Agent setup guide
Frost & Heat Alert
Every afternoon: the next 48 hours for each field or greenhouse against your frost and heat limits by crop and stage, with your playbook steps when it matters.
What it does
Every afternoon: the next 48 hours for each field or greenhouse against your frost and heat limits by crop and stage, with your playbook steps when it matters.
- Every early afternoon, reads your fields and greenhouses (up to 15) and gets the National Weather Service forecast for each.
- AI checks the next 48 hours against your frost and heat limits by crop and growth stage (or a field's own limits), flagging “risk” at the limit and “watch” within 2°F.
- When a limit is met, the crew gets a Slack alert and the crew lead an email: field, forecast value, your limit and your own playbook steps.
- No risk: nothing is sent.
What it needs
- A paid plan (agents run live on paid plans).
- An AI provider key (Settings → AI Providers).
- Google Sheets and Slack, connected in Settings → Integrations, plus an HTTP / Custom API connection to https://api.weather.gov (free, no key).
- A fields tab with each location's Lat and Lon, crop and growth stage, and your written limits and playbook.
What it doesn't do
- It's a point forecast (US only), not a field sensor or microclimate model: cold pockets and low spots can be colder than forecast.
- It doesn't control irrigation, vents or heaters; the crew acts on the alert.
- It sends only your own playbook steps and never invents limits or protection advice.
Availability and plans
Available
Its workflow is built and tested, and every app it needs is live. You can get it and set it up now.
Included free on the Enterprise plan; on other paid plans it's a one-time purchase per workspace (the price is on the Agents page). The Agents page in the app always shows its current status.
Before you start
- A paid plan: agents run live, and the Free plan only runs Dry Runs.
- An AI provider key (OpenAI, Anthropic, Google and more) in Settings → AI Providers. AI usage is billed by your provider.
- These apps, connected in Settings → Integrations: Google Sheets, HTTP / Custom API and Slack.
- Nothing to send: the agent runs on a schedule.
- About 20 minutes.
Set it up step by step
Get the agent first (buy it, or it's already yours when your plan includes it), then in Agents → My agents press “Set up this agent”. That creates the agent's workflow in your workspace (it counts towards your plan's workflow limit) and opens the canvas with a setup checklist above it. Each item links to the exact place to go and ticks itself off when it's done.
1. Connect your AI provider
The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.
2. Connect Google Sheets
Connect the Google account that can open your fields sheet (Settings → Integrations → Google Sheets).
3. Connect the National Weather Service (HTTP / Custom API)
In Settings → Integrations, add an HTTP / Custom API connection named “National Weather Service” with base URL https://api.weather.gov and Authentication “None”. The NWS API is free, public domain and needs no key; it covers US locations only.
4. Connect Slack
Connect the Slack workspace your crew uses (Settings → Integrations → Slack).
5. Pick your fields sheet
Open “Read your fields and greenhouses” and pick your account, spreadsheet and tab.
| Setting | What to enter | In step |
|---|---|---|
| Google account (fields) | The Google account that can open your fields sheet. Pick your connected Google Sheets account. | “Read your fields and greenhouses” |
| Fields spreadsheet | Paste the link of the spreadsheet with your fields. | “Read your fields and greenhouses” |
| Fields tab | The tab with one row per field or greenhouse (Field, Lat, Lon, Crop, Stage), e.g. “Fields”. | “Read your fields and greenhouses” |
6. Set up the weather lookups
Open “Find the forecast office” and “Get the forecast”: pick the National Weather Service connection in both, and in Extra headers replace the placeholder with your business name and a contact email.
| Setting | What to enter | In step |
|---|---|---|
| Weather connection (forecast office) | The HTTP / Custom API connection with base URL https://api.weather.gov and Authentication “None”. Pick your connected HTTP / Custom API account. | “Find the forecast office” |
| Your contact for the weather service | In Extra headers, replace the placeholder with your business name and a contact email. The National Weather Service asks every app to identify itself this way and may block requests that don't. It starts as “[YOUR BUSINESS NAME AND CONTACT EMAIL]” until you replace it. | “Find the forecast office” |
| Weather connection (forecast) | The HTTP / Custom API connection with base URL https://api.weather.gov and Authentication “None”. Pick your connected HTTP / Custom API account. | “Get the forecast” |
| Your contact for the weather service (forecast step) | In Extra headers, replace the placeholder with your business name and a contact email. The National Weather Service asks every app to identify itself this way and may block requests that don't. It starts as “[YOUR BUSINESS NAME AND CONTACT EMAIL]” until you replace it. | “Get the forecast” |
7. Paste your limits and playbook
Open “Check frost and heat risk” and replace the placeholder with your limits by crop and stage and your playbook steps.
| Setting | What to enter | In step |
|---|---|---|
| Your limits and playbook | Replace the placeholder with your farm name, default frost and heat limits by crop and growth stage, and the steps the crew takes for each risk. Only your steps are sent. It starts as “[PASTE YOUR FARM NAME, DEFAULT FROST AND HEAT LIMITS BY CROP AND GROWTH STAGE (E.G. STRAWBERRIES IN BLOOM: 30°F; TOMATOES: 35°F; LETTUCE: HEAT ABOVE 85°F), HOW FAR AHEAD TO WARN, AND YOUR PLAYBOOK STEPS PER RISK (COVER ROWS, RUN FROST-PROTECTION IRRIGATION, VENT OR SHADE GREENHOUSES, HARVEST EARLY) HERE]” until you replace it. | “Check frost and heat risk” |
8. Pick who gets the alerts
Open “Alert the crew in Slack” and pick your account and channel, then “Email the crew lead” and enter the address.
| Setting | What to enter | In step |
|---|---|---|
| Slack account | The Slack workspace your crew uses. Pick your connected Slack account. | “Alert the crew in Slack” |
| Crew channel | Where frost and heat alerts go, e.g. #farm-crew. Turn notifications on. | “Alert the crew in Slack” |
| Crew lead's email | Replace the example address with who gets the alert by email (up to 5 addresses, comma-separated). It starts as “crew-lead@your-farm.example” until you replace it. | “Email the crew lead” |
9. Test it with Dry Run
Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.
10. Switch the trigger on
Open the trigger, set your time zone and switch the schedule on. It runs every day at 13:00.
How it works
The agent is a normal workflow with 11 steps (1 AI step). You can open, edit and monitor it like any other workflow.
- Every day at 13:00 — Runs on a schedule (cron 0 13 * * *, UTC — change it in the trigger's settings). Runs every early afternoon, leaving time to cover rows or set up irrigation before evening. Set your time zone on the trigger.
- Read your fields and greenhouses — Google Sheets: Read rows. Reads your fields tab: one row per field or greenhouse with Lat, Lon, crop, growth stage and (optionally) its own frost and heat limits.
- Each field or greenhouse — Repeats the steps below for each item (up to 15 per run). Gets the forecast for every field or greenhouse (up to 15).
- [For each item — “Each field or greenhouse”] Find the forecast office — HTTP / Custom API: Send a request. Asks the National Weather Service which forecast grid covers this field (from its latitude and longitude).
- [For each item — “Each field or greenhouse”] Get the forecast — HTTP / Custom API: Send a request. Reads the National Weather Service 12-hour forecast periods for this field (temperature, chance of rain, wind and the forecast text).
- Check frost and heat risk — AI step (runs on your AI provider key). AI checks the next 48 hours (the forecast's first 4 periods) for each field against your limits by crop and growth stage and, when one is met, lists your own playbook steps for it.
- Frost or heat risk? — Decision: picks the branch to follow. A risk or watch alerts the crew in Slack and by email. No risk: nothing is sent.
- No risk — Kept in the run history. Branch: No risk. No field is near its limits in the next 48 hours: nothing is sent. The run history keeps the check.
- Alert the crew in Slack — Slack: Post a message. Branch: Risk. Posts the alert with each field, the forecast value, your limit and your playbook steps to the crew channel.
- Email the crew lead — Sends an email from your workspace's sender. Emails the same alert to your crew lead or farm manager (up to 5 addresses), so it reaches someone away from Slack.
- Crew alerted — Kept in the run history. The run history keeps the forecast check and the alert.
Test it with Dry Run
Press Dry Run in the canvas. The agent runs on the sample data stored on its trigger (the “Sample data for Dry Run” box), so you can check every step's output before anything is live.
- Nothing is sent or written: app actions, emails and Slack posts are simulated, and AI steps don't call your AI provider.
- For-each loops repeat only the first 3 items.
Go live
- Open the trigger, set your time zone and switch the schedule on. It runs every day at 13:00.
- Scheduled runs start only once the schedule is activated, and can't repeat faster than your plan's minimum interval.
- The setup checklist adds a “paid plan” item before activation: live runs need a paid plan (the Free plan only runs Dry Runs).
- When every checklist item is done and the trigger is on, the checklist says “Live — this agent is running”. Follow its runs in the workflow's History tab and in Analytics → Agents.
Questions
Where does the weather come from?
The US National Weather Service API (https://api.weather.gov): free, public domain and no key, through an HTTP / Custom API connection. Two calls per location: one finds the forecast grid for the latitude and longitude, the second reads the 12-hour forecast. US locations only. NWS asks every app to name itself and a contact in the User-Agent header, which is why you add yours in setup. Its forecasts are general area forecasts, not on-site measurements.
What should the fields sheet look like?
One row per field or greenhouse with a header row: Field, Lat, Lon (named exactly so, up to 4 decimals), Crop and Stage, plus optional Frost limit and Heat limit columns that override the defaults for that field. Update the stage as the season moves.
Is it a frost sensor?
No. It reads a point forecast for each location, which can miss cold pockets and low spots. Keep your thermometers and sensors; this is an early warning so the crew has time to act.
Troubleshooting
- “No AI provider connected” or a rejected key: connect or fix the key in Settings → AI Providers, then press Test there.
- A checklist item stays unticked: the setting is still empty or still contains its placeholder text. Open the step from the checklist and fill it in.
- An app step fails with “Needs reconnect”: the account's access was revoked or expired. Reconnect it in Settings → Integrations.
- Slack says the app isn't in the channel: in Slack, type /invite @Fluxo Flow in that channel (always needed for private channels).
- It didn't run at the expected time: the schedule must be activated, and its time is in the trigger's timezone.
- A step failed: open the run in History and check that step in the Trace tab for the error and what it received.
Generated from the agent's own workflow, so it always matches what the agent does. Last updated .