# AI Workflow Builder — Pencel.ai > Describe a job in plain language and watch Pencel compile it into concrete steps bound to real tools. It rehearses once against your own data before it runs alone, and the agents that run it are yours to define. Canonical: https://pencel.ai/product/ai-workflow-builder [Product](https://pencel.ai/product) AI Workflow Builder Built into Pencel — nothing to install # AI Workflow Builder in Studio Describe a job the way you would explain it to a new hire, and Pencel compiles it into a workflow you can read: named steps, a real tool bound to each one, approval gates where they belong. It rehearses once against your own data before it ever runs alone. And the agents that run it are yours to define — role, model, tools, spending cap, and how much each one may do without asking. Who builds it with you **Planner** turns what you describe into a plan **Verifier** checks every run against your guardrails Download Free [Build your first workflow](https://pencel.ai/download) 1 rehearsal Every workflow runs once, watched, before it runs alone 3 verdicts Each run lands as clean, repaired or failed — never ambiguous Per agent A role, a model, a risk level and a spending cap you set See it in Studio ## What it looks like with this running. Thursday · 4:12 PM Workflows · Authoring Workflows Agents Jobs You **You** 4:12 PM Every Monday, pull last week’s Stripe revenue, compare it to the quarter target, and put the summary in Documents. **Planner** 4:12 PM Here’s what that compiles to. Weekly revenue summary — 4 steps Every step bound to a real tool: read Stripe, compare against the target on your Company page, draft the summary, save it to Documents. Nothing leaves your machine except the model calls. 4 steps Stripe · Documents No external send **Planner** 4:13 PM One thing I couldn’t ground. Which quarter target? Your Company page has an annual target but no quarterly one. Add the real figure, or I can derive it as annual ÷ 4 and label it derived so nobody mistakes it for confirmed. Add the real figure Use annual ÷ 4 You **You** 4:15 PM Rehearse it before you schedule anything. It ran once against your live Stripe data while you watched. Output held for review — nothing saved, nothing scheduled. **Verifier** 4:16 PM Clean run. Ready to schedule The rehearsal produced the summary in 38 seconds with no gaps and no failed steps. Mondays at 8 AM? Rehearsal: clean 38s Scheduled. It shows up in Jobs with its own run history and trust bar. What you just saw **You describe, it compiles** No form and no flow chart. The plan comes back as concrete steps with a real tool on each. **It names what it can’t ground** A missing fact stops the compile and asks you, rather than being filled in with a plausible guess. **Rehearsal isn’t optional** A workflow runs once, watched, against your own data before it can run unattended. **Every run keeps its evidence** What it read, which tools it called, what it produced, what it cost, and the verdict. End to end ## The whole loop, start to finish. Every step below runs today. Nothing here is a mock-up of what is coming. - 1 Describe Say what needs to happen, in plain language. No form to fill in, no flow chart to draw, no code. - 2 Compile Pencel turns it into concrete steps and binds each one to a real tool. Anything it cannot ground, it names instead of guessing. - 3 Rehearse It runs once against your own data while you watch, so you see real output before anything is scheduled. - 4 Schedule Give it a cadence or a trigger. It becomes a job with its own run history and trust bar. - 5 Watch Every run keeps what it read, which tools it called and what it produced, with a clean, repaired or failed verdict. Capabilities ## Everything it does, named. One line each. No adjectives — every one is a specific thing you can go and watch it do. - Takes a description of the work rather than a form, so you say what you want, read back what it built, and correct it in the same conversation. - Compiles into named steps with a real tool bound to each, and reports any step it cannot ground in a tool you actually have instead of leaving the model to improvise. - Runs once against your own data, with you watching, before a workflow may run unattended — nothing goes onto a schedule sight unseen. - Gives every agent a role, a writing style, a preferred model, the skills it may use, behavioural restrictions and a risk tolerance, from asking before every action to acting alone and asking only when genuinely uncertain. - Caps spending at both ends, with a maximum cost per run on an agent and a monthly credit cap on a room, neither of which can be exceeded. - Stops at the approval gates you place, and stops at every external send and financial write whatever the workflow says. - Catches up schedule fires it missed while the app was shut, refuses to overlap a run with itself, and can pause a job after repeated failures. - Rolls recent runs into a per-job trust bar — clean, repaired or failed, plus the current clean streak — so you can see whether to leave it running. - Presents a form at launch for any workflow you give inputs to, with nothing to design. - Binds a step to Google Workspace, Slack, QuickBooks Online, GitHub, Notion, Atlassian, Linear, Stripe, a database, browser automation, or any MCP server you point it at. Inputs and outputs ## What it reads, and what you get back. What it connects to Any agent in your workspace Every connected tool and MCP server Your Knowledge and Company facts Jobs — schedules, triggers, run history Home and Pulse, where the results land What lands in your hands - A workflow you can actually read, compiled from a description - A rehearsal run against your own data, before anything is scheduled - A job with a schedule, a trust bar and full run history - Agents you defined once, reusable across every Program A week with it running ## Day one to steady state. What the first day looks like, what the quiet days look like, and when it comes to find you. - Day 1 Describe one thing you do every week. Watch it compile, then rehearse it once while you watch. - When it looks right Put it on a schedule. It becomes a job, with its own history and trust bar. - Every run The full trace is kept — what it read, which tools it called, what it produced, what it cost. - Over time The trust bar tells you whether it has earned being left alone, instead of you guessing. Guardrails ## Where it stops for you. The line between what it does on its own and what it will never do without you, stated plainly. Waits for you Anything it could not ground in a fact or a tool you actually have, and your go-ahead before a workflow moves from rehearsal onto a schedule. Never does Put a workflow on a schedule you did not approve, or bind a step to a tool you have not connected. Studio holds Agents, Workflows and Jobs. Install a Program and it sets its own up for you. [Build your first workflow](https://pencel.ai/download) [Previous Agent Rooms](https://pencel.ai/product/agent-rooms) [Next Knowledge & Company](https://pencel.ai/product/knowledge-and-company) Get started ## Three steps to your first real result. - 1 Download Pencel and open Studio. - 2 Describe one thing you do every week in plain language, and read back what it compiles to. - 3 Rehearse it once against your own data, then put it on a schedule. Download Free macOS, Windows and Linux. No invite code. [Read the docs first →](https://pencel.ai/docs/getting-started/what-is-pencel.html)