AI agents and workflow automation

Put AI to work across a real business workflow

A document arrives, someone checks three systems, and the next team waits for an answer. That is a useful place to explore AI. Tenhaw works with the people doing the job to design a workflow that gathers information, prepares the next action and brings the right decisions back to them. Start with one process and test it against the cases your team actually handles.
Talk it through

30 minutes with James Rooney to discuss your team, workflow and first scope.

See the evidence and approach
The job to be done

What we can help you deliver

For operations and technology leaders joining up work across documents, systems and teams, with a clear owner for the result and people available to shape the first version.

Your team can follow each handoff

Give each stage a clear input, output and owner. Show reviewers where information came from and what needs their attention before work moves on.

Approvals stay part of the workflow

Agree which actions the system may take, which need a person and how exceptions return to the team. Build those decisions into the process.

The first build informs the next decision

Test completion, errors, review effort and running cost against an agreed starting point. Use the results to decide what deserves further investment.

Use a 30-minute call to discuss the outcome your team needs.

Talk it through
Working together

Build the capability around real work

  1. 01

    Map the work with its owners

    Bring the ordinary cases and the awkward ones. We trace the handoffs, permissions and decisions, then choose a useful slice for a proof of concept.

  2. 02

    Build inside your environment

    Connect the necessary data and tools within your agreed access controls. Pair with your engineers and test the workflow with the people who will review its output.

  3. 03

    Plan how the team will operate it

    Define the review queue, monitoring, support responsibilities and release criteria. A continuing build engagement develops the software and the working practices around it together.

Ask how this approach would fit your data, systems and team on a 30-minute call.

Talk it through
Evidence and approach

Read the evidence behind the approach

Documents became business intelligence at PPL

At Placing Platform Limited, the London market digital placing platform, Tenhaw paired with a client engineer to build a working proof of concept in two weeks. PDFs became structured, enriched data feeding a dashboard the business already used, on Azure.

Read the PPL document workflow case study

Book 30 minutes to ask James about the work and how it relates to your situation.

Talk it through
Scope and price

Choose a starting engagement

Agree the workflow, deliverables and team before work starts. These are the existing engagements this use case can sit within; prices exclude VAT.

AI Readiness Audit

Fixed price · £44,000

4 weeks

Find the AI workflows worth funding. Test them with your team.

See scope, team and terms

Agentic Proof of Concept

Fixed price · £20k–£55k

2–4 weeks

Build and test one AI workflow in your own tenancy.

See scope, team and terms

Agentic Build Team

£70k–£85k / month

6–12 months

Build enterprise AI with an embedded team your people learn from.

See scope, team and terms

Use a 30-minute call to decide which scope is a sensible starting point.

Talk it through
book a call

Talk through the work you want to change.

A 30-minute discovery call with James Rooney. Bring a workflow, product or team challenge and we will discuss a sensible first scope.

most start with a fixed-price AI Readiness Audit · £44,000 · 4 weeks · working prototypes

// pick a slot · cal.com/tenhaw/professional-servicesLIVE CALENDAR

No time that suits? Email hello@tenhaw.com. Calendar not loading? Open it on cal.com.

Frequently asked questions

Can a workflow agent reuse a decision our team has already approved?

Yes, within the scope and conditions attached to that approval. We define what the approval covers, when it expires and which changes require another review. The workflow keeps the decision with the relevant case so later steps can check it.

How do reviewers pick up a case an agent has paused?

Through a defined review step containing the source material, the proposed action and the reason for the pause. Reviewers need enough context to decide, correct or return the case, with the result recorded before processing continues.

What should we bring when scoping an automation across two teams?

A few completed cases, the people responsible for each handoff and examples of where work gets stuck. Those inputs help establish the boundaries, identify decisions that need an owner and choose a first workflow both teams can test.