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. AgentWorks gives an agent an outcome to own. It plans the work, runs it on schedule, measures every run and changes its own plan until the metric hits your target.
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.
Auto-improve
It fixes what broke, drops what didn't work and tries what's next.
Under the hood
Three layers, built to run for months.
- 3Workflows & goalsPipelines of deterministic and agentic steps, learnings and a knowledge base, measured against a goal
- 2CrewsAn agent with skills, memory, a browser, Slack and WhatsApp, triggers, and calls to other crews
- 1AgentsVendor-native Claude Code, Codex, Cursor, Pi and Muse in live terminals, with your MCP tools and sandboxed commands
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.
- One primary metric. The number that decides whether the goal is met.
- Supporting metrics. The signals that explain why it moved, like reply time or open rate.
- What must stay true. Guardrails the agent can't trade away, like "never email the same person twice a day".
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
Measure
Progress, not activity. And never a made-up number.
Every run leaves evidence: what it did, what it cost, and what the metric did next. If a number is missing or out of date, the goal says so instead of guessing.
- Trend, not a snapshot. Every measurement is dated, so you see the direction.
- Stale data flagged. "Measurement stale" beats a confident wrong number.
- Cost per goal. What each goal costs to run, per run and per model.
Auto-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.
- Fixes. A step failed or a login expired: it repairs it and re-runs.
- Did for you. Each change says what it should move and when it will check.
- Focus areas. Tell it where to look first. Your goals and rules always win.
- Challenges your rules. If a rule is costing the goal, it asks. The rule stays until you answer.
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.
Start from a premade agent or describe your own goal. Ten minutes to set up, on the AI plan you already have.