Goals
One goal. One metric. An agent that doesn't stop at done.
Most AI automation finishes a task and waits for the next prompt. Goals puts an agent inside your process with a target to work toward. It plans its part of the work, runs it on schedule, measures every run and adjusts its plan, so you can see what is moving the metric. Your team stays in charge of the goal.
Set the goal
An outcome in plain words, the metric that proves it, and the target.
Run
Agents plan the steps, connect your tools and run on schedule.
Measure
Every run records what it did and what it moved.
Review each run, improve the next
What broke gets fixed, what didn't work gets dropped, and the next idea gets tried.
Use cases
One goal per team. Illustrative numbers.
-
Book more demos
Sales team
Target met
Demos booked per week
7from 2
Agent did: answers new signups within 10 minutes.
-
Get paid on time
Finance team
Tracking
Overdue invoices
8%from 14%
Agent did: sends polite reminders and escalates after the third.
-
Answer faster
Support team
Tracking
First reply time
15 minfrom 4 hours
Agent did: drafts replies from your help docs for an agent to send.
-
Grow search traffic
Marketing team
Tracking
Organic clicks per week
+30%from last quarter
Agent did: refreshes the pages that lost their ranking.
-
Win back carts
Store team
Tracking
Abandoned carts recovered
11%from 4%
Agent did: sends the reminder at the hour each buyer usually shops.
-
Calm down CI
Platform team
Tracking
Flaky tests in CI
3from 19
Agent did: fixes the flakiest tests first and checks they stay green.
Goals
Say what you want. Pick the number that proves it.
A goal is the outcome, a primary metric with a target, a few supporting metrics, and the rules that must stay true while the agent works. Describe it in chat and AgentWorks sets it up with you.
What we're working toward
Turn more inbound signups into booked demos.
SupportingFirst reply time · Reply rate · Show-up rate
Must stay trueMax 2 emails per person a week · Never promise pricing
Improve
It finds what would move the goal. Then it does it.
After runs, AgentWorks reviews the evidence against your goal. It repairs broken steps, drops ideas that didn't work, does the work nobody was doing, and comes back later to check whether it helped.
Autonomy
You decide how far it goes. Turn it up as you trust it.
Set it per goal. Anything that reaches a customer can always require your approval, whatever the level.
- Level 1
Ask first
Proposes every step and waits for your yes. Good for week one.
- Level 2
Run steps
Runs the workflow on its own. Asks before anything goes out or the workflow changes.
- Level 3
Edit workflow
Also rewrites its own steps when the evidence says a change will move the goal.
- Level 4
Full
Runs, changes and ships within the rules you set. You review the log, not each step.
Layer 3 · Workflows & goals
A full plan, not a prompt. Code where it should be, agents where it matters.
A workflow is the whole operation written down: pipelines of steps, some fixed and deterministic, some handed to an agent or a crew, all measured against one goal. Each run adds to what it knows.
Pipeline · New signups
- ScriptPull new signupssaved script
- AgentResearch each companyClaude Code
- ScriptRoute by company sizerule, no model
- CrewSage writes the emailcrew step
- ApprovalYou approve the sendhuman step
Pipeline · Follow-ups
- ScriptFind quiet signupssaved script
- AgentDraft the check-inCodex
- ScriptLog to the goalmetric update
Scripted where it counts
Fetching data, calling APIs and applying changes run as scripted steps: plain code with no AI, which must exit cleanly and pass an output check before the next step starts. Routing is a rule in code, never a model guessing.
Agentic where it matters
Research, judgment and writing go to an agent step or to a crew, with the right model for each step and a human approval wherever you want one.
Learnings & knowledge base
Every run writes what it learned into a shared skill, and each workflow keeps a knowledge base that other workflows can read. Run fifty knows what run one had to discover.
Start from a playbook
64 Goal playbooks, ready to install.
Sales follow-up, invoice chasing, support replies, SEO, store operations and more. Each sets up the goal, the metric, the tools and the approvals, and you tune it to your business.
FAQ
How it works, answered.
Does every step use AI?
No. Work that should run the same way every time, like pulling data, calling an API or applying a change, runs as a scripted step: plain code with no AI, whose output is checked before the workflow moves on. Agents take the steps that need judgment, and rules like "over $200 needs approval" are decided in code.
What makes a good goal?
One outcome you care about and one number that proves it, with a target. "Book 5 demos a week" works. "Do more marketing" doesn't, because nothing can tell whether it happened.
What if the metric can't be measured automatically?
AgentWorks says so. A missing or stale measurement is flagged on the goal instead of guessed, and the agent asks you how to get the number.
Can it change my workflow without asking?
Only if you let it. At the default autonomy level it runs steps on its own and asks before posting, sending or editing the workflow. You can move it up or down at any time.
Can I use it from ChatGPT or Claude?
Yes. AgentWorks includes an MCP server. Connect it to ChatGPT, Claude, Cowork or any MCP client to check goals, read reports and start runs from that chat. Hosted AI apps connect to your AgentWorks server with a sign-in link.
Does it work with the tools I already use?
Yes. Agents use MCP servers, APIs and their own browser, so anything you can do in a web app, they can do too, with credentials kept in the vault.
What's the difference between a Goal and a Crew?
A Goal owns an outcome and keeps working on its own schedule. A Crew is an expert you or your team ask for help, in Slack, WhatsApp or from Claude and ChatGPT. Goals can hand steps to Crews.
Pick one goal. Watch the number move.
We set up your first Goal with your team, agree how success is measured and connect the tools it needs.