Production AI engineering, scoped as fixed engagements.
Each engagement is one bounded piece of work with a fixed scope, a fixed duration, and a single deliverable pack. Start with the workflow build, or with the review, deployment, or audit that fits where you are.
Available for one-to-two engagements at a time.
Production AI workflow build
The anchor engagement. One bounded workflow, six weeks, a single architect, and one deliverable pack. Fixed scope, fixed duration. From GBP 25,000.
When this fits
A useful AI workflow, prototype, or AI-assisted manual process works in demonstrations but cannot yet run as part of regular operations, because the workflow boundary, source-system access, tool authority, approval points, evaluation evidence, telemetry, release ownership, rollback, and runbook are undefined.
What you get
One workflow build pack: a deployed service in your environment, plus the workflow boundary map, evaluation fixture suite, run-evidence schema, release-gate rubric, deployment handover notes, and a runbook your team can operate from. Related proof: from AI prototype to controlled workflow.
Shape
Six weeks from kick-off to handover, with a scoping checkpoint at the end of week one. If the workflow cannot be bounded to fit six weeks, scope is trimmed or the engagement is paused before the build phase starts.
Boundary
Radian IT owns the scoped workflow boundary, build, integration, evaluation baseline, telemetry, release controls, and handover. You own data-access decisions, production approval, user rollout, and regulated decision policy.
Other engagements
Three further engagements sit alongside the workflow build. Each is fixed in scope and duration, with a single deliverable pack.
Agent or RAG behaviour is inconsistent, hard to debug, over-reliant on prompt context, or unsafe to expand. You get an architecture review, retrieval and memory boundary design, a risk register, an evaluation outline, and an implementation plan. One bounded system, two weeks. Fixed scope, fixed duration. From GBP 8,000. Related proof: why agent memory needs architecture before autonomy.
You want to operate an open agentic-stack runtime without owning the whole deployment path. You get a deployed and hardened runtime in your environment, with integration, tool policy, memory and channel setup where appropriate, handover notes, and a runbook. One named runtime into one environment, three weeks. Fixed scope, fixed duration. From GBP 18,000.
An agentic workflow is nearing regular use before tool authority, approval points, audit evidence, costs, or release gates are clear. You get a workflow and tool-authority map, a telemetry and audit-evidence gap analysis, a fixture outline, a risk register, release-gate recommendations, and a control roadmap. One bounded workflow, two weeks. Fixed scope, fixed duration. From GBP 10,000. Related proof: how to evaluate agentic workflows before rollout.
Supporting capabilities
Most production AI workflows have to integrate with existing business systems, automation, bespoke software, reporting, and support tools. Radian IT has operated in those layers since 2005; that experience shapes how the workflow boundary is drawn, where data enters and leaves, and how the runbook hands the workflow back to the buyer's team.
AI checks before wider use
For AI-assisted workflows, the useful question is not whether the demo looks plausible. It is whether the workflow has boundaries, evidence, and a clear release decision.
Boundary
Define the job, source systems, allowed actions, approval points, fallback path, and owner.
Fixtures
Test expected cases, denied access, stale information, missing sources, prompt injection, costs, latency, and known failures.
Evidence
Record retrieved sources, tool calls, approvals, denials, output decisions, cost, latency, and audit events.
Decision
Turn the results into fixes, release gates, runbook checks, or buyer-owned risk decisions.
A sensible first step
Send the situation
Tell us what the workflow does now, what needs to change, and any timing, budget, approval, or system constraints.
Agree the engagement and scope
We agree which engagement fits. A scoping checkpoint in week one bounds the work before the build phase starts.
Fixed delivery and handover
The engagement runs to its fixed duration and ends with the deliverable pack, evaluation fixtures, release controls, and a runbook that make ownership clear.
Practical details
Commercial shape
Each engagement is fixed in scope and duration with a published 'from' band. A scoping checkpoint in week one bounds the work before the build phase starts. Day rates and retainer rates are not published.
Working model
Remote-first. Engineering hours overlap with European and US East Coast windows. Onsite by arrangement where the engagement requires it.
Confidentiality
Client references are kept anonymous and plural by policy. Public examples stay generic unless exact wording has been approved.
Contact
Email [email protected] with the workflow, the desired change, and any deadline or constraint.
Start with a short note.
Email [email protected] with what the workflow does now and what needs to change.