Automate Salesforce + X (Twitter)
The enterprise system of record for revenue. The feed where your market thinks out loud. Put an agent between them and the hand-off stops being manual: it reads, decides, acts, and shows its work.
Lead Researcher is a ready-made agent built around Salesforce; point its last step at X (Twitter) to finish this hand-off.
Automations teams run
These are not field mappings. An agent reads the Salesforce side, works out what it means, and only then decides what — if anything — should happen in X (Twitter).
When a lead or opportunity changes in Salesforce…
…an agent can post threads and replies in X (Twitter) — after reading the context and deciding it should.
When a task is due in Salesforce…
…an agent can collect engagement metrics in X (Twitter) — after reading the context and deciding it should.
When a report cycle begins in Salesforce…
…an agent can post threads and replies in X (Twitter) — after reading the context and deciding it should.
When a mention or keyword appears in X (Twitter)…
…an agent can update records and fields in Salesforce — with the reasoning recorded in the run’s receipt.
When a schedule fires in X (Twitter)…
…an agent can create tasks and notes in Salesforce — with the reasoning recorded in the run’s receipt.
Copy this Salesforce → X (Twitter) workflow
Salesforce is reached through a custom-api call to {instance}.my.salesforce.com and X (Twitter) through the twitter-api node. Between them sits the agent, which is the part a field-mapping tool cannot do: it reads the item and decides whether the hand-off is warranted at all.
{
"id": "f7593c64-a0d9-4978-a701-e098324d53a0",
"name": "Salesforce → X (Twitter)",
"nodes": [
{
"id": "5de0e69e-2630-422e-ad4c-a0baae1e0640",
"text": "Poll Salesforce",
"x": 512,
"y": 144,
"isEditing": false,
"type": "trigger-timer",
"icon": "connect",
"category": "trigger",
"isSelected": false,
"parameters": {
"interval": "15",
"unit": "minutes"
},
"description": "Checks Salesforce on a schedule.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "cc981238-ec28-478b-abc7-63e79717f43e",
"text": "Read it and decide",
"x": 512,
"y": 336,
"isEditing": false,
"type": "agnt-agent",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"instructions": "Read the Salesforce item. Decide whether it warrants action in X (Twitter), and explain why."
},
"description": "Decides whether this Salesforce item warrants anything in X (Twitter).",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "860f54b2-1e63-4540-ae05-d058b8031128",
"text": "Act in X (Twitter)",
"x": 512,
"y": 528,
"isEditing": false,
"type": "twitter-api",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"action": "POST"
},
"description": "Interact with Twitter to post, quote, reply, delete, retrieve tweets, search, manage follows, and fetch profiles/conversations.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
}
],
"edges": [
{
"id": "2fd59da6-dd6c-4d73-ae2a-cc9f225bde0a",
"start": {
"id": "5de0e69e-2630-422e-ad4c-a0baae1e0640",
"type": "output"
},
"end": {
"id": "cc981238-ec28-478b-abc7-63e79717f43e",
"type": "input"
},
"startX": 800,
"startY": 168,
"endX": 512,
"endY": 360
},
{
"id": "b7b5425a-ceb8-48f0-a199-681a8edade34",
"start": {
"id": "cc981238-ec28-478b-abc7-63e79717f43e",
"type": "output"
},
"end": {
"id": "860f54b2-1e63-4540-ae05-d058b8031128",
"type": "input"
},
"startX": 800,
"startY": 360,
"endX": 512,
"endY": 552
}
],
"zoomLevel": 1,
"canvasOffsetX": 0,
"canvasOffsetY": 0,
"isTinyNodeMode": false
}Install Lead Researcher
Lead Researcher is a working agent built around Salesforce. Install it, point its last step at X (Twitter), 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
- Get AGNT Community Core. Free, local, no sign-up needed to run a workflow.
- Add both connections to the vault — Salesforce takes one OAuth sign-in, X (Twitter) takes one OAuth sign-in.
- 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.
- Run it once with an approval gate in place. The receipt tells you what it read, what it concluded, and what it changed in X (Twitter).
Salesforce and X (Twitter) — common questions
Can I connect Salesforce to X (Twitter) without writing code?
You can build it entirely from the canvas. Authorise Salesforce with one OAuth sign-in, X (Twitter) with one OAuth sign-in, then tell the agent what hygiene enforced across the pipeline should look like once X (Twitter) is involved. Code is an option for the unusual cases, never a requirement for the common ones.
How is this different from a field-mapping Salesforce to X (Twitter) automation?
Mapping tools move data; this reasons about it. Rather than copying a field into X (Twitter), the agent can weigh what arrived from Salesforce, classify it against criteria you wrote in prose, draft something new, and act only when it is warranted.
Does my Salesforce and X (Twitter) data leave my machine?
Not to us. AGNT runs locally and both sets of credentials are encrypted on your own disk. Outbound traffic goes only to Salesforce, X (Twitter) and whichever model you chose — and pointing that at Ollama or LM Studio keeps everything on your hardware.
What does a Salesforce and X (Twitter) run leave behind?
Every run is recorded end to end — the Salesforce items examined, the decision and its reasoning, the resulting X (Twitter) write. That record is what makes it reasonable to let this run unattended, and what lets you widen its remit on evidence.
