Workflow Compass
Find the workflow worth automating — and the one that isn't.
Workflow Compass maps how your work actually runs, then scores each step for how well an agent fits. You begin the build already knowing it's the right one.
What it addresses
Most AI pilots fail the same way: the wrong workflow gets automated first. A team picks something visible, or easy, or whatever was top of mind, sinks weeks into it, and the payoff isn't there — while the work that would have paid off sits untouched. Choosing well is the hard part, and it usually happens on instinct, under time pressure, with no evidence to point to.
The capabilities
Workflow canvas
Map your processes into clear steps: who does what, which systems are involved, and where the decisions sit. A navigable map of the work, not a deck.
Fit-scoring engine
Each step is scored against what actually decides whether an agent will work: data availability, how structured the decisions are, volume, error tolerance, and how much human judgement is required. You see the score and the reasoning behind it — not a black-box rating.
Opportunity report
A ranked set of automation candidates with fit scores, indicative payoff, and a recommended approach for each — evidence you can put in front of the people who sign off.
Build-spec generator
For the option you choose, Compass produces a structured build specification — target workflow, agent approach, input/output contract, data and governance requirements — ready to hand to the build phase.
End to end
Map — you describe your workflows; Compass structures them into steps, actors, systems, and decision points.
Score — the fit-scoring engine rates each step across the readiness axes, keeping the evidence behind every score.
Prioritise — fit, operational cost, and strategic weight combine into a ranked opportunity backlog.
Specify — the opportunity you choose becomes a structured build spec.
Hand off — that spec passes straight to Wrought to begin the build.
How we decide which of Educate, Build, or Run fits a given piece of work is set out in our method — see how it works →
The case for it
The first build is the right build.
Compass surfaces the highest-fit opportunity, with evidence, before you commit to building anything.
Scoping in days, not workshops.
A structured, software-led assessment in place of weeks of open-ended discovery.
Evidence your stakeholders can check.
The scored report is the internal champion's case for why this workflow first — your evidence, not a vendor's assertion.
A low-commitment way in.
Compass delivers a prioritised AI backlog before any build spend — the lowest-friction entry to the work.
On the lifecycle
Workflow Compass is the front door of the scope → build → run lifecycle. Its output feeds Wrought, where the chosen workflow becomes a deployed agent; Wrought hands on to Operations Console, where it runs in production. All three sit on the always-on AI Observability foundation. Compass is also the software our human-led Build engagements scope with — the service line and the product work the same phase from two sides.
Prefer to work with a team rather than a tool? Our human-led Build service line runs the same phase as an engagement — distinct from the software, two sides of the same work.
What runs underneath
Beneath all three: always-on monitoring of every agent — what it did, what it cost, where it drifted. The foundation the lifecycle runs on.