Make

Overview

The coSPEC Make integration lets you start agent runs from any scenario. Because Make has a 5-minute module timeout and agent runs can last much longer, results arrive in a separate scenario via the "Run Finished" trigger — not in the same scenario that started the run.

Prerequisites

• coSPEC account with an API key (csk_live_...) — see API Keys
• Make.com account (any plan)

Install

coSPEC is currently a private app (invite-only).

1. Click the button above
2. Click Install
3. The coSPEC app appears in your Make.com account
4. Search "coSPEC" when adding modules to scenarios

Connect Your API Key

1. In a scenario, add a coSPEC module
2. Click Create a connection
3. Paste your API key (csk_live_...)
4. Make validates the key automatically

Where to find your key: Dashboard → API Keys → Create API Key

Modules

Create Run

Agent runs last minutes to hours. Make.com has a 5-minute module timeout, so a single scenario can't wait. Results arrive via a separate scenario with the "Run Finished" trigger.

Scenario 1 — Start the run:

[Your Trigger] → [coSPEC: Create Run]

Scenario 2 — Receive results:

[coSPEC: Run Finished] → [Your Actions (Slack, Jira, etc.)]

When you add the "Run Finished" trigger, Make automatically registers a webhook with coSPEC. When any run finishes, coSPEC delivers the results to that webhook — you never see or copy any URL.

Correlating across scenarios: Use the Metadata field on Create Run to pass context (e.g. slackChannel: C123). The metadata is echoed in the Run Finished payload so Scenario 2 can route results back to the right place.

Get Run

Action module — fetch a run by ID. Returns the full run object with all output fields. Use it in Scenario 2 after the Run Finished trigger if you need additional run details.

Run Finished Trigger

Instant trigger — fires when a run reaches a terminal state.

• Events: Completed, Failed, Cancelled (multi-select, default: all)
• The webhook is registered automatically when you add the trigger
• Delivers the full run object including outputs, usage, and metadata

Output Fields

These fields are available from the Run Finished trigger (Scenario 2) and the Get Run module — not from Create Run (which only returns the run ID).

The run output is parsed into convenience fields for easy mapping. These extract the first output of each type — for example, PR URL is the first pull request. If a run produces multiple outputs, use the raw Outputs JSON field for the full list.

Failed Runs

When a run fails, the Status field is failed. Two additional fields help you diagnose:

• Fail Reason — why the run stopped: max_turns, max_cost, timeout, or error
• Error — error details (message and code) when failReason is error

These fields are available in the Run Finished trigger payload and Get Run output.

Troubleshooting