Multi-agent orchestration, multi-model routing, vision pipelines, closed-loop learning, all built on a shared knowledge base the agents and the team both read from. Residential general contractors in production. Not a demo. Not a prototype.
A multi-tenant SaaS covering the full residential GC lifecycle: CRM, estimating, proposals, budgeting, scheduling, field logs, change orders, closeout. Built for California GCs at $2M to $20M who escaped spreadsheets or bounced off Procore and Buildertrend. The deeper bet: execution data becomes intelligence. Estimates get more accurate, schedules learn from actuals, the bill of materials drives downstream decisions. The margin you priced is the margin you keep.
Public surface at baxiehq.com. App at app.baxiehq.com. Paid beta.
Baxie is the reference implementation. Below are the patterns scoped builds, fractional retainers, and AI-Native Org Audits actually deploy.
A coordinator agent decomposes a GC's request, routes sub-tasks to specialist agents, reconciles outputs against a typed schema. PDF takeoff, estimate generation, schedule synthesis, scope packaging each have their own agent with their own evals. Failure in one doesn't poison the others.
In consulting: the spine of every multi-agent scoped build.
Opus for hard reasoning. Sonnet for default. Haiku for routine high-frequency calls where latency and cost beat ceiling. Routing is a config layer, so workflows swap models when economics shift.
In consulting: the cost-control argument the CFO signs off on.
Architect plans arrive as PDFs. Baxie extracts dimensions, room labels, assemblies, feeds them to the estimating agent as structured data. Not OCR on a flat image. Multi-stage vision plus typed extraction plus validation.
In consulting: the pattern for any document-heavy intake, legal redlines, claims processing, lease ingestion.
Field actuals flow back into the next estimate. Schedule slippage calibrates the next schedule. Change orders feed the assembly cost library. The system sharpens job by job because every job is a labeled example.
In consulting: the differentiator vs bolted-on AI. The loop is the moat.
Most AI fails in production because agents and teams don't share context. The shared knowledge base fixes it. Versioned. Searchable. Both your team and your AI read from it. Positioning in one file. ICP in one file. Voice rules in one file. Sprint state in one file. Team changes a decision, agents inherit it immediately. Agent generates a draft, it pulls the same canon the team writes against.
Positioning, ICP, voice, and design language are canonical across marketing site, app, and sales. Drift is a bug, not a steady state.
Sprint plans, north-star pillars, and persona rosters live where agents read before drafting anything.
Memory persists between sessions because it lives in markdown, not in a chat thread.
The same shared-knowledge-base pattern Edwin ships in Fractional and Scoped Build engagements.
Growth motion is the proof motion. Architecture posts, worktree screenshots, shipping receipts, and demo clips ship on LinkedIn on a fixed cadence. Receipts compound across three audiences at once: GCs who see the product is alive, operators who want the playbook, engineers who recognize the architecture.
Post about multi-agent orchestration, post the diff. Post about multi-model routing, post the cost graph. The work is the pitch.
Closed-loop systems with humans in them. Augmentation, not replacement. AI-native architecture, not bolted-on. The stakes frame the build. The build proves the stakes are real.
No toy demos. No prompt screenshots without context. Build-in-public stays constrained to what's running in app.baxiehq.com against real beta data. Credibility transfers because the patterns are the same ones consulting deploys.
Most AI consultants pitch frameworks. A subset ship demos. Almost none maintain a production multi-tenant SaaS that exercises the same patterns they sell. That gap is what Applied AI means: shipped in production, not theorized in a slide. The fractional retainer, scoped build, and AI-Native Org Audit are the patterns Baxie deploys, transposed onto your stack and team.
Multi-agent orchestration, multi-model routing, vision pipelines, closed-loop learning are code paths Edwin maintains in his own codebase. Transfer to a client engagement is mechanical, not aspirational.
Baxie exercises the org-design questions too: where the human stays in the loop, what absorbs into the agent, how evals and observability earn budget. The fractional retainer is the same conversation, scaled to your team.
If a pattern Edwin ships in Baxie doesn't work, the LinkedIn audience sees it that week. Pressure to ship reliable, evaluable, production AI is structural, not a sales-call promise.
baxiehq.com is the live product. The architecture and the receipts are public. If the patterns map to your stack, book a call.