PROBATIOproh-BAH-tee-oh
Agent Role Diagnostic
Probatio is Latin for a trial, the root of “probation.” Every new hire works through one. Our Diagnostic gives an agent its first trial on your work, in code.
Bring one role. Leave with working code, a Role Card, and a clear next step.
$750: a time-boxed code trial on one task from one role. Further work is needed before an agent runs in production.
Included: one hour of agent coding, the code with a short README, a one-page Role Card, and a one-hour consultation with an engineer.
Is this for you?
- Owners weighing whether agents could take on part of a role they would otherwise hire for
- Teams with a role whose work is repeatable, rule-bound, and spread across a few systems
- Businesses that want code to inspect and an engineer to discuss it with, before a larger commitment
The problem
A role you would hire for may be work an agent can carry.
You have a role on the org chart, or one you are about to hire for. Much of its week is repeatable: reading what arrives, entering it, checking it against a rule, and following up.
Before you post the job, it is worth knowing how much of that work an agent could take on. Slides and estimates describe what might happen; code shows how the work actually behaves.
You also want an engineer’s view before committing to a managed service. The question is practical: which parts of the role could agents carry, and what stays with people?
How we solve it
One task from the role in code, then a senior conversation about it.
We pick one bounded task from the role with you, such as sorting intake documents or drafting follow-ups. An agent works on it for one hour under an engineer’s direction, and the engineer reviews the output before delivery.
You receive the code in a private repository, or as a ZIP. The README explains how to run it, what the hour produced, and what remains. Nothing is deployed to your systems.
The consultation works from that code and your Role Card. We discuss how much of the role agents could carry, where operators and your people step in, and what the full system would take. The fee is fixed at $750 USD.
Roles by industry
Where a Role Diagnostic fits.
Typical roles and first tasks across industries. Illustrative examples, not client results.
- Accounting firm · Intake coordinator
Client documents sorted for a staff accountant
The hour produces code that reads sample client uploads and sorts them by document type and tax year. Uncertain files are flagged, not filed. The consultation covers how much of the intake role this represents, and where a staff accountant confirms each sort.
- Distributor · Order entry clerk
Emailed purchase orders turned into order lines
An agent writes code that reads sample purchase orders and proposes order lines matched to the catalog. Unmatched lines are listed for a person. The consultation covers substitutions, price changes, and where the sales lead approves each order.
- Property management · Maintenance coordinator
Tenant requests triaged by urgency and trade
The hour produces code that reads sample tenant requests and proposes an urgency level and trade for each. The property manager approves every dispatch. The consultation looks at edge cases and what the coordinator role would still hold.
- Dental group · Front-desk coordinator
Insurance verification notes from de-identified forms
Working from de-identified sample forms, an agent writes code that extracts coverage details into a standard note. Front-desk staff confirm each note before it is relied on. The consultation covers privacy obligations and the practice management system.
- Home services · Dispatcher
Service calls matched to technicians and time slots
The hour produces code that reads sample service requests and proposes a technician and slot from a schedule export. The dispatcher confirms each booking. The consultation covers skills, travel time, and the calls that always need a person.
- Law firm · Legal assistant
Engagement letters drafted from intake notes
An agent writes code that turns sample intake notes into a draft engagement letter from the firm’s template. An attorney reviews and approves every letter before it is sent. The consultation separates clerical steps from legal judgment.
- E-commerce · Customer support agent
Order-status replies drafted from the order system
The hour produces code that reads sample support emails, looks up the order in an export, and drafts a reply. The support lead approves each reply until a policy is agreed. The consultation covers refunds, exceptions, and tone.
- Staffing agency · Recruiting coordinator
Candidate profiles screened against job requirements
An agent writes code that compares sample resumes with a job’s stated requirements and summarizes the match. A recruiter decides every shortlist. The consultation covers fairness checks, the data boundary, and what the coordinator role still holds.
What you receive
One hour of agent coding
An agent works for one hour on one agreed task from the role, under an engineer’s direction. You receive the code for review.
A Role Card
A one-page job description for the agent: the tasks it would take on, where operators review, where your people approve, the data boundary, and a first measure.
One hour of consultation
Discuss the code, the Role Card, the risks, and what a managed agent for this role would involve, with an engineer.
A clear next step
Leave knowing how much of the role agents could carry, and what scoping the full system would take. People approve any use.
How it works
Describe the role
Share what the role does in a week, the systems it touches, and what good work looks like. Leave confidential records and credentials out.
Agree the task
Choose one bounded task from the role for the hour of agent coding, and name the points where a person approves.
Receive the code
Receive a private repository, or a ZIP if you do not use GitHub. A short README explains setup, work completed, and remaining work.
Consult and decide
Review the code and your Role Card in the one-hour consultation, then decide your next step. You approve any further work.
How the Diagnostic is checked
What the hour and the consultation deliver.
Each item can be checked against the code, the README, the Role Card, or the consultation.
- Task agreed in writing
- The bounded task and its approval points are written down before the hour starts. The README records them, so the result can be checked against the agreed task.
- Code runs as documented
- The README’s setup steps are followed on the delivered code. It runs on the sample data as the README describes.
- Completed and remaining work
- The README separates what the hour produced from what remains. Each item can be checked against the code itself.
- A Role Card for the whole role
- The Role Card lists the role’s tasks, marks which ones agents could carry, and names where operators review and your people approve.
- A next step you can price
- The consultation ends with one named next step and what it would involve. The manager of the role confirms it is clear enough for a budget decision.
Common concerns
What owners ask before they sign.
- Confidential data
- The hour runs on representative samples or descriptions that contain no confidential records. Any access to sensitive material is agreed with the engineer before it is shared.
- One task is not the whole role
- An hour covers one task, not a role. The Role Card estimates the rest of the role in writing, marked as an estimate until the system is scoped.
- Agent-written code
- An engineer directs the agent and reviews its code before delivery. The README states what was reviewed and what still needs testing.
- Partial results
- An unfinished task can still answer the main question about the role. The consultation explains what the code shows and what it leaves open.
- What runs next
- The code is delivered to you in a private repository or as a ZIP. Nothing is deployed to your systems, and any further use is your decision.
Who does what
Who builds, who runs, and who approves.
Your team
- Choose one role and describe its weekly work
- Agree the bounded task for the hour of agent coding
- Provide non-confidential samples or descriptions of the data
- Bring the role’s manager to the consultation
- Decide and approve any further work
Ergon
- Help shape a task that fits one hour of agent coding
- Direct the agent and review the code it produces
- Deliver the code with a README on setup, output, and remaining work
- Write the Role Card and lead the consultation
- Recommend a next step, including when agents are not the right fit
Afterward
Where clients go next.
Most take one of these routes. You choose, and nothing starts without your approval.
Scope the whole role
A Workforce Blueprint assigns every duty to an agent, an operator, or your team, prices the system, and starts one agent running.
Bring another role
If a second role looks like a better first candidate, a second Diagnostic tests it the same way.
Continue with your own team
Your developers carry the code forward from the README. Its setup and remaining-work notes are written for that purpose.
Pause here
If agents are not the right fit yet, you pause with a clear reason. The code, README, and Role Card stay with you.
Before you start
What to have ready.
- A short description of the role and what it does in a typical week
- The systems or files the role reads from and writes to
- Representative examples that contain no confidential records
- The person who manages the role and can decide the next step
- A GitHub account for the private repository, or a preference for a ZIP
Related services
What arrives with the code
A README anyone on your team can follow.
Every Role Diagnostic delivery includes a README with the same six parts. This is the outline; yours is written for your task. People review the code and approve any use or deployment.
Agreed task
- Task
- The bounded task chosen for the hour of agent coding
- Version
- The commit or archive you received
- Consultation
- When the one-hour review takes place
What the hour produced
- Delivered
- What runs, what is scaffolding, and what is unfinished, stated separately
- Role Card
- Where to find your Role Card, the one-page job description for the agent
Run locally
- Setup
- Runtime, install command, and configuration names, never secret values
- Try it
- A safe example input and the result to expect
Review and evidence
- Checks run
- Each check, where it ran, and its result
- Not tested
- What was left out, named plainly
- Approval points
- Actions that need an operator or your team, and whose role that is
Remaining work
- Next
- Implementation, evaluation, integration, and deployment work still to do
Dependencies and data
- Inventory
- Libraries and their licenses, plus any approved data requirements
Probatio · Agent Role Diagnostic · $750 USD
Bring one role. Leave with working code, a Role Card, and a clear next step.
One hour of agent coding on a task from the role, the code delivered to you, a Role Card, and a one-hour consultation.
What the Role Diagnostic includes
- One hour of agent coding for the agreed task
- The code produced, delivered to you
- A Role Card: a one-page job description for the agent
- One hour of consultation on the work, the Role Card, and next steps
Receive a private repository, or a ZIP if you do not use GitHub. A short README covers setup, completed work, and what remains before production.
People review the code and approve any use or deployment. Full engagement terms are finalized in a Master Services Agreement.
What “accepted” means
Measured against criteria you agree to in advance.
- One hour of agent coding is completed for the agreed task.
- You receive the code produced during that hour.
- You receive a Role Card for the role.
- A one-hour consultation covers the work, the Role Card, the risks, and next steps.
Where this fits
- Learn How it works
- Ask free Ask an engineer
- Trial one role Agent Role Diagnostic
- Scope the system Workforce Blueprint
- Run every day Managed Agent Operations
Not ready yet? Ask an engineer. After this: Workforce Blueprint & Starter Agent or Managed Agent Operations.
Questions
What is included in the fee?
The $750 USD Diagnostic includes one hour of agent coding, delivery of that code, a one-page Role Card, and one hour of consultation.
Is “Ask an engineer” the same thing?
Ask an engineer is a free 15-minute call in which an engineer names the parts of a role that agents could take on. The Diagnostic adds the code, the full Role Card, and a one-hour consultation.
Is the Role Card the same as the Workforce Blueprint?
No. The Role Card plans one role on one page and comes with the Diagnostic. The Workforce Blueprint designs and prices the whole system, and includes a working starter agent.
Does this change anything in our operations?
No. The Diagnostic shows, in code, which parts of the role agents could carry and what would stay with people. Nothing is deployed, and staffing decisions remain yours.
How is the code delivered?
We provide a private repository, with a ZIP alternative. The README covers how to run it, what the hour produced, and remaining work.
What if agents do not fit the role?
We say so plainly in the consultation, and discuss the next steps that do fit the work.
How is the Diagnostic paid for?
You request it here, and we reply with an engagement letter for the task. Payment is arranged directly with you after you sign it, by invoice if you need one. No payment is taken on the website.
What governs further work?
Full engagement terms are finalized in a Master Services Agreement.
Will the hour finish the task?
Not necessarily, and the fee does not depend on it. The hour produces real work to review, and the README records what remains.
Is the code ready for production?
It is written for review and discussion. Production use needs further work, which the consultation helps you scope.
Who should join the consultation?
The manager of the role, and anyone who would approve the agent’s work. The discussion goes further when the decision-maker is present.