Mike Biggerstaff

Problem

Growers juggle a separate app per hardware brand — sensors and controllers that were never built to talk to each other.

Approach

A hardware-agnostic AI command center: connect whatever sensors and controllers you already own, any brand, any mix, and GrowBridge reads the whole grow and drives it toward better yield, less waste, and more consistency — with the grower in control of every action.

How it works — you're the human in the loop

The AI proposes; you approve before anything touches your equipment. Illustrative — the real dashboard does this with live sensor data.

Capabilities

• One dashboard across the brands you already own — consumer smart-home and professional grow gear alike — built for home and small-facility growers, not just large commercial operations. Three are proven against real hardware today: PulseGrow, Bluelab Guardian and OpenSprinkler. Ten more have adapters written and credential-wired — Home Assistant, Tuya, Shelly, Samsung SmartThings, Philips Hue, Govee, Aranet, SensorPush, AROYA and a generic MQTT path for DIY sensors — with hardware verification underway.
• The AI proposes; you approve before anything touches your equipment — mandatory, by default. Most well-funded competitors in this category sell removing that approval step; GrowBridge deliberately keeps it.
• A real multi-agent system, not a chatbot wrapper — specialist agents with their own knowledge bases, built and retrieval-gate-passed. The first live agent runtime and full multi-agent orchestration are landing now.
• A self-healing hardware-integration layer — the foundation is shipped; full self-healing behavior is landing next. Not something cultivation competitors market at all today.
• "Ask Rance," a voice assistant for grow status, plus a Grow Journal with automatic daily rollups, plant tracking, and breeding tools.

Problem

Most scanners do one thing, and almost none of them cover the AI-security / agent-supply-chain attack surface a self-improving agent or an LLM-in-the-loop pipeline actually faces.

Approach

Fuses four engines — SAST, hardcoded-secrets detection, dependency/SCA, and an AI-security engine for prompt injection, invisible-Unicode smuggling, data exfiltration, and dangerous auto-run hooks — into one prioritized, deduplicated, false-positive-filtered report.

Capabilities

• Static only — reads files, never executes, imports, installs, or evaluates the code it scans.
• The `secrets` and `aisec` engines are pure standard-library Python: zero third-party dependencies, fully auditable, run anywhere.
• Detects OWASP Top 10 for LLM Applications patterns most classic scanners don't model: prompt injection, Unicode Tag / Trojan Source smuggling, exfiltration pipes, dangerous Claude Code / git / npm lifecycle hooks.
• Scans MCP server manifests — the agent supply chain almost nothing else looks at. An MCP server declares the tools an agent may call; a hostile or careless manifest is a direct path to the agent's capabilities, and classic scanners have no model of it.
• An interpretation layer, not just N tool outputs: findings that can never execute are suppressed by reachability and lexical context, so what's left is ranked and worth reading.
• Ships with an honest-limits doctrine: every clean result means nothing matched these rules, not that the code is safe.

Problem

Retirement housing at this scale is usually run on paper, phone calls and a listing page someone else controls — so the operator owns neither the first impression nor the pipeline.

Approach

Own the whole funnel: a fast, accessible marketing site with the tour and application paths built in, and resident operations handed to software that already does it well rather than rebuilt in-house.

Capabilities

• Private cabin homes for adults 50+, singles and couples, on Hwy HH near Mexico, Missouri — serving Audrain and Callaway counties and the Columbia area.
• Applications, rent and maintenance run on Innago rather than a bespoke resident portal — a deliberate build-vs-buy call: the operator's edge is the land and the community, not re-implementing property management.
• Built and shipped with the same discipline as the software work — accessibility preferences that persist, real photography over stock, and a deploy that gates on its own checks.