What consultancies tell us

“We can't act until we understand the current process and its bottlenecks, and getting that out of people's heads takes too long.”

“
Clients are asking us to map every workflow in the business, work out which ones are ripe for AI, and tell them what it would save. We've done two of those by hand and lost more than we've won. Sitting consultants down to interview everyone for weeks isn't how it works anymore.
Engagement lead, strategy consultancy

“
We'd committed to an AI rollout and the board was watching. The only map we had was an SOP written two years ago. Every workshop ran differently depending on who facilitated it, and nobody had asked the people doing the work how it really runs.
What their clients say: Head of AI transformation, industrial manufacturer

How it works

Give Workstuff the goal and the org chart. It finds the people, interviews them, and hands you the map of work.

Understands the business. Start from the goal, the org chart and the documents you already have. Your methodology gives every interview the same structure.
Finds the right people. It works out who holds the knowledge and what to ask each of them, learning from each conversation to ask better questions of the next.
Interviews them. AI voice or text, on their own time, with documents attached. No meetings.
Analyzes what they say. Every account reconciled into one data set, traced to who said it.
Builds the map of work. The steps, decisions, exceptions and bottlenecks as they actually run.
Finds the AI opportunities. Ranked by how ready each workflow is and the time it would save.

Run it from the app, or from Claude or Codex via MCP.

workstuff

> Find out how our claims process really works. Ask everyone in claims ops.
● Planning interviews
  · 180 people across 6 teams
  · 12 questions, voice or text
  · portal at acme.workstuff.ai
● Portal live. Invitations sent to 180 people.
● 148 accounts reconciled into 47 steps, 9 decisions, 12 exceptions.
>

What it becomes

Every interview feeds two things: a map of work and a ranked list of AI opportunities.

From those, Workstuff generates client-ready deliverables in your own format, carrying the context from discovery through design, delivery and ongoing improvement. Each stage builds on what you already know.

01

The Map of Work

Every process as it actually runs: the steps, the decisions and who makes them, the exceptions, and where it slows down, jams, or breaks, from the people doing it.

02

AI Roadmap and Use Cases

Rank every workflow in the business on how ready it is for AI and how much time it would save, based on what the people doing it told you.

03

Consulting Proposals and Business Cases

Run a deep discovery to surface the real pain points, quantify the value, and price the work on what it is worth.

04

Context for Agents

AI agents are good at following a clear process; they cannot invent one. Give an agent the real picture of the work, so it starts on facts instead of assumptions that break it.

05

Knowledge Bases and Documents

Turn what's in people's heads but never written down into documentation the team can actually use.

06

An Ontology of the Organization

A digital map of how the client's organization actually works: the people, the processes, the decisions and the challenges.

For consultancies

Level up your firm's AI offering.

Workstuff goes into your proposal as a capability your firm brings to the work. Build your methodology into templates so every engagement runs the same way. Sell AI discovery, AI roadmaps and process mapping as productized offerings, under your own name, at your own price.

Pre-project

Win the work on evidence

Build the business case around the problems actually worth solving, sized from the client's own people before the proposal goes in.

In-project

Capture how the work gets done

The map of work for every process in scope, without pulling the client's people into weeks of workshops.

At the end

Evidence the value you created

Interview the same people again and show what changed, in their words and in the numbers.

The solution

An AI interviewer that finds the use cases worth building, and the evidence to measure the change.

Send a link. 100 people talk through how the work really gets done, and the AI probes for detail.
Your questions guide the interviews. Workstuff reconciles every account into one version, and flags where they clash.
When the build team asks how the process runs, you have the answer, with a name attached.

An AI-led interview running on a phone, by voice or text

100 people interviewed in 6 days. No meetings booked.

100People interviewed

6 daysTo a full library

Every answerTraced to who said it

Build-readyA spec, not a slide deck

See which processes are actually ready.

AI agents are good at following a clear process; they cannot invent one. Turn the interviews into a scored view of every process: documented steps, an owner for every decision, and a known list of exceptions, including the work that never made it into the SOP. You know which one to automate first, and which one will bite you.

Process health scored across steps, decisions, exceptions and readiness to automate

And how the work actually gets done.

Not one person's version. Every account of the same process, reconciled into one map. Where people agreed, it is settled. Where they did not, you see both versions rather than the loudest one.

A current-state process map with numbered steps, a loop and a revenue leak

01

Process steps

What actually happens, in order, including the step that never made it into the SOP.

02

Decisions

Who decides, on what basis, and who they go and ask when they aren't sure.

03

Exceptions

The cases that don't follow the rule. The ones that break an agent on its first day.

04

Pains

Where the work is slow, done twice, or quietly hated by everyone doing it.

05

Ideas

What the people doing the job would fix first, which nobody has ever asked them.

The difference

The same process, two very different builds.

Build from an SOP somebody wrote two years ago

↓

Build from what the people doing the job said last week

Discovery quality depends on which analyst you can spare

↓

Your best analyst's method in every conversation, whoever runs it

Debrief after every workshop and hope the notes are good

↓

Every conversation comes back structured: the steps, the decisions, the exceptions

Ship the agent and find the edge cases in production

↓

Know the exceptions before anyone writes a line of it

Send a survey, get a 20% response rate, get charts

↓

Send a link, get 80% completion, get the story behind the numbers

Every process starts from scratch

↓

Every process builds on the library you already have

Interview 100 stakeholders without scheduling a single workshop.