Creating an Automation with the Advanced Builder

The advanced builder is the single place you both create and edit an automation. It gives you full control over every part — identity and model, trigger, knowledge, capabilities, and guardrails — with a live test panel so you can chat with your automation before turning it loose. It follows a deliberately safe lifecycle: you first deploy the automation in dry-run mode (read-only tools), test it, and only then promote it to production to enable write-capable tools.

Open it from the Advanced builder card on the Automations tab, or go directly to /automations/builder. To change an existing automation, use the Edit button on its detail page — it opens the same builder with that automation loaded (see Editing an Automation). There is no separate "quick" create or edit form; the builder is the one canonical surface, so nothing you configure here is missing when you come back to edit.

How the builder works

• A step rail on the left shows the four steps and each step's completion state. You can jump between steps freely — nothing forces a strict order.
• A footer bar carries Back and the primary action button. The primary button changes as you progress: Next → Deploy as Dry Run → Promote to Production → View agent.
• Your draft autosaves in the browser on every change, scoped to you and your tenant. Close the tab, come back later, and your work is still there — including unsaved edits to an already-deployed automation.

The builder with the step rail on the left, Step 1 active, and the footer navigation bar.

Step 1 — Basics

Identity, model, trigger, and the system prompt.

1. Agent name (up to 60 characters) and Description (up to 240 characters) — both fields show a live character counter.
2. Model — pick one of the five model tiles: Fable 5 (claude-fable-5, \(\)) for frontier reasoning on the hardest tasks; Opus 4.8 (claude-opus-4-8, $$$) — the default, and the strongest general reasoning; Sonnet 5 (claude-sonnet-5, $$) for near-Opus quality at Sonnet speed; Sonnet 4.6 (claude-sonnet-4-6, $$) for balanced depth, speed, and cost; and Haiku 4.5 (claude-haiku-4-5, $) for the fastest, cheapest, high-volume work. Model choice is not plan-gated — every tile is selectable on any plan that has Automations enabled; the difference shows up in what each run costs you. Sonnet 5 and Sonnet 4.6 bill at the same credit rate, so prefer Sonnet 5 unless you have a reason to stay on 4.6. The dollar signs are relative cost tiers, not prices; you pay in credits based on actual usage (or on your own Anthropic bill under BYOK). If an automation was saved with a model that has since been retired (for example Opus 4.7), it shows as a "Retired option" tile and keeps running — and billing — until you pick a current model.
3. Trigger — choose one of the three trigger types; each shows its own editor:
   • On demand — optionally set a Default context: the first message the agent receives when a run starts without a caller-supplied message. You can also flip Expose to external AI harness, which lets your connected AI assistant discover and run this automation through StackJack's MCP tools (off by default, and only available for on-demand automations).
   • Scheduled — build the schedule in Quick mode (days of the week + time + timezone) or switch to Advanced for a raw 5-field cron expression. A live preview shows validation results and the next fire times. Consecutive firings must be more than 60 seconds apart — for higher-frequency triggering, use a webhook instead.
   • Webhook — choose a Payload mode: None (discard the request body), Full context (pass the body to the agent verbatim), or Selected fields (extract specific dotted JSON paths). Optionally set a maximum payload size (server default 32 KB, hard ceiling 64 KB). The webhook URL and secrets are issued after the automation is created.
4. System prompt / Role — the agent's standing instructions (markdown supported). Two helpers are built in:
   • AI Assist — opens a dialog that generates a suggested prompt from your draft so far; accept, regenerate, or cancel.
   • A live character counter shows how long your prompt is.

A live configuration preview in the right sidecar reflects your choices as you type.

Step 1 with the model tiles and the trigger type selector.

Step 2 — Knowledge and context

Durable context merged into the agent's system prompt on every run — brand guidelines, escalation policies, SLA thresholds, and similar reference material.

• Core knowledge — a free-text area (markdown supported) with a live character counter. Your instructions and all of an automation's knowledge share one system prompt, capped at about 100,000 characters; if the combined total goes over the cap the automation is rejected when you save it, so split or trim your sources and prefer summaries over raw document dumps.
• Add URL — attach a web page as a knowledge source. The dialog takes a label and URL and offers a Preview that shows the page title, estimated tokens, and extracted character count before you attach. Page content is fetched once when you attach it and the extracted text is injected into the prompt on every run. You can add a URL at any time; before the automation exists it stages in your draft and is attached when you deploy. Each saved URL source shows when it was last fetched and has a Refresh action to re-fetch the current page in place when the content changes.
• Paste text block — add a labeled block of text as a source. The label "Core Knowledge" is reserved for the core knowledge field and can't be used.
• Attached sources — the list of everything attached, with per-source delete.
• Upload document — attach PDF, Word (.docx), Excel (.xlsx), PowerPoint (.pptx), and text files (.txt, .md, .csv, .json, .log, .yaml / .yml, .xml, and similar) as knowledge sources; each file's text is extracted server-side and inlined into the prompt on every run. Up to 5 files at a time, 50 MB each. Documents up to 10 MB stage in your draft before the automation exists and attach when you deploy; documents over 10 MB need the automation to exist first, so deploy it and then upload them. Legacy binary Office (.doc, .xls, .ppt) isn't supported — paste that content as a text block. See Knowledge File Uploads.

Step 3 — Capabilities

What the agent is allowed to do.

Anthropic native tools

Three optional Anthropic-hosted capabilities, shown as compact square tiles (each with a toggle; hover a tile for its full description):

Native tools run on Anthropic's side and are available to every plan — they are never plan-gated.

Custom (MCP) tools

You choose how the agent's tool access is defined first, then which tools it applies to:

• Allow-list mode (the default, best for most automations) — the agent may call only the tools you pick, and nothing else. Everything you don't select is denied. Pick tools with the search-first picker (search, connector/category groups, read/write chips, and presets like All Tools, My Plan, Read Only, Write). Your current selection is always shown as a chip strip.
• Deny-list mode (for power users) — the agent may use everything it's entitled to except the tools you block. Reach for this when it's easier to describe the few things an agent must never touch than to enumerate everything it may.

Tools above your current plan for a connector appear as locked rows that show the plan they require, so you can see what an upgrade would unlock instead of them silently disappearing. Locked tools can't be selected.

Required tools (optional) — from your callable set, pick tools the agent should use at least once per run (for example, always post its findings back to a ticket). This is a prompt-level nudge, not a hard requirement: a run is never blocked or failed for skipping one. Because you pick required tools from the set that's already callable, marking a tool required never grants it access.

Tool chains

Optional ordered sequences of tools the agent should follow each run ("first look up the company, then list its tickets, then post a summary"). Turn on the tool-chain option, add a chain, name it, add tool steps from the picker, and drag to reorder; a live preview shows the sequence. Chains are ordered guidance enforced via prompt instructions — they steer the model but do not force a tool to run and do not grant access, so a chained tool must also be in your callable set.

Step 3 with a native tool enabled, the tool policy editor, and one tool chain with several ordered tools.

Step 4 — Review and deploy

Four summary cards recap everything: Basics, Knowledge and context, Capabilities (the tool mode and selected tools, native tools, chains), and Guardrails and consent (max runtime, max credits per run, trigger). Below the guardrails is the required consent switch:

I accept autonomous operation — "This agent runs against my MSP tools on my behalf. I've reviewed the system prompt and tool policy and accept responsibility for its actions."

You cannot deploy without turning it on.

Step 4 with the four summary cards and the consent switch.

Deploy as Dry Run

Click Deploy as Dry Run in the footer. This validates the whole draft, creates the automation with write tools filtered to read-only, and re-opens the builder against the new automation. If some knowledge sources fail to attach during deployment, a warning banner lists exactly which ones — the automation is still created.

Test it live

After deployment, the live test panel (right side of Step 4) becomes a chat with your automation, marked with a "staging" badge. Send a test prompt and watch the run stream in real time — the agent's text, its reasoning, every tool call with inputs and results, and usage.

Every test message is a real, billed run — it consumes credits (or your Anthropic account under BYOK) exactly like a production run, and appears in the automation's run history.

Save changes

While the automation is deployed but not yet promoted, edits in the builder are pushed with the Save changes button on Step 4 — the "Running in Dry Run" banner reminds you when edits are pending.

Promote to Production

When you're satisfied, click Promote to Production. The builder saves any pending edits first, then promotes: dry-run mode is switched off and write-capable tools are enabled. A confirmation makes sure you mean it. After promotion the footer button becomes View agent, taking you to the automation's detail page.

Creation and save errors

Failures show a support-coded banner (for example SJ-AGENT-CREATE-UNAVAILABLE when the automation service is unreachable, or SJ-AGENT-CREATE-VALIDATION with the exact fields to fix). Retry after fixing the reported issue, or quote the code to support.