Skip to main content
Home, Bellec Services

Services

Five families of engagement, from diagnosis to production.

I design the architecture and I write the code. Both, not one or the other.

Software

Architecture and development

Structuring a system, from the frontend to the APIs: design systems, debt reduction and shipping the components that matter.

Cloud

AWS architecture and industrialisation

Infrastructure, deployment, security, observability and cost control.

AI

AI integration and agents

Connecting LLMs, RAG and agents to your applications and data, held to production standards.

Visibility

SEO and answer engines

Being found on Google, and understood by AI assistants: crawlability, indexing, structured data, entities and extractable content.

Advisory

Technical leadership

Making the calls, structuring the work and growing a team without hiring full-time straight away.

Focused engagements

Short formats, sold by the day, to settle a specific question without committing to a long engagement.

  • Architecture audit

    1 to 2 days

    A read of the architecture, technical debt, risks and performance pressure points, followed by a debrief with a prioritised action plan.

    Deliverable: System map, ranked risks and a sequenced action plan.

  • AWS and FinOps audit

    1 to 2 days

    A review of the cloud architecture, sizing, cost, security and observability, with the quick wins identified.

    Deliverable: Costed diagnosis and a list of quick wins by impact.

  • AI opportunity audit

    1 day

    An analysis of processes, systems and data to identify which AI use cases are genuinely worth pursuing, and whether they are feasible.

    Deliverable: Prioritised use cases, feasibility and technical prerequisites.

  • AI architecture review

    1 to 2 days

    An audit of an existing LLM, RAG or agent architecture: answer quality, security, cost, observability and readiness for production.

    Deliverable: Breaking points identified and a route to production.

  • AI integration POC

    3 to 5 days

    A working prototype connected to a real application, documents, APIs or business tools, so you can decide on evidence.

    Deliverable: A runnable prototype and a target architecture note.

  • AI visibility audit (GEO)

    1 to 2 days

    What AI assistants can actually extract from your site: content present in the initial HTML, an identifiable entity, statements they can reuse as-is, consistency with your public traces.

    Deliverable: Extractability diagnosis and entity architecture.

  • Technical SEO audit

    1 to 2 days

    A survey of what a search engine really reaches and indexes: robots.txt, rendering, canonical, hreflang, sitemap, internal linking, response times, pages competing with each other.

    Deliverable: Fixes prioritised by impact and cost.

  • Structured data and markup

    2 to 3 days

    Setting up a coherent JSON-LD graph: a single entity connected from page to page, covering pages, offers, articles and breadcrumbs, aligned with what each page actually shows.

    Deliverable: Markup deployed, validated and documented.

  • MCP connector or agent tooling

    2 to 5 days

    Exposing your APIs and business services to an assistant or an agent, safely, with the permissions and limits that go with it.

    Deliverable: A working connector, documented and tested.

  • Technical scoping

    2 to 5 days

    Target architecture, technical choices argued in writing, risks and a roadmap before development starts.

    Deliverable: Target architecture, ADRs and a costed roadmap.

These formats do not replace longer engagements: they are often the way in. One can continue into development, architecture or technical leadership.

Something specific in mind?

Thirty minutes is usually enough to tell whether I am the right person for it.

Let’s talk about your project