Agent skill
engineering-chatbot-demo
GTM demo execution for engineering AI chatbot presentations — system prompt authoring, demo scripting, ROI capture
Install this agent skill to your Project
npx add-skill https://github.com/vamseeachanta/workspace-hub/tree/main/.claude/skills/business/client-demo/engineering-chatbot
SKILL.md
Engineering Chatbot Demo Skill
Full GTM workflow for presenting engineering AI chatbots to clients — covers system prompt design through ROI capture. Reusable template for any new engineering discipline.
System Prompt Template
Produce discipline-specific system prompts in this order:
- Role definition — "You are a senior [discipline] engineer with X years of [domain] experience"
- Core competencies — domain-specific bullet list (6–10 items)
- Primary codes & standards — with version years (e.g. API 2A-WSD 22nd Ed. 2014)
- Calculation capabilities — formula notation, accepted inputs/outputs
- Persona and Tone — precision · practicality · caution · transparency
- Known Limitations — hallucination risk, no proprietary data, no software execution
- Standard disclaimer — "Outputs are preliminary engineering estimates requiring QA review"
Demo Script Builder (15–20 min flow)
| Phase | Duration | Content |
|---|---|---|
| Hook | 2 min | Live lookup: "What does API 2A say about pile fatigue?" |
| Calculation | 5 min | Step-by-step calc: formula → substitution → result → acceptance check |
| Data processing | 4 min | Paste inspection data → AI generates corrosion rate summary table |
| Document gen | 4 min | AI drafts scope of work or memo from bullet points |
| Q&A | 5 min | Open questions; capture objections |
Calculation Template Format
### [Calc Name]
**Code ref:** API/DNV/ISO clause X.Y.Z
**Formula:** σ = F / A
**Inputs:** F = [value] kN, A = [value] m²
**Result:** σ = [value] MPa
**Acceptance:** σ ≤ F_y / 1.67 = [value] MPa → PASS/FAIL
Knowledge Base Structuring
Structure markdown KB files for reliable AI citation:
- Top-level
##headings per topic (AI retrieves by heading) - Tables for code values (yield strengths, load factors, limits)
- Numbered clauses matching source document numbering
> Note:callouts for exceptions or applicability limits
Pilot Feedback Capture
After each demo session record:
- Time savings estimate: "Task X took Y hours; AI did it in Z minutes"
- Q&A log: questions asked + AI answer quality (Good / Needs refinement / Wrong)
- Objections: capture verbatim; map to rebuttal
- ROI metric: hours saved × billable rate / demo session cost
Chatbot Pitch Delivery
| Tier | Description | Price signal |
|---|---|---|
| T1 | Read-only assistant (Q&A, code lookups) | Project-based |
| T2 | T1 + calculation templates + doc generation | Retainer |
| T3 | T2 + custom KB + pilot + 3-month support | Enterprise |
Objection handling:
- "It hallucinates" → Show disclaimer; position as senior-engineer-reviewer tool, not replacement
- "Our data is proprietary" → Explain no-training policy; local-deploy option (T3)
- "Too expensive" → Anchor to billable hours saved in pilot log
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
gsd-complete-milestone
Archive completed milestone and prepare for next version
gsd-reapply-patches
Reapply local modifications after a GSD update
gsd-verify-work
Validate built features through conversational UAT
gsd-thread
Manage persistent context threads for cross-session work
clinical-trial-protocol
Generate clinical trial protocols for medical devices or drugs through a modular, waypoint-based architecture with research-only and full protocol modes.
single-cell-rna-qc
Performs quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MAD-based filtering and comprehensive visualizations.
Didn't find tool you were looking for?