Scope & SOW Agent
Writes the statement of work, and finds where the margin will leak
5 of 8 deliverables need attention.
8 deliverables checked. 5 flagged. The largest gap is 12 days.
Start with D-05 Reporting module. Dana has the most flagged.
Whether the scope is fair to either side is for the people signing it; the list only checks criteria, prices and dates.
Why rows were flagged
- No acceptance criteria43%
- Past due and not accepted29%
- Not priced29%
Value flagged by Owner
- Dana2
- Omar2
- Lina1
Items to act on, worst first
| Item | Owner | Value | Days past due | Why |
|---|---|---|---|---|
| D-05 Reporting module | Dana | 1 | 12 | Past due and not accepted |
| D-02 Data migration | Omar | 1 | 5 | No acceptance criteria, Past due and not accepted |
| D-04 User training | Lina | 1 | 0 | No acceptance criteria, Not priced |
| D-07 Handover pack | Dana | 1 | 0 | No acceptance criteria |
| D-03 Integration build | Omar | 1 | 0 | Not priced |
What to do this week
- Resolve D-05 Reporting module first: it is the most urgent on the list.
- Fix the data or the status on every flagged row, then re-run.
- Re-run this check every time the list changes, before it reaches a decision.
Do
- Fix the highest-risk item first, then run the check again on fresh data.
Don't
- Don't act on one row alone: open the source record first.
How to improve
- Add more detail per row (owner, date, source) so the next report can trace each item.
- Add a second period of data so the next report can show whether things are improving.
Demo
Overview
Agencies and consultancies rarely lose money on their rates. They lose it in the gap between what the client believed and what the statement of work said — the revision round nobody bounded, the "small" integration, the approval that took three weeks while the team sat idle.
This agent turns discovery notes into a proper statement of work: deliverables stated as things that can be accepted or rejected, assumptions written down, dependencies on the client made explicit with what happens if they slip, and a change process that exists before it is needed.
Its most useful output is the exclusions list. It reads the notes for what the client clearly expects and the scope does not cover, and names each one — because that conversation is cheap now and expensive in week six. It prices nothing and signs nothing; commercial terms stay with a person.
Benefits
Protects the margin
Most overruns were visible in the discovery notes.
Proposals out same-day
The document written while the conversation is fresh.
Fewer difficult conversations
Or rather, the same ones, earlier and cheaper.
What it does
Finds the assumed inclusions
What the client thinks is in scope and is not. That conversation is cheap now.
Deliverables you can accept or reject
"Strategy support" cannot be delivered. "A 12-page strategy document" can.
Client dependencies with consequences
What you need, when, and what happens to the timeline if it is late.
Bounds the unbounded
Revision rounds, stakeholder counts, review cycles — the three that consume margin.
A change process before it is needed
Agreeing how scope changes is easy in week one and impossible in week six.
Prices nothing
Commercial terms are yours. It scopes.
What this changes
What this changes about your week
- It takes over
- Turning discovery notes into a scope that holds when the project changes.
- Done today by
- A delivery lead or the person who ran the call.
- How often
- Every proposal.
- Typical manual effort
- A proper SOW with assumptions and exclusions is half a day.
Why Professional Services in particular. Agencies do not lose money on rates. They lose it on the revision round nobody bounded, and that gap is visible in the notes.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Scope & SOW Agent has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsextract_structured_data
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Requirements
Integrations
No integrations required.
Before you start
- Discovery notes, a brief, or a call transcript
- Requires the Starter plan or higher
Use cases
After a discovery call
Notes to statement of work in one pass.
Reviewing a draft SOW
Find what is unbounded before it is signed.
A project already slipping
See which unstated assumption is causing it.
Pricing
Starter
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Does it set the price?
No. It scopes the work and estimates effort only where the notes support it. What you charge is a commercial decision that depends on things not in a discovery note.
Is the output a contract?
No. It is a scope document to be reviewed and, where it forms part of an agreement, checked by a lawyer. It never writes legal terms.
What if discovery was thin?
It says so and lists what to ask before quoting. A confident SOW built on a thin call is exactly how the margin disappears.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent