Clear Promise
After finishing, you can choose the right AI surface or harness for a task, write the handoff, and avoid locking the work to one vendor.
$49 standalone Build
AI Surfaces and Harnesses
Stop choosing AI tools by hype. Learn how to route work to chat, saved projects, file-backed harnesses, agents, runtimes, or human review based on the task, context, risk, and evidence required.
Buyer Clarity
Use this quick check to decide whether this Build is worth buying by itself.
Who This Is For
Learners comparing ChatGPT, Claude, Gemini, Codex, Claude Code, Antigravity, CLI, MCP, projects, apps, or automation surfaces and wondering what belongs where.
First 15 Minutes
List three recurring tasks, decide whether each needs chat, project space, harness, runtime, or human-only review, and name the verification step.
Quality Checks
The routing choice names the task, context source, tool surface, handoff format, permissions, verification method, and portability fallback.
How access turns into a first artifact.
This is a standalone Build. Checkout creates a clean learning handoff: what you bought, where to start, and which first artifact to build before opening the full Build pack.
1. Start Checkout
Use checkout when this Build matches the current work bottleneck.
2. Receive Access Status
The receipt confirms the Build, price, access link, start file, refund window, and support boundary.
3. Open The Start Path
After checkout, start with the Build room or paid-buyer start file before opening the Build zip.
4. Build The First Artifact
Use the first action, worked example, template, and rubric to produce a useful first draft.
Why This Stands Alone
This Build is worth buying by itself when tool choice is creating drag. The payoff is a routing habit: knowing when to use chat, projects, Codex, Claude Code, Antigravity, CLI/MCP-connected tools, a runtime, an agent candidate, or human review.
Immediate Payoff
Route three real tasks by context, risk, evidence, file access, repeatability, and human approval needs.
Finished Artifact
Leave with a surface selection map, portable project brief, harness handoff, runtime readiness check, and portability rewrite.
Quality Gate
Use the choice rubric to avoid overusing chat, overbuilding agents, locking prompts to one vendor, or moving work into a harness without evidence needs.
The Build stands alone because a better surface decision can save time and reduce risk before the learner builds any agent or workflow.
Buy This If
This Build is for the moment when a learner has more than one AI option and needs a repeatable way to decide where work belongs.
Good Fit
- You use ChatGPT, Claude, Gemini, Codex, Claude Code, Antigravity, or similar tools and feel tool-choice friction.
- You are not sure when chat is enough and when a project, harness, runtime, or agent is safer.
- You need a plain definition of a harness, CLI, MCP, runtime, and agent.
- You want prompts that survive across tools instead of locking everything to one product UI.
Not The Right First Step
- You want a ranking of the best AI tools this month.
- You want an always-on agent before your manual workflow is stable.
- You need procurement advice for enterprise AI platforms.
- You are not ready to name the task, risk, output, and human gate.
Your First 30 Minutes
A learner should get a practical win before the Build starts to feel theoretical. Start with one bounded artifact, use low-risk material, and stop before widening the system.
First Artifact
A three-task surface triage card.
- List three real AI tasks with different shapes: drafting, file work, source comparison, project context, browser check, or repeatable workflow prep.
- Mark what each task needs: memory, files, tools, browser checks, repeatability, or approval.
- Route each task to chat, project space, harness, agent, runtime, or human-only hold, then name the risk or human gate.
Early Win
You stop comparing tools in the abstract and can explain why one task belongs in ChatGPT, Claude, Gemini, Codex, Claude Code, Antigravity, or a human-only lane.
Open first: FIRST_ARTIFACT_STARTER.md, then HARNESS_DEFINITION_SHEET.md and HARNESS_HANDOFF_PREVIEW.md.
The Lesson Sequence
The Build keeps the durable skill in front: decide what kind of environment the work needs before choosing the tool.
| Lesson | Outcome | Class Asset |
|---|---|---|
| 1. What a surface is | Separate model, chat surface, project space, harness, runtime, and agent. | Start here file |
| 2. Route the task | Classify real tasks by context, files/tools, repeatability, risk, and desired output. | Surface routing lesson |
| 3. Use chat or a project on purpose | Decide when a bounded chat is enough and when saved context earns a project brief. | Project brief template |
| 4. Define harness work | Write a safe handoff for a file-backed workspace such as Codex, Claude Code, Antigravity, Cursor, or Windsurf. | Harness definition sheet |
| 5. Screen agent and runtime risk | Name identity, permission, memory, schedule, logging, and confirmation risks before automating. | Agent risk map |
| 6. Make the method portable | Rewrite one tool-specific instruction into a packet that works across ChatGPT, Claude, Gemini, Codex, Claude Code, and Antigravity. | Portability checklist |
Flagship Example
The flagship example routes a mixed work task list across chat, project spaces, coding harnesses, always-on agent candidates, runtimes, and human-only review.
Weak Tool Choice
"Use the best AI tool for my training hub, file cleanup, inbox, sales page, and monthly checks."
- It treats unlike tasks as one problem.
- It hides file, identity, and action risk.
- It invites stale tool rankings.
Strong Surface Routing
"Use chat for bounded drafts, a project for recurring course voice, a harness for local files and verification, a runtime only after manual proof, and human review for publishing or credential claims."
- The task shape decides the surface.
- The human gate is visible.
- The instruction can move across tools.
Open the full walkthrough: Full Example: Surface Routing Map. For a first-hour proof path, use Sample Lesson: Surface Routing, then compare it with Harness Handoff Preview and Portability Rewrite Preview.
Included Downloads
The Build is built around artifacts, not tool trivia. A learner should leave with a reusable routing habit and a packet they can apply to their own work.
Course Room
- Private paid learner room after access
- Start file, first 15-minute action, lesson path, download shelf, artifact checklist, and completion gate.
Core Class Files
- Student path
- First artifact starter
- Surface selection map
- Surface routing capstone
Tool Choice Files
- Harness handoff prompt
- Runtime readiness check
- Always-on agent risk map
- Portability rewrite preview
Review And Delivery
- Surface choice rubric
- Practice labs and common mistakes
- Workshop adaptation
- Download Build pack
Live delivery use: this Build can become a tool-choice clinic, harness handoff lab, or team routing workshop. The live version should leave participants with a surface map and one portable handoff, not a generic tour of every AI product.
Capstone And Rubric Standard
A learner completes the Build when another person can understand the work, the surface choice, the risk, the human gate, and the evidence of completion without needing a live explanation.
The Finished Packet Includes
- Five routed tasks with reasons and risk levels.
- One project brief for recurring context.
- One harness handoff with scope, allowed actions, verification, and receipt.
- One agent/runtime risk decision.
- One portable instruction packet.
Common Mistakes To Catch
- Using a harness for simple thinking.
- Using plain chat for file-backed work.
- Treating MCP access or app access as automatically safe.
- Turning a workflow into automation before it has manual proof.
- Writing prompts that only work inside one vendor interface.
Next class: Basic Agents, if the surface map reveals one narrow recurring helper role. Agentic Workflows comes later, once the learner has a repeatable multi-step process with review gates.
Access, Support, And Refund Boundary
This is a standalone Build, not a promise of unlimited consulting or external certification. Learners should know exactly what access includes before payment is accepted.
Access
Self-serve access should include at least 12 months of access to the Build materials and minor updates during that access period.
Support
Access help, missing-file fixes, broken links, and basic start-path confusion are included. Custom implementation, done-for-you work, live consulting, and artifact review are separate offers.
Refund Window
Confirm the 7-day fit-based refund window before payment is accepted. The window should cover duplicate charges, access problems, or a genuine mismatch with the Build description.
Tool choice stays platform agnostic. Completion means you build the artifact and review it against the rubric; it is not external accreditation or a guarantee of business, career, or productivity outcomes. For file, agent, workflow, or workshop work, start with low-risk material and keep human review in the loop before external use. Read the Buyer FAQ for fit, support, refund, safety, and completion boundaries.
Return To Current Offers
For now, access routes through the self-serve checkout page so the first public offer can stay evidence-led while the broader catalog matures.