Build Your Own AI Agent

Stack-agnostic by design

We don't sell stacks. We ship agents that work. The stack is a means to an end — editorial discipline, safety rails, curatorial loops and accountable humans are what make an agent trustworthy. Whether you run on Microsoft 365 + Copilot Studio, on Azure AI Foundry, on AWS Bedrock, on Google Vertex AI or on a private open-source deployment, the method is the same.

Data Riders works where your data already lives, under your existing identity and governance perimeter, with your compliance officer in the loop.

Technology-agnostic AI agent architecture on multiple clouds

Stacks we ship on

Pick the stack that fits your organisation

A short, honest map of the four most common families we build on — and where each one shines.

Deep dive

Microsoft Copilot Studio + Azure AI Foundry: the M365-first path

If your company already lives in Microsoft 365, Teams, SharePoint and Entra ID, the shortest path to a production-ready agent is Microsoft Copilot Studio with Azure AI Foundry. Here's how Data Riders designs, ships and governs agents on this stack — in practice.

What is Copilot Studio?

Microsoft's low-code/pro-code platform to build enterprise agents that converse inside Microsoft 365 — in Teams, Outlook, SharePoint, Word or external sites. Native connectors to Microsoft Graph, Dataverse, Power Platform and models hosted in Azure OpenAI via Azure AI Foundry.

Instead of building a chatbot from scratch, you inherit: identity (Entra ID), permissions (SharePoint Sites.Selected), governance (Microsoft Purview), DLP (Data Loss Prevention) and audit (Microsoft 365 audit log) — everything your IT team already manages.

Why this matters for M365 teams

Time-to-production: from months to weeks — no rebuilding SSO, user profiles or permission rails.
Inherited governance: Purview policies, sensitivity labels and DLP apply to the agent automatically.
Frictionless adoption: the agent lives where users already are (Teams, Outlook, SharePoint) — no new tool, no new login.
Predictable cost: per-message licensing or consumption-based via Azure, integrated with your Enterprise Agreement.
Data sovereignty: processing inside the customer's Microsoft tenant — data does not leave the M365 perimeter.

Scenarios and use cases where Copilot Studio shines

Six real mining and governance scenarios we deliver on Microsoft Copilot Studio.

SharePoint Agent

Scenario: governance teams spend hours searching for policies, procedures and reports across hundreds of SharePoint libraries.

Solution: Copilot Studio agent grounded on SharePoint Sites.Selected, answering with direct citation to document, page and section. Permissions inherited — users only see what they could already see.

Copilot inside Teams

Scenario: dam engineers need to query GISTM, ANM 95 and internal protocols during meetings and inspections.

Solution: agent published as a Teams app, voice and text, integrated with calendar, OneDrive and channels. Mandatory citation on every technical answer.

Smart triage in Outlook

Scenario: compliance mailbox receives hundreds of evidence requests per week — risk of missing regulatory deadlines.

Solution: Copilot agent + Power Automate classifies, applies Purview sensitivity labels, drafts a response based on policy and escalates to a human on sensitive cases.

GISTM / TSM compliance

Scenario: GISTM and TSM audits require traceability and document curation — the evidence base lives in the customer's SharePoint.

Solution: Copilot Studio agent with RAG pipeline on curated evidence, integrated Power BI dashboards and automated report export to auditors.

Operational agent (Dataverse)

Scenario: operational data — work orders, inspections, water KPIs — lives in Dataverse and Power Apps.

Solution: Copilot agent reads and writes to Dataverse via native connector, triggers Power Automate flows and returns answers with inline Power BI charts.

Onboarding & Training

Scenario: new hires must learn internal policies, code of ethics, safety procedures — knowledge is scattered.

Solution: onboarding agent in Teams/Viva, with interactive quizzes, progress tracking and citation of official documents. Multilingual (PT/EN/ES).

Concrete benefits for M365 teams

What Data Riders delivers on the Microsoft stack

We don't sell licenses. We deliver the agent — shipped, governed, and adopted.

Editorial discovery

Voice, scope, refusal and ritual document — adapted to the customer's Purview policies and SharePoint taxonomy.

Tenant deployment

Copilot Studio agent published inside the customer's tenant, connected to SharePoint (Sites.Selected), Dataverse, Power Platform and Azure OpenAI.

Red-team & evals

Scenario evaluations in PT/EN, prompt-injection tests, regression at every knowledge-base update and a signed quality report.

Internal team enablement

Train the customer's M365 team to operate, curate and extend the agent — no long-term Data Riders dependency.

Ready for a Copilot Studio agent?

We bring the method. You bring your tenant, your data and your compliance team. In 4 to 8 weeks an agent lives in Teams, Outlook or SharePoint — governed, citation-first and audit-ready.

Dedicated Copilot Studio page Start a Microsoft project

The method

Six steps from idea to production

The same playbook we used to build GISTM.ai, TSM.ai, RIDE and Muiraquitãna — regardless of which cloud or model hosts the agent.

1. Editorial design

Voice document, scope, out-of-scope patterns, ritual and refusal rules. Written in plain language with the accountable human in the room — not an AI-generated prompt.

2. Knowledge curation

The knowledge base is curated, not scraped. Primary sources, versioning, provenance, and a curatorial inbox for updates. RAG over documents you actually trust.

3. Stack selection

We pick the stack after the editorial work, never before. The question is always: where does your data live, who owns identity, and what does your compliance team need to sign off?

4. Safety engineering

Refusal patterns for medical/legal/financial advice, PII handling, prompt-injection defences, grounded-only answers, human-in-the-loop for sensitive actions.

5. Red-team & evals

Scenario-based evaluations in the user's language, red-team prompts, regression tests at every knowledge-base update. No silent drift.

6. Operate & curate

Weekly curatorial cadence, privacy-preserving telemetry, named accountable owner inside your organisation. An agent is a living product, not a one-off project.

In action

Seven agents, seven contexts, one method

Live agents we operate today — each one co-designed with the end client or institutional partner.

GISTM.ai

Continuous compliance with the 77 GISTM requirements. RAG on auditor evidence, executive dashboard.

Run Learn more

TSM.ai

Readiness, gap analysis and action roadmap under the MAC TSM protocols, auditor-oriented.

Run Learn more

TCM AI Assessor

AI pre-audit for The Copper Mark certification. Evaluates the 33 RRA criteria with verdicts, evidence, gaps and recommendations. Independent, demo-mode, no login.

Run Learn more

RIDE Agent

Structured discovery interview producing an executive-grade Work Plan. Multilingual, no login.

Run Learn more

AquaTwin Agent

Mining water-balance digital twin: visual modeling, document intake, Kalman fusion and auditable Excel export.

Run Learn more

Muiraquitãna

Territorial AI with voice and visual modes, community-first. Built with MuCA, launched April 2026.

Run Learn more

Data Riders Agent

Bilingual conversational widget on every datariders.com.br page. Citation-first replies and lead capture.

Run Learn more

Stack-agnostic by design

Pick the stack that fits your organisation