# From Ecosystem Consultant to Claude: A Cross-Training Pack

> You consult in Salesforce, ServiceNow, SAP or another enterprise ecosystem and want to move into Claude and AI agents. What transfers, what to learn, and six exercises that leave you with a portfolio.

Source: https://kowalah.com/resources/templates/consultant-to-claude-cross-training

## Overview

- **Who it's for:** Business analysts, functional and configuration consultants, solution architects and delivery leads at a Salesforce, ServiceNow, Google Cloud, Databricks, SAP, Workday or Dynamics partner, who want to move into Claude and AI agent delivery
- **When to use it:** When you have decided you want to get into this work and do not know where to start, or when you have done the courses and have nothing to show for them yet
- **What you get:** Six artefacts built on a fictional client, from a discovery workshop to an agent design, that show an employer you can do the job, without going near your current clients' data

## Get it

- **Claude skill `consultant-to-claude`:** https://18evqetn8qvaaj3d.public.blob.vercel-storage.com/skills/kowalah-consultant-to-claude.zip

## How to Use This Pack

1. **Install the skill.** Download the .zip above. In Claude, go to **Customize > Skills**, upload the file, and enable it. The skill runs every exercise with you, plays the stakeholders in the workshop rehearsal, and reviews what you build
2. **Start with an assessment.** Tell Claude your ecosystem and role. It translates what you do now into Claude terms and tells you where to start
3. **Learn the topic, then do the exercise.** Each exercise names a topic to study at Claude Academy first. The Academy gives you the language, the exercise gives you something to show
4. **Keep the artefacts.** Each exercise leaves you with one. Together they are a portfolio, and the pack shows you how to write it up

# From ecosystem consultant to Claude

You consult in an enterprise ecosystem. Salesforce, ServiceNow, Google Cloud,
Databricks, SAP, Workday, Dynamics. You run discovery workshops, map processes,
write requirements, configure, design, and get a change landed so it sticks.

You have been watching AI from the side of the room, and you want to be in the
middle of it. You do not know where to start, and the courses you have looked at
teach the platform as though you were starting from nothing.

You are not starting from nothing. This pack covers what transfers, what to
learn, and six exercises that take you from your first real Claude work to an
agent design, each leaving you with an artefact you can show.

There is an installable Claude skill that runs all of it with you, above. It
assesses where you are starting from, runs each exercise (including playing five
difficult stakeholders in a workshop rehearsal), and reviews what you build
against the bar a hiring team would use.

---

# What you already have

The hard part of getting AI into production is not the model. It is
understanding the process well enough to know what an agent should do, and
landing the change so people use it. Consultants from other ecosystems already
have that:

- Running a workshop where the stakeholders disagree with each other
- Mapping a process as it runs, not as the documentation says it runs
- Knowing when a requirement is a political constraint in disguise
- Being the outsider in someone else's building and earning trust inside a day
- Landing a change so it sticks, rather than shipping software and leaving

An agent built without this understanding is a demo. An agent built with it is
the thing people keep using at month six.

# What you need to learn

- What Claude does well, where it stops, and how to tell the difference on real
  work
- How skills, plugins, connectors and agents fit together
- MCP, the standard that connects Claude to the systems a business already runs
- Writing instructions a model follows consistently, which is a craft rather
  than a knack
- Claude Code, which is where build work happens

# What will be hard

**Writing logic in prose.** Configuration trains you to express logic as
settings. A skill is logic in sentences, and ambiguity in a sentence becomes
inconsistency in behaviour.

**Probabilistic behaviour.** The same input can produce different outputs. The
job is making the variation acceptable and catching it when it is not.

**The pace.** A prototype takes an afternoon. If you come from an ecosystem with
quarterly releases, the instinct is to over-plan the first build. Build it, test
it, change it.

**Being the builder.** If your ecosystem has a separate dev team, you are used to
handing specs over. Here the person who ran the workshop builds the first
version.

---

# The translation table

The fastest way into the Claude platform is through the one you know.

| What you know | Claude equivalent | Where the analogy breaks |
|---------------|-------------------|--------------------------|
| A Flow, a workflow rule, a Business Rule | A **skill**: plain-English instructions, plus reference files and templates, that Claude loads when a task matches | Nobody wires up the trigger. Claude reads the skill's description and decides when to use it, so the description does the job of the entry criteria. |
| A managed package, a scoped app | A **plugin**: skills and connectors bundled so a team installs them in one go | Far lighter. A plugin is mostly text files you can read in ten minutes. |
| An integration user, a Named Credential | An **MCP connector**: tools that reach a system, with the permissions of whoever signs in | Claude chooses when to call a tool and with what inputs, so you design tools where a wrong call is harmless or blocked. |
| Permission sets, profiles, ACLs | Connector scopes, the tools you expose, and what the agent is told it is allowed to do | Instructions guide, they do not enforce. Anything that must never happen has to be blocked in the tool or the system. |
| A sandbox | A Claude Code working copy, or a test organisation behind a connector | Instant and disposable. Make one per experiment. |
| An Einstein bot, a Virtual Agent topic | An **agent**: a model with instructions, tools, memory and a goal, working in a loop until the task is done | A bot follows a tree you drew. An agent decides its own next step. You design the boundaries and the checks, not the path. |
| A solution design document | An **agent design**: purpose, instructions, tools, data, guardrails, cost, owner | It includes how you will test it, because behaviour varies from run to run. |
| UAT scripts | **Evaluations**: realistic inputs with the expected output, rerun after every change | You rerun them every time, not once before go-live. A fix for one case can quietly break another. |
| Requirements gathering | Requirements gathering | This part transfers whole. |

---

# Where to learn the platform

Anthropic runs a free [Claude Academy](https://academy.claude.com). It has
courses on using Claude for everyday work, on what language models can and
cannot do, on Claude Code, on building and sharing skills, on connecting Claude
to other systems with MCP, and on building agents with the Claude API.

This pack does not repeat any of it. Each exercise below names the topic to
study first, and then gives you something to build with it.

Keep the courses in proportion. They give you the language. What you build gives
you something to talk about. Someone who has finished every course and built
nothing has not moved, and an employer can tell within a minute.

---

# The exercises

Exercises 2 to 6 run on one fictional client, **Hartwell Freight**: a UK road
freight company, 2,400 people, four months into an Anthropic Enterprise
agreement, with a CIO who has promised the board two AI processes in production.
Her first choice is customer claims. 900 a month, 19 days to close, and a
finance director who believes £400,000 a year goes on claims Hartwell was not
liable for.

The skill holds the full brief, including five stakeholders who each know
something they will not volunteer unless you ask the right question.

A fictional client matters for a reason beyond convenience. Your current
clients' data, documents and system details should never go into a personal
Claude account, even anonymised. Your employer's contracts almost certainly
forbid it, and a portfolio built on a client's material becomes a liability the
moment an interviewer asks where it came from.

Each exercise's output is the next one's input.

## 1. Your own work, pushed as far as it goes

**Learn first:** the Academy's introductory material on using Claude for
everyday work, and on what models can and cannot do.

Take something you wrote yourself and own: a workshop agenda, a requirements
template, a process guide. Remove anything that identifies a client. Hand it to
Claude and keep pushing past the point where you would normally stop. Restructure
it, rewrite it for a different audience, turn it into an interactive artifact,
ask what is missing.

**You end with:** the before and after, and a note of what surprised you and
what Claude got wrong that would have embarrassed you.

This is the most important of the six. It shows you reach for AI on your own
work before anyone asks you to, which is the first thing an employer in this
space looks for.

## 2. Plan a discovery workshop, and rehearse it

**Learn first:** the Academy's material on working with AI effectively: how to
delegate, describe what you want, and judge what comes back.

Plan the half-day claims workshop at Hartwell with Claude: objectives, agenda,
stakeholder map, question bank. Then rehearse it. The skill plays the CIO, the
head of customer service, the finance controller, a depot manager and a senior
claims handler, in character, and holds back what each of them would hold back
in a real room.

Afterwards it steps out of character and tells you which of the hidden facts
you found, which you missed, and the question that would have found each.

**You end with:** a workshop plan and a rehearsal debrief.

## 3. Map the process and find where AI changes it

**Learn first:** nothing new. This is your existing craft. Our guide to
[mapping an AI operating model](/resources/templates/map-your-ai-operating-model)
covers the method we use, if you want it.

Map the claims process as it runs, from what the rehearsal uncovered: every
step, who does it, how long it takes, where it waits. Then draw the future state
and mark each step as done by a person, done by Claude with a person approving,
or done by Claude alone. For each Claude step, note what it needs to reach, and
whether security has approved that.

If you prefer, map it in the [Kowalah Plugin](/platform/plugin) in Claude.
Installing it and signing in gives you your own organisation with an empty
operating model, free. A document or a diagram works as well for the exercise.

**You end with:** a current-state map, a future-state map with each step
classified, and the access each Claude step needs.

## 4. Build the client playback

**Learn first:** by doing. Claude Design builds decks, one-pagers and prototypes
from a conversation.

Build what you would take back to Hartwell's CIO a week after the workshop: what
you found, the current and future state, the one first build you recommend, what
has to be true for it to go ahead, and the next step. Write it for a CIO who
will forward it to the finance director.

**You end with:** a deliverable you would be comfortable sending to a real
client. It leads with what you found, not with what AI can do.

## 5. Package your method as a skill

**Learn first:** the Academy's material on building and sharing skills, and its
introduction to Claude Code.

Turn the way you plan discovery workshops into a Claude skill: a folder with a
SKILL.md and, where they help, reference files and templates, so a colleague can
plan a workshop for any process the way you planned Hartwell's. Install it, test
it on a process that is not claims, and revise it.

The description at the top of a skill decides when Claude uses it. Test that it
fires on "help me prep a stakeholder session" and does not fire on "write an
agenda for the team meeting". Our [Claude skill template](/resources/templates/claude-skill-template)
shows the structure.

**You end with:** a working skill, tested on two cases, with a note of what you
changed after testing.

## 6. Architect your first agent

**Learn first:** the Academy's material on connecting Claude to other systems
with MCP, and on building agents with the Claude API.

Design the agent for the highest-value step in your future-state map. At
Hartwell that is gathering the evidence for a claim, checking it against the
customer's contract, and drafting a recommendation for a handler to approve.
The skill includes a design template covering purpose, what the agent must never
do and how that is enforced, tools and access, evaluation cases, cost per day,
and where your build stops.

That last one matters more than it looks. A prototype proves the process works.
A production agent needs authentication, monitoring and error handling at
volume, and a good builder knows which of those to hand to a platform team
rather than build alone.

**Stretch:** build a working prototype in Claude Code against a folder of
made-up claims, contracts and delivery records.

**You end with:** an agent design, a set of evaluation cases, and optionally a
prototype that passes them.

---

# Turning it into a portfolio

Six exercises, six artefacts. Written up one page each, they show an employer
the whole arc of the job: understanding a business, finding where AI changes a
process, building the thing, and knowing its limits.

The skill includes a portfolio template. Three rules for it:

**Label the fictional client as fictional.** Presenting Hartwell as a real
engagement is found out in the first follow-up question.

**Show what went wrong.** What Claude got wrong in exercise 1, what you missed
in the rehearsal, what you changed after testing the skill. Candour about limits
reads as experience.

**Be ready to explain every decision.** An interviewer will pick one choice in
one artefact and ask why. If the answer is "Claude suggested it", the artefact
is working against you. The skill's review mode gives you the questions an
interviewer is likely to ask about each piece.

## Frequently Asked Questions

### I'm a Salesforce consultant. Is my experience relevant to AI work?

It is the harder half of the job. Building a Claude agent that works in production depends on understanding the process it serves: who does each step, where the time goes, which rule is a workaround in disguise, who will resist. Running workshops where stakeholders disagree and mapping a process as it runs rather than as it is documented are exactly the skills that separate an agent people use from a demo nobody uses. The platform side, skills, connectors and agent design, is learnable in weeks. The consulting side takes years, and you already have it.

### Do I need to be able to code?

You need to be comfortable in Claude Code, which is where build work happens, and able to read what it writes well enough to know when it is wrong. You do not need to write code from scratch. Configuration consultants and BAs make the move without a programming background. The bigger shift is writing instructions in precise prose rather than setting fields, which is harder than it sounds and is what exercise 5 is for.

### Where do I learn the Claude platform itself?

Anthropic runs a free Claude Academy at academy.claude.com, with courses on using Claude for everyday work, on Claude Code, on building skills, on connecting Claude to other systems with MCP, and on building agents with the Claude API. This pack does not repeat any of it. Each exercise tells you which topic to study there first, and then gives you something to build with what you learned.

### Why use a fictional client rather than my own projects?

Because your current clients' data, documents and system details should never go into a personal Claude account, even anonymised. Your employer's contracts almost certainly forbid it, and a portfolio built on a client's material becomes a liability the moment an interviewer asks where it came from. The fictional client, a UK freight company with a claims problem and five stakeholders who each know something they will not volunteer, is built to be realistic enough to practise on. Exercise 1 is the exception: it uses your own work, a template or method you wrote, with anything identifying removed.

### How long does it take?

At three to four hours a week, a month to six weeks for all six exercises, plus the Academy study alongside. Exercise 1 takes an evening and is the most important. If you do only one, do that one: it shows you reach for AI on your own work, which is the first thing an employer in this space looks for.

### What is the difference between a skill, a plugin, a connector and an agent?

A skill is plain-English instructions, with reference files and templates, that Claude loads when a task matches, closest to a Flow written in sentences. A plugin bundles skills and connectors so a team installs them together, closest to a managed package. A connector, built on MCP, gives Claude tools that reach a system with the permissions of whoever signs in, closest to an integration user. An agent is a model with instructions, tools and a goal, deciding its own next step until the task is done. The translation table in this pack covers each, and where the analogy breaks.

### What role does this lead to?

The closest is a forward deployed engineer: on site with a client, running the discovery, mapping how the business works, then building the skills, agents and prototypes that prove a better process in Claude and Claude Code. The six exercises follow that job from first workshop to agent design. Internal roles with titles like AI Operations Lead or AI enablement lead draw on the same skills.

### Can I use Claude Design for client deliverables?

Yes. Claude Design builds decks, one-pagers and prototypes from a conversation, and exercise 4 uses it to build the playback you would take back to a CIO after a discovery workshop. Hold it to the standard of any client deliverable: it leads with what you found, recommends one thing, and a CIO can forward it to the finance director unedited.

---

Free and ungated, from Kowalah, a UK Anthropic implementation specialist. More templates and skills: https://kowalah.com/resources/templates. Talk to us: https://kowalah.com/contact