About
Over 20 years inside supply chain, analytics and SAP at billion-dollar companies in Brazil, Canada and the USA. Today I lead Analytics & Market Intelligence for the Supply Chain of a leading North American energy infrastructure company, and in just over a year I have architected and built 20+ AI solutions. I bring the business process, the enterprise data and the AI to the same table.
I started in 2002 at Gerdau in Rio de Janeiro, as a purchase analyst and SAP MM key user. Then came AmBev, Vale (as a consultant) and ThyssenKrupp CSA, where I moved from buying into the systems and data behind buying and earned my SAP MM certification (2011). In 2016 I moved to Calgary and joined TC Energy, moving from Senior Buyer to Procure-to-Pay analyst to Lead Supply Chain Business Analyst. Along the way I was pulled into a divestiture, a corporate spin-off and enterprise transformation programs, because I knew where the data came from and what it really meant; one colleague called me “a true SAP guru.” In October 2025 I was selected through a competitive internal process to lead TC Energy's Analytics & Market Intelligence team of business analysts in Houston.
In parallel, I architected and built B1Brain: 20+ AI solutions in just over a year, running on a private six-machine AI lab I built myself. Its one rule: if a claim is not backed by evidence, it does not ship. It is the kind of platform I would design for your organization, and I have already built it.
What I bring
Most AI projects fail in the gap between the model and the business process. I have spent two decades on the business side of that gap and the last year building the AI side, which is exactly the seat an AI Solution Architect has to sit in.
The process
Sourcing, contracts, procure-to-pay, inventory and logistics, from the buyer's desk to leading the analytics function at a leading North American energy infrastructure company. I know where the exceptions, workarounds and controls live, which is exactly where AI projects succeed or stall.
The systems & data
SAP MM certified (2011) and called “a true SAP guru” by colleagues. Master data, specs, mass changes in SAP ECC, including Canada's first mass purchase-order closure, and the reporting layer on top. AI is only as good as the ERP data underneath it.
The AI
Gateways, agent orchestration, memory, retrieval and optimization, designed to be governed, observable and honest about their limits, and running on a six-machine AI lab I built. Built and run, not drawn on slides.
How I work
I get up to speed fast on the context and the data's limitations, then deliver something leaders can act on, on time. That is how I delivered a first-ever enterprise spend view while half the team was out, and earned a Gold award for it.
I flag privacy, control and audit risks before they become problems, in dashboards and in AI systems alike; one colleague's verdict on such a flag: “great catch!” In B1Brain the same instinct means spend receipts on every model call and components that publish their own limits: the controls an enterprise needs before it can trust AI.
I coach my team on technical and leadership skills, mentored junior staff as a lead analyst, and treat change management (communication, training, user engagement) as part of the delivery, not an afterthought. Adoption is where AI value is won or lost.
In colleagues' words
“He quickly got up to speed on the context and data limitations and developed a new view that had never previously been reported by Supply Chain… Bernardo re-prioritized, put in the hours, and delivered.”
Ownership
“You demonstrated true leadership and took accountability to deliver critical visibility for leaders across all BUs; including rearranging vacation time to make sure this task was completed.”
BI & analytics
“Bernardo was optimistic and resolute to resolve the problem, and we could not have done it without him!”
SAP & data
“Greatly appreciate you taking the time troubleshoot the data mining within SAP and teaching me afterwards! You're a true SAP guru.”
Enterprise programs
“Your great work, flexibility, and responsiveness ensured that Supply Chain deliverables remained off the critical path to close.”
Enterprise programs
“Your deep understanding of our systems, willingness to collaborate and jump to action were key in supporting multiple workstreams…”
Enterprise programs
“I know your knowledge is valuable in the company and you are spread thin, but you are always there to help when needed.”
Analytics
“Your guidance and advice with our reports and data has been invaluable… Your skill and work sense has certainly made our work life better!!”
Governance
“Thank you for bringing the dashboard and your privacy concerns to our attention, great catch!”
Assurance
“Bernardo – you are a wizard. Thank you so much for this, this report will be extremely helpful in our assurance activities.”
Analytics
“Bernardo's analytical skills and Supply Chain knowledge greatly increased the quality of the outputs from the working group.”
Ownership
“You handled everything calmly and professionally and delivered a final product that met all of the defined attributes.”
SAP & data
“Your SAP system knowledge and willingness to share ideas has also created efficiencies related to system reporting and order tracking.”
SAP & data
“You are always very helpful, a great team player and provide input and suggestions based on your knowledge in SC and of the data.”
BI & analytics
“Your responsiveness and commitment ensured we had the insights we needed.”
Leadership
“Amazing! Thanks for your continued leadership Bernardo!”
Leadership
“We value your partnership and One Team approach!”
Leadership
“Let's go!!!!! Appreciate the one team approach and all the effort”
Ownership
“You are always very responsive and it does not go unnoticed. You are also very detail oriented and your work is done perfectly every time.”
Procure-to-pay
“Thank you for all your efforts in reducing our invoice exceptions by over 200.”
SAP & data
“Being a consistent sounding board and technical expert for eCommerce transactions.”
Procure-to-pay
“Going above and beyond to assist with eCommerce PO Cutover”
Procure-to-pay
“I really appreciate your attention to detail, communications on PO status and willingness to pull reports together – often at short notice…!”
Ownership
“Thank you for your sense of urgency, your attention to detail and your collaboration… Love having you in the supply chain family and your contribution is noticed!”
SAP & data
“The information you have provided us with has been extremely helpful and will allow for us to get one step closer to a solution”
Procure-to-pay
“Bernardo's timely issuance of POs makes my job as electric unit fleet manager much more efficient.”
Enterprise programs
“Thank you for your contributions in making the Sales and Use Tax Project successful!”
Ownership
“I know it was a lot of work and a tight timeline. Thanks!”
Colleagues
“you are one of the smartest at TC”
Excerpts are verbatim from peer recognitions and messages; names withheld.
What I'm looking for
I am most valuable where an AI program has to work inside real operations: supply chain, procurement, finance-adjacent processes and ERP data. I sit with operators to understand the process, with data owners to fix the foundations, and with engineers to design and build the system. One architect who closes the gap most AI programs fall into.
SAP Certified Application Associate, Procurement (2011) · Business Intelligence, PUC-Rio · Bachelor in Business Administration, Universidade Federal Rural do Rio de Janeiro. Education details
Proof, not a promise
Designed and directed by me, built with AI coding agents under my direction. Every decision below is one an enterprise AI program faces, and you can test each one yourself.
Governance & safety
Three gates: non-role text is refused before any model call; the model must attest the input is a role; and no model-written prose reaches the screen. Free text is kept only if it is grounded in the pasted description.
Grounding & honesty
Answers cite ids from my evidence file, unknown ids are dropped, scores are calibrated in code (never 100, gaps lower the ceiling) and "not a fit" is an allowed, expected answer.
Resilience
If on-device AI isn't installed, it uses the cloud model; if that is down or over quota, a deterministic fallback still answers, and every result says which layer produced it.
Model & vendor independence
An OpenAI-compatible gateway pattern: provider, model and limits are configuration. Today it runs an open-weight model on a free tier; tomorrow it can run anything.
Interoperability
The fit tool is exposed over MCP (current stateless revision and the legacy handshake, so old and new clients work) and as an A2A agent, with discovery cards and an OpenAPI description.
Security & operations
The key lives only on the server, inputs are capped and rate-limited, origins can be restricted, nothing is stored, and logs record status and timing, never the text you paste.
Try it
/api/mcp.Paste the role description and get an honest read on whether I fit: evidence, gaps and a recommendation. That includes "not a fit" when it's true.
Contact
I'm open to AI Solution Architect roles where business process, enterprise data and AI meet.