From tender to client report — working AI deployed in 4–6 weeks, on the platforms you already use.
Construction projects lose margin to administration, not to complexity. Estimators spend days reading RFPs. Project managers write reports instead of managing projects. Liorant builds and manages AI systems that remove this administrative load.
No open-ended consulting. No transformation programme that ends with a slide deck. Three structured phases — each producing a concrete deliverable.
Free, 30–60 minutes. We map your workflows, confirm which platforms you already licence, and identify the highest-value place to begin. No presentation, no pitch.
4–6 weeks, fixed scope and price. We build the AI system on your platform, test it against real project data, and hand it over with documentation and governance guardrails. A working system — not a prototype.
Monthly, optional. We monitor, optimise, and expand your AI portfolio — and each month you receive a business outcome report written as a leadership narrative, not a technical dashboard.
The administrative load is structural. It runs in parallel to every project, consumes your most experienced people, and scales with complexity — the more demanding the project, the heavier the cost.
Estimators read entire RFP packages manually to extract scope, conditions, and pricing signals — several days per large tender.
Project managers maintain daily reports, RFI logs, safety records, and client narratives at once — each from a different source, each compiled by hand.
Engineers draft RFIs and change orders from field notes, searching specifications and prior correspondence before each formal submission.
Safety officers complete incident checklists and compliance reports by hand — and incomplete forms create regulatory exposure.
Procurement coordinators track dozens of supplier quotes, delivery confirmations, and price changes across fragmented email threads — with no automated alert when something slips.
None of this work requires human judgment. All of it consumes time your teams could spend executing the project. Liorant builds the AI systems that handle it — structured, auditable, and governed to your company standards.
Each starts as a single, scoped deployment with a defined deliverable. All connect into coordinated systems as the portfolio grows.
Reads RFPs and BOQs in minutes, not days.
Surfaces risk clauses before mobilisation.
Supervisor speaks — the system writes the report.
Generates formal RFIs from field notes.
Photo to structured inspection report.
Complete safety reports with regulatory references.
Daily digest of delays, price changes, and actions.
Who is behind schedule — surfaced automatically.
Flags deviations before they hit the margin.
Generated from data already in the system.
Estimators spend days reading RFPs, BOQs, and specifications to extract scope, exclusions, and pricing conditions. An AI reading assistant, built on your platform, reads these documents and answers questions in natural language — in minutes. Scale adds BOQ generation and integration with your estimating software.
A contract review copilot processes contracts and specifications and surfaces the clauses that require attention — categorised by risk type — in under an hour. Scale adds an active contract register, version tracking, and independent review flagging.
A voice-based report assistant lets the supervisor describe the day in two minutes — the system generates a complete, structured report. Scale adds a centralised progress tracker and a PM dashboard updated in real time.
An RFI drafting assistant generates the formal request from field notes in seconds, with specification references pulled in. Scale adds an open RFI register, follow-up alerts, and critical-path impact flagging.
A photo-to-report workflow accepts photo uploads from site and generates a structured inspection report, marking items that require priority attention. Scale adds a defect database by subcontractor, quality trend tracking, and warranty documentation.
A safety report assistant takes a verbal or written description of what occurred and generates a complete report with applicable regulatory references included. Scale adds a compliance dashboard, unresolved-observation alerts, and audit summaries.
A supplier communications monitor produces a daily digest showing what is delayed, what has changed in price, and what requires action today — without reviewing every thread by hand. Scale adds supplier performance scoring and automated reorder alerts.
A coordination assistant consolidates status across all active subcontractors and delivers a daily summary: who is behind schedule, what communications are pending, and what requires escalation today.
A budget deviation monitor flags cost variances as they emerge, explains why — comparing committed costs, actuals, and forecasts — and delivers this weekly without the controller building the report from scratch.
A progress report generator builds the client report directly from data already recorded — daily logs, procurement updates, budget snapshots. Project managers review and send, rather than write.
Most institutional knowledge sits in file servers, email archives, and individual hard drives — inaccessible when teams need it most. Liorant makes it retrievable in plain language, answered from your own files. Not from the internet, not from a generic base.
Protocols, templates, and quality standards answered in plain language — sourced directly from your internal documentation.
RFI precedents, change-order history, and lessons learned — retrievable by project type, location, or specification section.
Specs, material standards, and compliance clauses retrieved by natural-language query, cross-referenced to applicable standards.
New team members query your real procedures from day one — no senior engineer required — and the system flags where human judgement is needed.
The knowledge system builds on the same platforms as your operational AI — SharePoint and Copilot Studio, Google Drive and Gemini, or Claude with your document library — and connects to systems already deployed: inspection reports feed the quality base, RFI resolutions feed the precedent library, contract clauses feed the standards assistant.
See how Liorant builds knowledge systemsThe first deployment handles one bottleneck. The managed model builds from there — one use case per month — until AI covers the full project administration lifecycle. Not a collection of tools; a coordinated operating layer.
No new software subscriptions unless your current platforms genuinely do not support the use case.
Copilot Studio enables agent-building and workflow automation inside your existing environment. Microsoft 365 Copilot licences typically include the infrastructure for internal-facing agents at no extra platform cost. SharePoint and Teams integrate natively.
Gemini Enterprise integrates AI into Docs, Sheets, Gmail, and Drive, with Gemini Studio for custom agent development. Site-report templates, procurement tracking in Sheets, and document management in Drive connect directly.
For use cases requiring precise document processing at scale — large RFPs, technical specifications, contract libraries — we build on Claude. Particularly effective for tender reading, contract analysis, and structured report generation from unstructured field input.
For routing between systems, triggering approvals, and connecting field data to project management, we use Power Automate, LangChain and LangGraph for multi-step agent orchestration, and native platform connectors — sized to your existing stack.
Every system is scoped from the start to comply with the AI regulations of your operating geography. Not a separate workstream, not a post-deployment audit — part of the build.
We map every deployment to its risk classification, document intended use and governance controls, and maintain the records required as obligations phase in through 2026–2027. Safety- and quality-critical systems get high-risk controls from design.
Enacted March 2025 under the National AI Agency (ANIA). Our deployments align to its requirements — documented purpose and scope, transparency with end users about AI-assisted outputs, and data handling consistent with national standards.
We align implementations to the NIST AI Risk Management Framework — mapping systems against the four core functions, implementing transparency and accountability controls, and documenting risk decisions for contract and compliance review.
We do not hand over a system and a hope. We hand over a system and its governance documentation.
The build-vs-hire decision: hiring an internal AI capability takes months and carries the full cost of employment, management, and onboarding. Retaining Liorant delivers a working system in weeks at a fraction of the annual cost — with the flexibility to scale scope as project priorities change.
The activation project delivers a working AI system in 4–6 weeks from signature. Most clients have their first workflow running before the end of week four.
In most cases, no. We build on Microsoft 365, Google Workspace, or Claude — whichever you already licence — and run a platform qualification check before scoping. If a licence change is needed, we tell you at the start so you can decide.
Informal use rarely produces consistent, auditable outputs. The difference is implementation: a governed workflow, tested prompts aligned to your document formats, and a system that produces the same quality regardless of who runs it. We do not give you a tool — we give you a process.
With a managed retainer we add one new use case per month, building toward full lifecycle coverage. Each deployment connects to those already live. You also receive a monthly business outcome report and a 90-day opportunity backlog reviewed at each quarterly review.
All implementations use your organisation's existing security perimeter — Microsoft or Google data governance, access controls, and retention policies apply — and we do not move client data outside your environment. Deployments are scoped to GDPR and the EU AI Act, the AI Promotion Law (Decreto 234) and ANIA, or the NIST AI RMF as applicable, with compliance documentation delivered as part of every engagement.
The activation project is a fixed-price engagement with no ongoing obligation. If you continue with a managed retainer, the initial term is three months — after which you can cancel with 30 days' notice.
Yes. Liorant has a presence in Barcelona, Medellín, and San Salvador, with native bilingual delivery in Spanish and English, adapted to each market — including EU AI Act requirements for European clients and market-specific platform availability for Latin American clients.
Your estimators, project managers, and site supervisors are doing work AI can handle. Liorant builds and runs the systems that give that time back — starting with the bottleneck that costs you the most. A free 30-minute discovery session, no slides, no pitch.