Automate PostgreSQL + Telegram
The production database your reports should come from. The fastest channel between your agents and your phone. Put an agent between them and the hand-off stops being manual: it reads, decides, acts, and shows its work.
Report Assembler is a ready-made agent built around PostgreSQL; point its last step at Telegram 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 PostgreSQL into Telegram.
When a scheduled query runs in PostgreSQL…
…an agent can send messages and alerts in Telegram — after reading the context and deciding it should.
When a threshold is crossed in PostgreSQL…
…an agent can reply to commands in Telegram — after reading the context and deciding it should.
When a message arrives in Telegram…
…an agent can run parameterised queries in PostgreSQL — with the reasoning recorded in the run’s receipt.
When a command is sent in Telegram…
…an agent can write validated rows in PostgreSQL — with the reasoning recorded in the run’s receipt.
When a schedule fires in Telegram…
…an agent can produce report extracts in PostgreSQL — with the reasoning recorded in the run’s receipt.
PostgreSQL to Telegram, setup template
Start with a custom-api call to {host}:5432 and the telegram-api node. Configure the PostgreSQL source payload, the agent input, and the Telegram operation. The sequential template does not implement conditional writes or approval by itself.
This is a schema-checked starting point, not an end-to-end tested automation. Replace every CONFIGURE_ value, choose the operations you intend, connect credentials and map source outputs into later inputs. An edge orders steps; it does not supply a condition, an approval gate or a field mapping. Add and test those controls explicitly before any write. Cloud APIs and model providers may receive data. Keep the workflow inactive until tested with fixtures.
{
"id": "6f962329-86e7-47af-a2c1-fc127bb42a72",
"name": "PostgreSQL → Telegram",
"nodes": [
{
"id": "23ca36b9-a712-4a66-a1f0-804d310e4a5c",
"text": "Run on a schedule",
"x": 512,
"y": 144,
"isEditing": false,
"type": "trigger-timer",
"icon": "connect",
"category": "trigger",
"isSelected": false,
"parameters": {
"fireOnStart": "No",
"scheduleType": "Interval",
"schedule": "Every 15 Minutes"
},
"description": "Setup template for Timer Trigger. This trigger node fires the workflow at specified intervals or at a specific time. Configure credentials, inputs and output mapping before use.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "9cedaf4f-0a81-410b-afe0-ea282b44584e",
"text": "Review source and draft",
"x": 512,
"y": 336,
"isEditing": false,
"type": "agnt-agent",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"agentId": "CONFIGURE_AGENTID",
"message": "Read the PostgreSQL item. Decide whether it warrants action in Telegram, and explain why.\nSource input: CONFIGURE_SOURCE_INPUT. Produce a reviewable draft only; do not take external actions."
},
"description": "Setup template for Agent Chat. Chat with an AI agent from your agent library. Select an agent and send messages to interact with it within your workflow. Configure credentials, inputs and output mapping before use.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
},
{
"id": "59580c5c-2cac-4848-a30c-dc0c1818dcbc",
"text": "Configure destination in Telegram",
"x": 512,
"y": 528,
"isEditing": false,
"type": "telegram-api",
"icon": "connect",
"category": "action",
"isSelected": false,
"parameters": {
"action": "GET_ME",
"botToken": "CONFIGURE_BOTTOKEN",
"apiBaseUrl": "CONFIGURE_APIBASEURL",
"includeRaw": false
},
"description": "Setup template for Telegram API. Use Telegram Bot API from a single AGNT node. Choose an action to validate a bot, send messages/media, edit/delete messages, download files, or call any raw Bot API method. Configure credentials, inputs and output mapping before use.",
"error": null,
"isActive": false,
"output": null,
"outputs": {}
}
],
"edges": [
{
"id": "f2410454-ecf1-476f-a920-a31de95eaca6",
"start": {
"id": "23ca36b9-a712-4a66-a1f0-804d310e4a5c",
"type": "output"
},
"end": {
"id": "9cedaf4f-0a81-410b-afe0-ea282b44584e",
"type": "input"
},
"startX": 800,
"startY": 168,
"endX": 512,
"endY": 360
},
{
"id": "86f1ec31-8247-48fd-a99a-ed9ea140599e",
"start": {
"id": "9cedaf4f-0a81-410b-afe0-ea282b44584e",
"type": "output"
},
"end": {
"id": "59580c5c-2cac-4848-a30c-dc0c1818dcbc",
"type": "input"
},
"startX": 800,
"startY": 360,
"endX": 512,
"endY": 552
}
],
"zoomLevel": 1,
"canvasOffsetX": 0,
"canvasOffsetY": 0,
"isTinyNodeMode": false
}Configure Telegram API
Use Telegram Bot API from a single AGNT node. Choose an action to validate a bot, send messages/media, edit/delete messages, download files, or call any raw Bot API method.
- action — Telegram operation to perform. Current example:
GET_ME. - botToken — Optional fallback Telegram bot token from @BotFather. If omitted, AGNT uses the connected Telegram provider token from Settings → Connections. Current example:
CONFIGURE_BOTTOKEN. - apiBaseUrl — Optional Bot API base URL. Use https://api.telegram.org by default, or a local Bot API server URL. Current example:
CONFIGURE_APIBASEURL. - includeRaw — Include the full raw Telegram API response when available. Current example:
false.
Install Report Assembler
Report Assembler is a working agent built around PostgreSQL. Install it, point its last step at Telegram, and you have this hand-off without building it from an empty canvas.
Runs on your own machine · See what it does
Wiring PostgreSQL to Telegram
- Download AGNT Community Core — free and local-first.
- Connect PostgreSQL with a local endpoint on your own machine and Telegram with an API key pasted into the vault; both land in the local vault.
- Start from a marketplace workflow, or drop a custom-api node and telegram-api onto the canvas with an agent between them.
- Put an approval gate on anything consequential, then run it — the receipt shows what was read in PostgreSQL and what was written to Telegram.
PostgreSQL and Telegram — common questions
Can I connect PostgreSQL to Telegram without writing code?
Yes. PostgreSQL connects with a local endpoint on your own machine and Telegram with an API key pasted into the vault, both from the local credential vault. You then describe the job in plain language — “when a scheduled query runs, send messages and alerts” — and the agent handles the rest.
How is this different from a field-mapping PostgreSQL to Telegram automation?
A field mapping copies values and breaks on the first record nobody anticipated. The middle step here reads the PostgreSQL item in full and decides — whether it matters, how to summarise it, and what belongs in Telegram. Deciding to do nothing is a valid outcome, which no mapping can express.
Does my PostgreSQL and Telegram data leave my machine?
Your credentials stay in a vault on your own disk rather than in someone else’s cloud. The only calls made are the ones the workflow needs: PostgreSQL, Telegram, and your chosen model provider — which can be a local one.
What does a PostgreSQL and Telegram run leave behind?
A receipt: what was read in PostgreSQL, which tools ran with which arguments, what the agent concluded, and what it wrote to Telegram. Anything consequential can sit behind an approval gate so a person signs off before it happens.
