Cookbook - Engini Developer Docs

Recipes are organized by what you’re trying to do, not by which surface you use - most show cURL, CLI, Python and TypeScript side by side, so pick whichever lane you’re in.

Connect apps

Connect a customer's app (OAuth)

Run the full OAuth handshake from inside your own product - the flow every embedded integration needs.

Sync database objects

Refresh the object catalog, poll until it settles, and choose which tables the connection exposes.

Run tools

REST walkthrough

Zero to executed tool with nothing but cURL.

Page a large catalog

Walk every tool or application with offset/top, and survive rate limits.

Debug a failed tool call

isSuccess vs HTTP status, reading executionInfo, and what each error code means.

Build agents

Scope an agent with a toolset

Decide exactly which tools an agent may call - enforced server-side, not by prompt.

monday.com assistant

The canonical agent loop. Start here if you’re new to agents.

Gmail agent with attachments

File uploads - the model picks attachments by name, your code controls the bytes.

Priority ERP assistant

The same loop pointed at an ERP.

React to events

Receive trigger events on a webhook

Destination, trigger, test event, and a receiver that verifies every signature.

Debug and replay a failed delivery

Read why attempts failed, bring a destination back, replay the gap, rotate a secret safely.

Develop a trigger locally

Stream events to your laptop and rehearse signed deliveries on localhost - no tunnel.

Automate

CLI walkthrough

The journey from the terminal - as a human, and as an agent using resumable gates.

Run Engini in CI/CD

Headless auth, exit-code branching, and JSON output in a pipeline.

Work with large results

Handles, dot-paths and projections - pay for the slice you need, not the payload.

Scripted automation (no LLM)

The SDK as a plain typed API client - the shape of a cron job.

The two integration paths

High-level, with Toolset - bind app → connection once, then two calls per turn:

ts = client.toolset(connections={"salesforce": conn_id})
tools   = ts.tools()                  # provider-shaped tool schemas
results = ts.handle_tool_calls(reply) # resolves connection + runs each call

Low-level - drive the pieces yourself (fetch schemas, wrap, parse calls, execute, format results); see LLM providers. Or skip the model entirely and call client.tools.execute(...) directly. Runnable sources for the agent recipes live in engini-sdk/python/examples - each is a self-contained script (uv run <file>).

​Connect apps