Colibri

Sovereign AI for your data

Colibri transforms your internal data into instant, source-backed answers with sovereign AI.

Contact salesTry the free version
Colibri Logo

Colibri

Verified with sources

What was the daily rate negotiated in the 2025 framework agreement with the Walloon Region?

+Source
Colibri LogoColibri

The negotiated daily rate was €685 excl. VAT, capped at €720 for urgent interventions, with annual indexation limited to 2.5%. 12

1Source
2025 framework agreement, financial appendix, art. 4.2: base daily rate €685 excl. VAT; urgent intervention cap €720; max indexation 2.5%.

Compared to standard AI?

Knowledge

Answers based on your internal data.

  • ChatGPT doesn't know them.
  • No inventions or hallucinations.
  • Handles unlimited amounts of data.

Reliability

Answers sourced from your internal data.

  • Every answer is verifiable in one click by your team.
  • Prevents errors.

Security

No data leaves your company.

  • Runs in your closed environment.
  • No external API calls.
  • Your GPUs, your CPUs.
Q

New tender: office HVAC renovation, 800m², Brussels. What relevant past projects do we have?

87%

HVAC Renovation — Avenue Louise, Brussels (2022)

Technical report · 3 sections matched · p. 14, 28, 41

74%

Office Energy Audit — Ghent (2023)

Audit report · 2 sections matched · p. 7, 19

61%

Energy Performance Assessment — Liège (2021)

Specification document · 1 section matched · p. 33

Illustrative example

Cross-referencing

Leverage every past project

When your team starts a new project, bid, or audit, Colibri doesn't just search for keywords. It identifies past projects with similar requirements, surfaces reusable content from previous deliverables, and flags relevant precedents across your entire document base.

A new tender comes in. Colibri finds three past projects with comparable specifications, pulls the relevant sections from their technical reports, and highlights where the current requirements differ. Work that used to take a full day of manual searching happens in a single query.

Already in production

Deployed at Alteo Group across 12 companies.

Colibri indexes over 50,000 documents for the Alteo Group, a Belgian group active in building energy services. Field engineers and project managers use it daily to find technical specs, compliance requirements, and past project data.

Read the full case study→

Data sovereignty

On-premise or hosted in Europe. Your data stays with you.

Colibri can be delivered on-premise, directly on your company's own servers, or deployed on dedicated European infrastructure. Your documents are indexed and stored in your environment. Nothing is sent to non-European servers. GDPR-compliant by design, built for organizations where data sovereignty is a requirement.

Frequently Asked Questions about Colibri

How is data protection managed?

Data protection at BRAFT is absolute. The Colibri system operates entirely within your company's closed environment. It is hosted on your own servers, using your GPUs and CPUs, without making any external API calls. No data ever leaves your proprietary infrastructure, guaranteeing total compliance with GDPR standards and data sovereignty requirements.

How is your AI search solution different from traditional keyword search?

Unlike keyword search which is limited to textual matching, our solution uses multi-agent search algorithms. These intelligent agents communicate with each other to browse your database, understand the context and semantics of your documents, and synthesize precise answers based on your internal data. This allows you to find complex information without needing to know the exact terms used in the original documents.

What are the benefits of using Colibri?

Using Colibri delivers decisive advantages: - Total Isolation: A 100% closed environment, completely siloed within your company, ensuring no data leaks outside. - Internal Knowledge: Access to your internal data that general AI tools like ChatGPT do not possess, preventing potential hallucinations. - Unlimited Capacity: Unlimited data processing capabilities, unlike the limits imposed by public cloud models. - Traceability and Verification: Every answer is sourced. Users can check the origin of the information with a single click, preventing errors and fabrications.