How it works

Unlock your organizational intelligence.

A via ferrata is a fixed steel line bolted into rock so that people who aren’t technical climbers can cross terrain they otherwise couldn’t. The line goes in before anyone climbs. Same order of operations here, foundation first, agents second, your team third.

01

Assess

We map workflows, not org charts. Transaction volumes, exception rates, where people are re-keying between systems, what the errors cost when they escape. In parallel we audit what you already have, cloud posture, data residency obligations, what your security team will and won't allow.

The output is a ranked list with a defensible number against each line. You keep it whether or not you continue with us, because a ranking you can't take to your board isn't worth the two weeks.

2 weeks · you keep the output either way

You get

  • Ranked workflows with a cost attached to each
  • A target architecture for your environment
  • What runs frontier, what runs open-weight, and why
Your workflows, mappedAccounts payableInvoice intake and coding14,200 / moThree-way match exceptions2,900 / moVendor query handling1,450 / moPayment run preparation4 / moMeasured in your systems, not benchmarkedWhat it costs todayPeople6.4 FTE, fully loaded$418,000Software3 subscriptions, annual$96,000Cost of the function$514,000a year, before errorsFigures illustrative. Every candidate workflow gets this treatment
02

Anchor the platform

The foundational step, and the one most firms skip. We stand up model access and routing, serving for open-weight models where cost or residency demands it, retrieval across your documents and systems of record, evaluation harnesses, and the logging that makes any of it defensible.

It runs in your environment and it belongs to you. This is the difference between buying agents and owning the capability to run them, and it is why the fourth step is possible at all.

3 weeks · the asset you keep

What gets built

  • Model gateway across frontier and open-weight
  • Retrieval over your own corpus and systems
  • Inference in your VPC or on-premise
  • Evaluation, cost controls and audit logging
  • Identity and access wired to your directory
Your environmentModel gatewayRetrievalEvaluationAudit loggingIdentityOpen-weight, served in your VPCFrontier, called out under policyThe asset you keep
03

First agent live

One agent, one workflow, in production against real transactions with a human approval gate on every action that matters. You watch it work on your own numbers before committing to a second.

It's configured to your rules, your pricing logic, your approval thresholds, your escalation paths. This is where the Agent Development Lifecycle runs, and where you see what disciplined agent engineering actually looks like from the inside.

Under 90 days from start

Non-negotiable

  • Nothing releases cash without approval
  • Every action logged and attributable
  • Rollback path defined before go-live
Real transactionsLivetransactionsAgentreads · decides · draftsGateA personapprovesPosted tothe ERPOverrides return as training signalUnder 90 days
04

Expand, then hand over

Add agents as trust builds. When you want it in-house we install the POD operating model, one lead, one product owner and two full-stack AI developers per unit, with runbooks and evaluation harnesses documented.

Your engineers build the next agents themselves, on infrastructure designed from day one to be handed over. You should never need us to change a prompt.

Ongoing, or until you don't need us

Enablement

  • POD structure and hiring profile
  • Agent development runbooks
  • Evaluation harness your team can extend
  • Managed operation if you'd rather not
Ferrata operatesYou operateAgent 1Agent 2Agent 3Agent 4Agent 5Agent 6The POD1Lead1Product owner2AI developersHanded overRunbooks · eval harnessPlatform in your environment

What changes, and where.

Transformation is not a model licence. It happens in three places at once, and skipping any one of them is why most of it stalls.

Layer 01

People

We deploy the POD operating model into your team, working on your systems and your rules to unlock the organizational intelligence you already have. Your people learn the framework while it is being built. By the end they are building the next agent on it themselves.

Layer 02

Product

Agents wired into the systems you already run, acting on live transactions. Nothing is re-platformed: the agents are infused into the products your team already works in. The approvals they stop at happen on the platform we stand up with you.

Layer 03

Process

Agentic workflow that runs on the rules your business already follows: your approval thresholds, your escalation paths, your guardrails. Encoded, audited and governed rather than reinvented, so the agents work on top of the framework you have.

ADLC

Agent development is a discipline now. We run it like one.

Software got reliable when teams stopped treating each build as a one-off and adopted a lifecycle around it. Agents are at the same point, and most of what goes wrong in enterprise AI is not the model, it is shipping without a lifecycle. Ours has eight phases, and every agent we put into production goes through all of them.

01

Scope

One workflow, stated as a contract: the inputs, the decision boundary, what the agent may never do.

02

Ground

Wire the agent to real systems of record and real documents. No demo data, grounding failures surface here or in production.

03

Build

Tools, prompts, routing and fallbacks. Frontier or open-weight decided per task on cost, latency and sensitivity.

04

Evaluate

A harness of real historical cases with known-correct outcomes. The agent is scored against them, not demonstrated on a happy path.

05

Gate

Human approval on every consequential action, plus the rollback path, both defined before go-live rather than after an incident.

06

Deploy

Into your environment, against live transactions, at a volume you choose. Logged and attributable from the first action.

07

Observe

Accuracy, exception rate, cost per transaction and gate overrides tracked continuously. Drift is caught by the harness, not by a person noticing.

08

Improve

Overrides are the training signal. Each one is examined, and the agent earns wider autonomy only on evidence.

What SDLC settled

  • Version control and reproducible builds
  • Automated test suites before release
  • Staging environments and rollback plans
  • Monitoring, alerting and on-call
  • Postmortems that change the next build

What ADLC settles

  • Evaluation harnesses over historical cases
  • Grounding against systems of record, not demo data
  • Approval gates as the default, autonomy as earned
  • Cost, latency and accuracy watched per transaction
  • Overrides fed back as the improvement signal

The harnesses, runbooks and gates that come out of this are documented and handed to your team in step 04. The lifecycle is the transferable part; the agents are just what it produces.

Questions we get asked early.

The ones that come up in nearly every first conversation, answered the way we’d answer them on the call.

Where does our data actually go?
Into infrastructure standing in your environment. Retrieval runs over your own systems of record. Where residency or sensitivity requires it, models are served inside your VPC or on-premise rather than called out to a third party. What leaves your boundary, and to whom, is decided in step one and documented before anything is built.
Do you train on our data?
No. Your operating logic is your advantage and it stays yours. If fine-tuning makes sense for a specific workflow, the resulting model is yours, trained in your environment, and it doesn't inform anything we build for anyone else.
What happens if an agent gets it wrong?
It gets caught at the approval gate, because agents start behind one and only earn their way out with evidence. Every action is logged and attributable, and a rollback path is defined before go-live rather than after an incident.
Frontier models or open-weight?
Both, usually. The decision is made per workflow on cost, latency and sensitivity rather than as a company-wide religion. High-volume classification is rarely worth frontier pricing; a nuanced negotiation draft usually is.
Are we locked into you?
The platform runs in your environment and the runbooks are yours. Step four exists specifically so your own engineers can build the next agents without us. We'd rather you outgrow the engagement than depend on it.
What does this cost?
It depends on the workflow and how much of your environment already exists, which is why the assessment comes first and why you keep its output either way. We'll give you a range on the first call rather than making you sit through a process to find out.

Bring us one workflow.

Thirty minutes, no deck. Pick the process that costs you most in people, errors or delay, and we'll pressure-test whether an agent is genuinely the right answer for it.

  • An honest read on whether that workflow is a good agent candidate
  • What the first deployment would involve, and roughly what it costs
  • An honest answer if the sequencing is wrong and you should fix something else first
Book a discovery call