Peregrine is the AI design assistant that understands what engineers are trying to build — in plain English — and recommends exactly the right components with plain English reasoning. Not spec search. Intent understanding.
You don't ask Jarvis for the schematics. You tell Jarvis what you're building — and Jarvis figures out the rest.— The Peregrine Vision
Every electronic product starts with a connector problem. An engineer knows exactly what the application needs. But translating that into a spec, filtering 847 results, reading datasheets, and waiting two days for a FAE reply — that costs hours per decision. Multiplied across every connector on every board, it costs programs weeks.
The tools haven't changed in twenty years. Distributor search is keyword search. Manufacturer catalogs are PDFs. Cross-reference tools are lookup tables. None of them understand what the engineer is actually trying to build.
Peregrine's core breakthrough is the Translation Layer — a proprietary engine that maps what an engineer is building directly to the connector specifications required, without the engineer needing to know what those specs are.
No dropdown menus. No datasheets until asked. The engineer described a problem — Peregrine turned it into specs, specs into parts, and parts into a recommendation with live data.
Natural language → right part, every time. Cross-manufacturer recommendations with plain English reasoning. Live availability and pricing from connected distributor APIs. No spec knowledge required.
AI engine for customer interactions. Intelligent cross-reference. Proactive alternatives when parts are allocated. Customer-facing chat powered by the distributor's own inventory and preferred stock.
AI layer on the OEM's own catalog. Application-driven search within their product line. Competitive positioning. Surfaces products customers didn't know existed — in the OEM's own portfolio.
The Winjit POC validated the core approach — RAG architecture, intent understanding, real-time distributor data. It works in the happy path. A full technical audit by MAAX (June 2026) confirmed the concept is sound and identified exactly what needs to change to go from proof-of-concept to production.
Replace raw SDK calls with a proper multi-agent state machine. Each agent has a specific job. Observable, debuggable, improvable independently.
Results stream progressively — no waiting. Feels fast even when processing is deep. Engineers see Peregrine thinking in real time.
DigiKey, Mouser, Arrow, customer ERP — each is a plugin. New data sources added without touching core infrastructure.
Azure Key Vault for all secrets. Entra ID for auth. Zero credentials in code. CORS locked down. Audit logging from day one.
Every major distributor will add an AI chatbot. The big OEMs are running LLM pilots. DigiKey has an AI team. None of them have built — and none of them can easily build — what Peregrine has.
We understand the application, not just the catalog. Nobody else has this Translation Layer.
We build and iterate faster than any traditional electronics company can move.
Real-time pricing, inventory, ERP data. Not a stale catalog that's wrong before it loads.
Every engagement trains the Translation Layer. The moat deepens with every customer interaction.
Consulting-led model. Profitable immediately. Every engagement funds the next capability.
Once integrated into a customer's ERP and workflows, the relationship deepens every day.
The connector market alone is $90B annually. The broader electronic components market is $500B+. Every company in this space — OEMs, distributors, engineering firms, procurement teams — has the same intent-to-spec problem. None have solved it. The window is open. And it won't stay open.
TE Connectivity, Amphenol, Molex, Hirose, JST. License Peregrine for their own catalog. Internal engineers use it; they offer it to customers as a value-added service.
DigiKey, Mouser, Arrow, Avnet, regional specialists. White-label Peregrine as their AI search and recommendation engine for customer-facing interactions.
Design assistant for engineering teams. Cut component selection time from hours to minutes per decision. High-frequency usage drives high retention.
Validate specs, find alternates, cut sourcing time. Connect directly to their ERP, approved vendor lists, and contracted pricing — live, not static.
The window is open — but it won't stay open. The distributors know this. DigiKey has an AI team. Mouser is experimenting. The big OEMs are running LLM pilots. None have cracked the core problem — they're all building better keyword search wrapped in a chat interface. We have the domain knowledge, the AI capability, and the speed advantage to get there first. That window closes in 18–24 months.
We start narrow and go deep. The End User Design Assistant for connectors is the beachhead — highest pain, clearest value, hardest to replicate. Once the Translation Layer is proven, every other category and persona is an expansion, not a rebuild.
Build the core product. End User persona. Connectors only. Intent Agent + Translation Layer + Retrieval + DigiKey integration + streaming UI. Validate with 2–3 paying customers. Learn what the Translation Layer is missing — and fix it.
✓ Gate: 80%+ recommendation accuracy on validated test scenariosAdd Distributor and OEM personas. Expand data integrations (Mouser, Arrow). Customer ERP connector. Customer admin console. Translation Layer refined to 500+ application patterns.
✓ Gate: A distributor deploys Peregrine for their customersExtend Translation Layer to resistors, capacitors, inductors, discrete semiconductors. New manufacturer API integrations. Peregrine handles BOM-level design assistance across a full bill of materials.
✓ Gate: Peregrine handles 80% of component selection across a full BOMTrue multi-tenant SaaS. Self-serve onboarding. Marketplace of pre-built data connectors. Partner API for distributors and OEMs to embed Peregrine in their own products and websites.
✓ Gate: ARR, net revenue retention >100%, customer countPeregrine enters the market through paid consulting engagements — profitable from day one, building the customer relationships and data integrations that become the SaaS foundation. Every engagement funds the next capability. Every integration raises the switching cost.
The POC is built and validated. The architecture is designed. The domain knowledge is in the room. The audit is complete. The next step is a straightforward set of actions that move Peregrine from plan to Phase 1 build.
Mark Beatty (15yr TE), Bob Mulfinger (TE career / sales), Joe Olson (TE engineer) + Kano. This is the session that seeds the Translation Layer with real connector engineering expertise that no competitor can replicate. Everything starts here.
One OEM or distributor willing to deploy Peregrine and provide real-world feedback. Paid engagement. The goal is not perfection — it's validation and learning. Everything after that is refinement.
Two-week sprint: Azure infrastructure, Key Vault, Entra ID auth, LangGraph scaffold, streaming API skeleton. All security issues from the audit resolved before a single line of product code is written.
The distributors and OEMs are moving. DigiKey has an AI team. If we move now, we build the Translation Layer moat before anyone else gets close. That window closes. We move first.