//  Put AI to work in your business

MCP & AI Tool Integration

Let your AI assistant work with the tools your business runs on.

Discuss what you want to improve and whether we can help. No technical brief needed.

//  The work

What this can change

Give an assistant useful actions in your systems.

Looking up an order, checking a record or preparing an update requires access to the system where that information lives. We build the connections that let compatible AI assistants use those functions.

Model Context Protocol, or MCP, provides a shared way to expose these tools. We define the actions, connect authentication and test their behaviour so the assistant has a clear interface to your business applications.

Less work on your shoulders. A process you can trust.

Some work needs reliable rules. Some needs judgement. We combine both around the task, with checks before important actions.

Give the goal. Keep control.

For research, investigating requests and work across several tools.

When the path varies, an agent can choose its next step, use approved tools and check what happened. You set its permissions and limits.

SOHOB Workflows

Illustrative example

Agents + tools + approvals

A request, carried through to a result

100%
Revise with feedbackLimit reached → teamUse tools / return resultsApproved
Select a step to exploreScroll sideways to follow the workflow

Work towards the goal

The agent chooses the next useful action using the context, instructions and tools it has been given.

Illustrative workflows · research behind the approach

The canvas uses connected nodes and branches inspired by OpenAI’s Agent Builder. Original SOHOB illustrations of published patterns, rather than a client system. See Anthropic’s Building effective agents for workflows, tool use and feedback loops, and When AI builds itself for iterative AI-assisted development. Checking and revising work does not mean retraining the underlying model.

Useful AI. Sensible running costs.

The right model for the job.

Use lighter models for routine tasks and more capable ones where the work needs them. Test prompts against real examples before scaling up.

Less wasted AI spend.

Trim unnecessary context, reuse repeated inputs where supported and batch work that can wait. Measure token costs alongside quality and speed.

Infrastructure that fits.

Run applications and agents in containers, with Kubernetes where it fits. Choose managed hosting or your infrastructure, connected to model APIs or suitable self-hosted models.

Clear limits. Visible results.

Set tool permissions, spending limits and approval points. Track failures and running costs so you can see what needs improving.

Model and prompt choices are evaluated against the work they need to do. Related reading: OpenAI’s guide to optimising agents for cost and quality.

Your agents, hosted and looked after.

Like managed hosting for a website, with ongoing care for the agents doing your work. We run the infrastructure, monitor jobs and maintain the tools and integrations they depend on.

Explore managed agents & hosting

Infrastructure without the daily upkeep

Hosting for websites, apps and agents, with containers and Kubernetes where the workload calls for it. We manage deployment, capacity and the underlying environment.

Someone watching the work

Monitoring for failed runs, service issues and unexpected usage. Support hours, response targets and escalation routes are agreed with you.

Maintenance as things change

Security updates, dependency upgrades, integration fixes and tested releases. Model or prompt changes are checked against your tasks before rollout.

//  Inside the service

What we deliver

Connect your business applications

Build MCP servers and tools for systems such as Odoo, Payload, Notion and internal APIs, according to the access each supports.

Make each tool’s job explicit

Define inputs, outputs and allowed changes. Keep functions focused, such as finding a customer or preparing an order update.

Apply the right permissions

Keep credentials separate from prompts and enforce the agreed user or service permissions when a tool reads or changes information.

Make actions reviewable

Record tool calls and results, add approval points for selected actions, and check behaviour with the AI clients your team intends to use.

What would you like to improve?

Tell us what is getting in your way, what you use today and what you want to change.