VANDAMAgent-Ready Audit
Know what needs fixingbefore the AI build.
A readiness report, a scorecard and a prioritized list of fixes. You learn which data, process, connection and permission gaps stand between your company and a useful first AI project, with the evidence attached.
$9,600 two weeks
Is Atlas & Co. ready for its first agent?
The agent would answer order-status emails and rebook late deliveries with the carrier. Each area is scored against what that agent needs.
- Fix first
-
31needs 60
Late deliveries are handled from memory. Three service agents gave three different rules for when to rebook.
Write the late-delivery rule: when to rebook, when to refund, who approves exceptions. Dana Ruiz, service lead · 3 days
- Interviews with 3 of 5 service agents. They rebook after 2, 3 or 5 days late.
interviews · service · 3 of 5 - The last written procedure dates from 2021 and still names the old warehouse.
sharepoint/service/late-delivery-2021.docx - Refund or rebook is decided case by case, with no record of who decided.
mailbox · 40 late-delivery threads read
- Interviews with 3 of 5 service agents. They rebook after 2, 3 or 5 days late.
-
48needs 65
The agent can read orders through the ERP’s API. Rebooking only happens by hand in the carrier’s portal.
Move the carrier contract to the tier that includes API access. Tom Becker, IT manager · about 2 weeks
- ERP API: orders and stock can be read, shipments are read-only.
erp api · /orders /stock /shipments - The current carrier contract has no API. The business tier includes one.
carrier contract · renewal clause 4.2 - Customer emails arrive in a shared mailbox an agent can connect to.
mailbox · service@
- ERP API: orders and stock can be read, shipments are read-only.
-
55needs 60
Every service role can edit orders. Nobody is named to decide what an agent may do.
Create a read-only service role and name who approves new agent actions. Tom Becker, IT manager · 1 day
- Four ERP roles exist. All three service roles include edit rights on orders.
erp · roles export - Access requests go to whoever is available in IT. No owner signs them off.
it tickets · last 90 days
- Four ERP roles exist. All three service roles include edit rights on orders.
- Then build
-
72needs 70
Orders and shipments match in the ERP. The promised delivery date is missing on 6% of orders, mostly phone orders.
The agent reads orders and shipments as they are. Fill the missing dates on phone orders as they come in.
- 389 of 400 sampled March orders have a matching shipment record.
erp.orders · 2026-03 · n=400 - The promised date is empty on 24 of the 400, mostly orders taken by phone.
erp.orders.promised_date · 24 null - 97% of shipments carry a tracking number.
erp.shipments.tracking_no
- 389 of 400 sampled March orders have a matching shipment record.
-
68needs 55
Single sign-on and two-step login on every core system. The shared mailbox keeps no audit log.
Log every email the agent sends in the agent itself, since the mailbox will not.
- Single sign-on with two-step login on the ERP, mailbox and file storage.
identity provider · app list - The ERP keeps an audit log for 12 months. The shared mailbox keeps none.
erp.audit_log · retention 12m
- Single sign-on with two-step login on the ERP, mailbox and file storage.
-
80needs 50
The service lead owns the queue and wants this. Two agents offered to review drafts in the first month.
Dana reviews the agent’s replies with two colleagues for the first month.
- About 140 late-delivery emails a week, handled by five people.
mailbox · weekly volume, Sep 2026 - Dana Ruiz agreed to own the written rule and the review.
workshop · service team
- About 140 late-delivery emails a week, handled by five people.
59 of 100 overall. 3 of 6 areas fall short of what this agent needs.
Process documentation blocks the first agent.
With no written rule, an agent would rebook some orders after two days and others after five, the way the team does today.
- Next action
- Write the late-delivery rule with the two agents who handle most cases.
- Owner
- Dana Ruiz, customer service lead
- Effort
- 3 days
- Week 1Write the rule. Create the read-only role.
- Weeks 2–3Build the order-status replies. They only read, so they go live before the carrier change.
- After the contract changeAdd rebooking through the carrier’s API.
Most companies can’t say whether their data is ready.
- 63%
- of organizations lack, or don’t know if they have, the data practices AI needs.
Gartner survey of 1,203 data leaders, 2025. - 30/50
- AI practitioners interviewed by
RAND described persistent data quality problems, the second most common reason projects fail. - 23%
- of organizations are scaling AI agents anywhere, while 62% are experimenting.
McKinsey, State of AI, November 2025.
Every company I talked to wants to pipe its internal data into one place and expose it to agents through MCP. Then they look at the data and realize it’s a mess: five versions of the same customer, old Slack channels, PDFs nobody can search.
Late CheckoutOctober 2026Source So no, the mess is normal. We find out which part blocks the first agent.
Find the dependencies before they delay the project.
An AI agent is software that carries out tasks in your connected tools. Before it does useful work it needs information it can read, a process it can follow and permission to take the right actions. A demo can look convincing with one of the three missing, and the gap tends to surface halfway through the build.
We trace the workflow you have in mind back to everything it depends on. The report separates the foundations you can build on from the gaps, explains what each fix makes possible and names who has to be involved. You start the build knowing its real scope.
Data has to be cleaned up and moved to modern systems, processes have to be re-engineered and documented, workflows have to be evaled, SLAs have to get achieved, and so on.
BoxJune 2026Source What the team works through after the report.
The report opens on the workflow you picked and a score for each area against what that agent needs. Areas that fall short sit at the top, each with the finding, the records we read, the next action, a named owner and an estimated effort.
Owners take their fixes from there. Each finding can be assigned, accepted as it is or closed, and decisions are written next to it in plain words, linking the people, documents and systems they name. Anyone can ask what blocks the build and get an answer that points to the evidence.
What every readiness report contains.
Your systems and gaps differ. The report is built the same way each time.
Workflow scope
The agent task the score is measured against, agreed at the start.
Systems inventory
Your sources, systems, process instructions and access arrangements, listed.
Record samples
Representative records read to see what an agent would actually find.
Team interviews
Conversations with the people who do the work today.
Readiness score
A 0 to 100 score with a breakdown by category.
Evidence file
Every finding linked to the sources and systems reviewed.
Ordered fixes
Actions ranked by the work they enable, with effort and dependencies.
Named owners
Who has to be involved in each fix, so the list can be handed out.
How the readiness report is assembled.
Inspect the current setup
We inventory your sources, systems, process instructions and access arrangements. Representative records and conversations with the team reveal how the work happens and where the proposed system would need help.
Inventory - CRM · 18,400 recordssampled 200
- Order inboxread 3 weeks
- Process notes2 of 6 written down
- Admin accessone person holds it
Assess each dependency
We assess readiness across data, process, tools and permissions. Findings link back to the evidence reviewed, so your technical and operating teams can understand the reason behind each part of the score.
Readiness by area Put the fixes in order
We rank the actions by the work they enable, their expected effort and their dependencies. You receive the score breakdown, evidence file and an ordered list of improvements to discuss with owners.
Fixes, in order - Write the returns process downunblocks 3 builds
- Split the shared admin logintwo days
- Clean duplicate CRM accountsone week
- Add API access to the ERPvendor quote
Scored once.
Re-scored every quarter.
Fixes land, systems change and the next workflow comes up. After the report we can re-run the assessment each quarter, so the score shows what moved and what still stands between you and the build.
Re-score
Each area assessed again with the same checks, next to last quarter’s score.
Fix tracking
Every fix followed from open to closed, with its owner and the date it closed.
Next workflow
A new workflow scored against what its agent would need, before anyone scopes the build.
Review session
A quarterly session with the owners on what moved, what stalled and what to fix next.
What you
receive.
Readiness assessment
A 0–100 score with a breakdown by category.
Evidence file
Findings linked to the sources and systems reviewed.
Prioritized fixes
Actions with estimated effort and dependencies.
Where the audit leads.
Each next step has its own service.
Floor Plan
Comes before the audit: the workflows it checks your data and systems against.
$6,400
Source Cleanup
Fixes the data the audit flagged, so agents read one clean version of it.
$12,800
Agent Onboarding
Connects the systems that passed, with an owner and the right access for every agent.
$9,600 + $1,600/mo
MCP Retrofit
When your own product is the gap: an interface assistants and agents can use.
$12,800
Before you ask.
Which workflow is the score measured against?
One you choose with us at the start, usually the first task you want an agent to take on. Every area is scored against what that agent would need.
What access do you need to our systems?
An inventory, representative records and a view of how access is set up. We agree with your IT lead in advance what we look at and how.
Does the audit include fixing the gaps?
No. You receive the score, the evidence file and an ordered list of fixes with owners and effort. The build can be scoped once the gaps are known.
What if our score is low?
Then you know before the build budget is spent. The fix list separates the gaps that block the first workflow from the ones that can wait.