Services for SaaS teams and software consultancies. Looking to automate a business workflow? ↗

Services / Engineering engagements

AI engineering services, from the first decision to production.

Five ways to work together, depending on your project’s stage and the support your team needs. We agree on the scope, deliverables and acceptance criteria.

01 / Typically 3 days

Technical diagnosis

AI Gap Analysis

A compact engagement for SaaS teams that do not know where to start or already tried something that did not land. One context meeting, a written report, and a second meeting to walk through it.

What’s included and who it’s for

Best for

SaaS teams with an AI feature on the roadmap or an earlier attempt they want to understand before investing more.

Context meeting on the target feature
Recommended technology choices
Data and datasets you will need
Predictable risks and how to avoid them
Step-by-step guide for the next steps

Case study: document classification, three approaches measured before deciding Talk about this engagement

02 / Typically 3 days

Architecture and project foundations

AI Project Foundations

For software consultancies that deliver custom projects. We leave a reusable technical base, planning guides, and delivery criteria for AI projects.

What’s included and who it’s for

Best for

Consultancies that want to raise the technical bar on AI work without relying on individual judgment call by call.

Standard technical base
AI project planning playbook
Technical criteria for pre-sales
Reusable templates and deliverables
Team onboarding

Talk about this engagement

03 / Typically 1 to 2 weeks

First working version

Agent MVP

For concrete projects where we get you started with the right foundations and your team takes it over the finish line. We set up the first agent version, quality checks, monitoring, and an explicit guide to what is left for production.

What’s included and who it’s for

Best for

Teams with a defined project that want to start well and own the last mile themselves.

Golden set and reference dataset
Evaluation and observability system
First version of the agent or system
Technical foundations for the project
Explicit guide on what is left for production

Case study: multi-agent system for expert legal reports Talk about this engagement

04 / Typically around 1 month

Production implementation

Production Delivery

Same as Agent MVP, taken to the finish line: system ready for production and integrated with your product, on the same evaluation, observability, and delivery foundations.

What’s included and who it’s for

Best for

Teams that want TenBeltz to own implementation, integration, and production delivery end to end.

Full system implementation
Integration with your existing product
Guardrails and operational controls
Production-ready delivery
Technical handover to the team

Case study: Qamarero voice agents running in production Talk about this engagement

05 / Programme and duration agreed with the team

Training for technical teams

Applied AI Training

Technical training built around your team’s level and working context. Local models, serving with vLLM, private architectures, RAG, agents and evaluation, with practical sessions. Experience includes 30 hours of local AI training delivered through Imagina to Opus Dei’s international technical team.

What’s included and who it’s for

Best for

Technical teams that need to understand, build or operate AI systems and apply that knowledge to their own projects.

Programme scoped to the team’s level and objectives
Local AI and model serving
RAG, agents and quality evaluation
Practical sessions on implementation and operation

Experience: 30 hours of technical training through Imagina Talk about this engagement

Where to start

Choose by the decision in front of you.

Each starting point opens a different engagement. We will confirm the fit with your product and team.

01We need to decide what to buildAI Gap Analysis 02We need a reusable foundation for client projectsAI Project Foundations 03The scope is clear; we need a working first versionAgent MVP 04The solution is defined; we need to take it to productionProduction Delivery

Next step

What does your team need to move forward with AI?

Tell us about your product, the AI system and its current stage. We will review the fit and outline a concrete next step with you.

hello@tenbeltz.com +34 640 520 819

Prefer a conversation?

Book a 15-minute phone call

We will discuss your goal, available tools and data, and whether we can help.

Want to assess your AI project first?

Technical AI diagnosis · 2 min

Assess evaluation, observability and control. Get your priorities in a downloadable report.