Live
Brand identity and Wix Studio site with Velo · UAE construction and MEP
- Branding
- Wix Studio
- Velo
Manufacturing and B2B · Knowledge and data
Shop-floor SOP and maintenance copilot
Give technicians cited answers from manuals and SOPs, hands-free voice Q&A on the floor and video review of procedures, with Claude and Gemini.
- ClaudeAnthropic
- GeminiGoogle
- Typical timeline: 4–8 weeks
The problem
Know-how lives in manuals, SOP binders and senior technicians' heads, and downtime stretches when the expert isn't on shift.
- Manuals are long and hard to search on the floor.
- SOPs drift out of date.
- New technicians take months to work independently.
How we solve it
A copilot that answers from your manuals with citations, helps engineers keep SOPs current, reviews short procedure videos and works hands-free by voice.
It plugs into CMMS / maintenance system, SharePoint or Google Drive and BigQuery or Postgres, so nothing you rely on today is replaced. The architecture below shows each step and which model does the work.
Architecture
From your stack, through the AI layer, to numbers you can track
Each step names the model or system doing the work. Writes to your systems wait for a person to approve them.
Your stack
- CMMS / maintenance system
- SharePoint or Google Drive
- BigQuery or Postgres
AI layer
Softpiper AI layer
- Claude
- Gemini
- Index the knowledge, using Drive / SharePoint
Manuals, SOPs and maintenance history are indexed from SharePoint or Drive.
- Cited answers, using Claude Sonnet · citations
Technicians ask questions and get answers with citations to the manual page.
- Voice on the floor, using Gemini Live API
Hands-free questions and answers by voice.
- Video review, using Gemini video understanding
Short procedure videos or machine clips are reviewed against the SOP.
- SOP revisions, using Claude Opus
Engineers receive drafted SOP revisions from incident notes to review.
- Maintenance context, using CMMS · BigQuery / Postgres
Answers can draw on work orders and sensor logs from your CMMS or data warehouse.
Outcomes you measure
- Mean time to repair (MTTR)
- First-time-fix rate
- SOP update cycle time
- Onboarding time for new technicians
Why this model
Claude and Gemini, each where it leads
We choose per task on capability, cost and where your data must stay. Final versions are picked at kickoff.
ClaudeAnthropic
Claude answers from manuals with citations to the exact page, and its most capable model drafts SOP revisions for engineering review.
GeminiGoogle
Gemini's agentic video understanding reviews short procedure or machine clips, and the Live API gives technicians hands-free voice Q&A.
Delivery
What you get, how long it takes, and how we keep it safe
Guardrails
- Safety-critical steps always defer to the official SOP.
- Lock-out/tag-out and safety warnings are quoted, never paraphrased away.
- An engineer approves SOP changes before publication.
- Answers without a source are marked as such.
Plus the guardrails on every build: facts from your systems, approvals for writes and money, a human one step away, audit logs and evals. See all
Deliverables
- Indexed manuals and SOP library
- Copilot with cited answers on web and mobile
- Voice mode
- Video review workflow
- SOP revision workflow
Typical timeline
- Knowledge base, copilot and voice4–8 weeks
A planning range for a first production release. We confirm scope, price and dates in a tailored proposal.
KPIs to track
- Mean time to repair (MTTR)
- First-time-fix rate
- SOP update cycle time
- Onboarding time for new technicians
Goals we agree with you and measure from a baseline. They are what we track, not results we promise.
Related services
The services behind this playbook
AI product engineering
From prototype to production: RAG, copilots, multimodal features and the evals that keep them honest.
View serviceAI agents
Agents that answer, act and hand off, on Claude and Gemini, inside the tools you already run.
View serviceData and automation
Turn scattered data and repetitive work into dashboards, pipelines and reviewed automations.
View service
Our work in this space
What we've built for manufacturing and B2B
Sites and products we've shipped for businesses in this sector. They show how we work; they are not deployments of this playbook.
Archived previewFire-safety company site on Wix · Same group as Greenberg Engineering
- Wix
- Fire safety
- Engineering
More playbooks
Related playbooks
Manufacturing and B2B
RFQ-to-quote and PO intake automation
RFQs and purchase orders arrive as emails, PDFs and spreadsheets, and re-keying them into the ERP slows quotes and introduces errors.
- Claude
- Typical timeline
- 6–10 weeks
- Plugs into
- SAP · TallyPrime · Zoho Books / Inventory +1 more
Education
AI tutor with text and voice
Learners need personalised, multilingual practice and feedback at scale, and teachers don't have the hours to give it.
- Claude
- Gemini
- Typical timeline
- 6–12 weeks
- Plugs into
- LMS (Moodle, Canvas) · Google Classroom · Supabase / Postgres +1 more
Any industry
“Talk to your data” analyst
Business users wait days for an analyst to pull simple numbers, and dashboards can't answer the follow-up question.
- Claude
- Gemini
- Typical timeline
- 3–6 weeks
- Plugs into
- Postgres / Supabase · BigQuery · Snowflake +1 more
Pip · Softpiper's AI
Ask Pip about this playbook
Ask Pip how this would work for you
Pip is Softpiper's AI. Tell it what you run today and it will walk through how this playbook fits, what we would build first and a tailored price range. Or book a call with the team.