — “when an issue is created or transitions, update records and fields” — and the agent handles the rest.

How is this different from a field-mapping Jira to Salesforce automation?

The difference shows up on the messy inputs. A rule chain needs every case enumerated in advance; an agent handles meeting actions become tickets automatically the way a colleague would — reading the Jira context, judging it, then writing to Salesforce with the reasoning recorded.

Does my Jira and Salesforce data leave my machine?

AGNT Community Core is local-first, so there is no vendor middleman holding your Jira or Salesforce tokens. The runtime talks directly to both services. Choose a local model and the content of what it reads never leaves the machine at all.

What does a Jira and Salesforce run leave behind?

You get an auditable trail rather than a success flag. It shows the Jira context the agent worked from, the judgment it made about hygiene enforced across the pipeline, and the exact change applied in Salesforce, with approvals attached where you required them.

Give AI a job. Get the proof.