Thirteen AI agents, each with a defined role, a name, and a private memory that improves over time. They work in Slack — message any of them directly, or they'll come to you when something needs your attention.

Every agent has its own Slack channel. You talk to them like you'd message a colleague — they respond, take action, and follow up. Agents can also message each other internally when a task needs a different specialist. Ahsoka (performance coach) runs weekly check-ins with every agent via internal messaging — you don't see the chatter, just the outcomes.

50 skills agents can deploy on demand, plus 12 backend services powering the whole operation. Skills are like specialist tools — agents load the right one for the job, use it, and put it back.

These aren't just features — they're complete workflows. Each skill contains a full set of instructions, decision rules, and output formats. When an agent runs /brand, it doesn't just read brand colours — it gets the complete brand voice, all naming rules, every do/don't, and full visual identity reference.

These are the 12 Node.js services running on the server. They're the engine room — agents talk to them via API to get data and take action. Each has its own database, its own secrets, and is managed by PM2 (the process manager that keeps them alive).

The plain-English version of what's happening under the hood — for Drew, mostly. Sean already knows this bit.

Agents don't have unlimited memory — each session starts fresh. But they're designed around a 5-tier system that means they always have the right context for the job.

This is the most important thing to understand about the system. Every correction you give is permanent. If you tell Elara that she approved copy that sounded too corporate, that rule goes into her memory file and applies to every review she does from that moment on — forever, unless you change it. The more feedback you give, the better the team gets. It compounds.

The complete visual and verbal identity for Increase Construction. This is the source of truth Mando uses for all content. Reviewed by Elara.

The wordmark is the logo — there is no separate icon. The "IC" monogram is for favicon/app-icon contexts only where the wordmark won't fit.

• White version on dark/navy backgrounds. Colour version on light backgrounds.
• Minimum digital size: 120px wide. Clear space equal to the cap height of "I" on all sides.
• Never stretch, recolour, rotate, add effects, or place on busy photographic backgrounds.
• Never use the IC monogram as a standalone logo on documents or marketing materials.

Poppins for all headings (600–700 weight). Open Sans for all body copy (400–600 weight). Minimum 16px body size. No exceptions.

Direct, no-nonsense Australian trades talk. Conversational but authoritative. No corporate jargon, no passive voice, no fabricated stats. Em dashes are banned — they're the #1 AI writing tell.

AI-powered auto-responders for the ECTC, Increase Construction, and Australis Roofing Facebook Pages. Trained on 3,800+ real conversations. Responds in seconds, routes to forms, qualifies candidates, and escalates to humans when needed.

Live counts as of 12 Jun 2026 — ECTC 1,621 · IC 1,830 · Australis Roofing 436 conversations.

The system lives inside social-ads-platform (port 3003). A single webhook endpoint receives events from all subscribed Facebook Pages. The handler identifies which page/channel the message belongs to, loads the correct system prompt, and processes it through a 15-step pipeline.

ECTC, IC, and Australis Roofing are completely independent. Different prompts, different decision logic, different kill switches, different ad funnels. They share the same handler infrastructure but never cross-contaminate.

When someone messages from a Facebook ad, Meta sends an ad_id. The handler resolves this to the adset name via the Graph API (cached). The adset name drives the entire response strategy. New adsets are handled automatically at runtime.

Lead router integration (ECTC only): When an applicant fills out the employment form, the lead router processes it and calls back to the Messenger system. If the applicant has an open conversation, the bot sends "thanks [name], I'll get your info over to the local area manager" and marks it completed.

Every inbound message passes through this pipeline sequentially. Early exits at each checkpoint prevent unnecessary processing.

~$5-15/month per channel via OpenRouter (Sonnet 4.6). Each message ~$0.002-0.005 in tokens. Infrastructure: $0 (existing VPS).

Live dashboard in the ECTC Leads → Messenger tab. Stats, searchable conversation table, chat-bubble viewer, escalate/reset actions. Proxied via /api/proxy/messenger/*.

A commercial multi-client SaaS that lets builders survey their customers at every stage of a build. Satisfaction is tracked as a trend, not one end score. Detractors trigger a same-day recovery call; promoters get asked for a Google review. Sold at $2,000 per build + GST (competitors charge $5,000-6,000). Standalone service, proxied at mc.increaseconstruction.com.au/pulse.

Brand: teal #107b8c, sage #7d8d74, cream #faf7f3, Poppins. First prospect: Renovair. Ships disabled until a pilot builder onboards.

A single end-of-build satisfaction score tells a builder nothing they can act on. The Pulse asks a short question at each stage of the build, so a dip shows up while the job is still live and can be recovered. It turns customer experience into a running trend line with named-staff accountability, automatic detractor recovery, and a promoter-to-Google-review funnel — the loop most builders never close.

A single Express service (port 3013, ESM, better-sqlite3 WAL) that does four things: serves the admin dashboard SPA (public/index.html); serves a public, HMAC-token-guarded mobile survey page (/survey); captures responses two ways (inbound JustCall SMS webhook + web deep-dive form); and runs three background pollers — survey sender (60s), recovery-case reminders (hourly), non-responder handoff sweep (daily). Its own database file (data/pulse.db) means no shared-file contention with Mission Control. Caddy proxies /pulse* to it; the app is path-prefix aware via PULSE_BASE_PATH.

prelim Design & Proposal → deposit Contract → slab Build Start → completion Practical Completion / Handover (NPS asked here) → maintenance Warranty. A commercial journey is a second configurable template. Every stage label is per-builder configurable.

Each stage measures named staff in generic roles (Sales Consultant, Customer Liaison, Selections, Site Supervisor, Maintenance Coordinator, Office — labels per-builder configurable). Each role is rated on four dimensions: Communication, Responsiveness, Clarity, Care. Scores normalise into csat_survey_roles so results aggregate by person, stage, and dimension — a builder can see which team member drives satisfaction and where it slips.

The benchmark endpoint returns a certification block whose eligibility counts distinct verified phone numbers, not raw responses, plus a duplicate-number guard. A builder cannot inflate their score by surveying the same happy customer repeatedly — the certification is only as strong as the number of real, distinct customers behind it.

• JustCall — outbound survey SMS, inbound 1-5 pulse webhook, and recovery-call recording download.
• Google Workspace SA (MANDO_WORKSPACE_SA_JSON) — email fallback + alert emails.
• AssemblyAI + OpenRouter — recovery-call transcription + AI tone/sentiment read.
• Pipedrive — CRM read (pull won/open deals to jobs) and write (push survey-result note back to the deal). Adding a CRM = adding one adapter in lib/crm-sync.js.
• Slack — ops alerts for detractors, overdue recovery, and handoffs.

Flat $2,000 per build + GST. GET /api/csat/plan?slug= returns the billable-build count and the revenue it represents (ex-GST, GST, inc-GST). Billing itself is out of scope — Pulse only surfaces the number that drives it. Non-responders are billable; billing counts every enrolled build.

PM2 pulse on 3013, wired into start-mando.sh with an env allowlist; Infisical holds the PULSE_* tokens. Live and proxied at mc.increaseconstruction.com.au/pulse; moves to the TGB-owned thepulse.thegoodbuilder.com.au once Aaron provides DNS. Survey SENDING ships disabled (CSAT_SURVEY_ENABLED off, CSAT_DRY_RUN on) until a pilot builder onboards — the dashboard and public survey still render for demos. Repo: increase-construction/good-builder-pulse.

For Sean. The complete infrastructure, auth, file paths, secrets, and operational runbooks.

Self-hosted at 127.0.0.1:8443. 80 secrets across 13 scoped folders. Machine identity mando-bootstrap (Universal Auth) authenticates start-mando.sh at boot. Infisical is the sole secrets store — SOPS was decommissioned 2026-04-08; there is no SOPS/Age fallback. If Infisical auth fails or returns fewer than 70 keys, start-mando.sh aborts the boot (fail-closed).

# Fix single file
sudo chown ubuntu:ubuntu /home/node/.openclaw/openclaw.json && sudo chmod 660 /home/node/.openclaw/openclaw.json

# Fix everything after bulk changes
sudo chown -R ubuntu:ubuntu /home/node/.openclaw/

# Paste value at prompt — never inline in the command
infisical secrets set SECRET_NAME \
  --projectId 616a8bc2-e838-4d95-8ea8-a78ebeee889f \
  --env prod --path /services/mission-control

# Verify it exists (name only — never print the value)
infisical secrets get SECRET_NAME --projectId 616a8bc2... --env prod \
  | grep -c SECRET_NAME  # returns 1 if set