Quickstart

The fastest way to a first useful result depends on where you are. Pick the path that matches your situation — each one gets you to a real result in Pulse.

Your situation	Path	Time
I just installed Pencel and want the fastest first result	Path A — Install a Marketplace pack	~5 min
Onboarding already set up a starter job for me	Path B — Run the job onboarding installed	~2 min
I want to build my own process and learn the pieces	Path C — Build a job by hand	~10 min

Before any path: sign in

Pencel requires you to sign in before using any model — including when you bring your own API key. On first launch you accept the Terms of Service and sign in with Google or email. To run models you also need either an active subscription (Pencel Auto/Private modes) or your own API key. See Accounts & sign-in, and Data Handling for what stays on your machine.

Path A: Install a Marketplace pack

The quickest route to value: install a ready-made pack instead of building from scratch. A pack brings its own agent, workflow, and connections, configured to work together.

Prerequisites: signed in, with a subscription or your own API key. Expected result: a working job you can run, with results in Pulse.

1. Open the Marketplace in the sidebar (under Manage).
2. Pick a pack — for example RFP Scout (government contracting) or Stock Watch (markets). Each card shows a setup-readiness badge.
3. Review the What this installs list, then click Install. Pencel creates the entities and compiles the pack's workflows.
4. Follow the Finish setup panel. Pencel runs verification checks and tells you exactly what still needs attention (for example, an OAuth sign-in). Many packs use managed connections and need no API key at all.
5. When setup is green, open Jobs, run the job, and watch it execute live.
6. Read the result in Pulse — see Path A result.

If a connection won't verify or the run won't start, see Troubleshooting.

Path B: Run the job onboarding installed

If you finished onboarding, Pencel already researched your context and installed a starter job (and often a starter pack). You just need to run it.

Prerequisites: completed onboarding; signed in with model access. Expected result: your starter job runs and posts a result to Pulse.

1. Open Jobs in the sidebar. Your starter job is listed there. (You can also open the Marketplace to see any starter pack that was installed.)
2. If the job shows a setup prompt, finish the required connection setup.
3. Run the job and watch it execute in the Jobs run detail.
4. Read the result in Pulse — see Reviewing the result.

Don't see a starter job? Onboarding may have been skipped — use Path A instead, or see Troubleshooting.

Path C: Build a job by hand

Build your own job to learn how the pieces fit together. This path creates an agent, authors a workflow with the guided "Your job" pane, runs it, and reviews the result.

Prerequisites: signed in with model access. Expected result: a custom "Daily Summary" report, produced by an agent you configured.

1. Create an agent

Agents are the AI workers that carry out tasks. Each has a name and a role.

1. Click Agents in the sidebar (under Manage), then New Agent.
2. Fill in:
   • Name: Report Writer
   • Role: You write concise executive summaries based on available workspace data. You focus on clarity, brevity, and actionable insights.
3. Save the agent.

INFO

Write the role in second person, as if talking directly to the agent. Be specific — "You write concise executive summaries" works better than "This agent writes reports."

2. Author a workflow

A workflow is a multi-step process that tells an agent what to do. Pencel authors workflows through a guided "Your job" pane: you describe the outcome and Pencel drafts the steps with you.

1. From Home, click Build (or open Workflows → New).

2. Describe the job in plain language, for example:

   Every morning, search the workspace for recent artifacts and documents,
   summarize the key findings from the past day, and create a report titled
   "Daily Summary" — organized by topic, with a brief executive overview at the top.

3. Pencel drafts a plan. Review the collapsible Inputs, Connections, and Won't-do sections, and expand any step to see what it will do.

4. Use Test this step to safely dry-run a step — a step is only marked Validated after a test passes. If a step fails, click Ask Pencel to fix.

5. When you're happy, Finalize. Your job lands on the Jobs page.

3. Run it and watch it work

1. Open your job on the Jobs page and click Run once now.
2. Watch execution live — each step, the tools it uses, its output, and the cost.

WARNING

Some steps pause and ask for your approval before proceeding — the human-in-the-loop gate that makes sure agents do not take actions you have not reviewed. Approve to let the agent continue.

Reviewing the result

When a run completes, its output shows up in two places:

• Pulse — a briefing card summarizing what the agent produced. From the card you can ask a follow-up, investigate, or draft a reply without leaving Pulse.
• Workspace — the actual artifact (for Path C, the Daily Summary report). Click Workspace in the sidebar, open the artifact, and review or edit it in place.

If Pulse or Jobs looks empty after a run, see Troubleshooting.

What's next

• Using Pulse — read and act on your agents' results
• Monitoring Jobs — run history, live monitoring, and schedules
• Marketplace — install more whole jobs in one click
• Trust & Permissions — approvals and the graduated trust model
• Building a Workflow — author effective multi-step workflows with the guided "Your job" pane
• Core Concepts — how agents, workflows, Pulse, Jobs, Knowledge, and memory fit together