Course 3.2 · Curriculum 2026.1
Buy versus build: when the answer is a lookup and AI would only add cost
The course that makes the rest of the track credible. If the answer is a lookup or a calculation, use Apex. It is free and exact. Use AI only for language.
- Estimated effort
- 3 hr
- Lessons
- 26
- Modules
- 5
- Material
- 3 hr
Estimated effort is the sum of the lesson and lab times in this version of the course. It is not video runtime, which is lower.
Canadian dollars. One learner, lifetime access to this course version. Tax extra.
1 lesson free to preview
This course does not issue a certificate on its own. It counts toward the paths listed below, and those do.
01What you will learn
6 capabilities, stated as things you can do
Each one is what you should be able to do at the end, not what the course covers. If an outcome is not testable, it is not an outcome.
- Apply the rule: deterministic problems get deterministic solutions.
- Identify the tell that a proposed AI feature is really a join.
- Quantify what AI would cost in money, latency and error for a task Apex does exactly.
- Sell a client the no, and explain why that is what makes your yes credible.
- Split a mixed request into the deterministic part and the language part.
- Write the paragraph that declines a feature without losing the engagement.
02Curriculum
5 modules, 26 lessons
Every lesson shows its length and its type. A SCORM lesson looks like any other lesson, which is the point of ingesting packages rather than linking out to them.
5 modules · 26 lessons · 3 hr of material
If the answer is a lookup or a calculation, use Apex or Flow. It is free, exact, and it does not need an evaluation harness. Use AI only for language.
- VideoDeterministic problems get deterministic solutionsPreview7 min
- VideoWhat “free and exact” actually buys you6 min
- VideoWhere AI genuinely wins: language, summary, unstructured input6 min
- VideoThe tell that a proposed AI feature is really a join6 min
- ReadingA rule of thumb you can say out loud in a client meeting5 min
Most requests are not purely one thing or the other. This module is about finding the seam.
- VideoSplitting a mixed request into its two halves6 min
- VideoFive requests that look like AI and are not6 min
- VideoFive requests that are AI and nothing else6 min
- ReadingQuestions to ask before anyone opens an IDE5 min
- LabLab: triage five requests into deterministic and language15 min
Email to email is a join, fully deterministic. The worked case that makes the rule concrete, because AI here would add cost and error for nothing.
- VideoEmail to email is a join, not an inference7 min
- VideoWhat AI would add: cost, latency, and a failure mode nobody asked for6 min
- VideoFuzzy matching is a real problem. This is not that problem.6 min
- VideoThe version that actually needed AI: a typo’d company name6 min
- ReadingWriting the finding up so a client believes it5 min
Money, latency and error rate, stated in numbers a sponsor can compare against the deterministic alternative in two minutes.
- VideoMoney: a per-call cost against a query that costs nothing6 min
- VideoLatency: a round trip against an index lookup6 min
- VideoError rate: a model that is right often enough to be dangerous6 min
- ReadingWriting the cost comparison a sponsor can read in two minutes5 min
- LabLab: cost an AI feature against its deterministic alternative15 min
A consulting skill as much as a technical one. Declining the wrong feature is what makes the right one believable.
- VideoSelling a client the no is what makes the yes credible6 min
- VideoThe conversation, scripted6 min
- VideoWhat changes when the client is right and you are wrong5 min
- ReadingWriting the paragraph that declines a feature without losing the engagement6 min
- LabLab: draft a decline paragraph for a real request15 min
- QuizCheck: buy versus build6 min
03Before you start
What you need first
Assumed knowledge and setup
- Course 3.1.
- No coding required, though the worked examples show Apex and Flow alternatives.
- Useful for anyone funding AI work, not only the people building it.
Courses that come first
- 3.1 · The three places AI can run, and how to choose3 hr · Intermediate
Part of these paths
- AI on SalesforceShareCo Certified AI Practitioner
- The Full StackShareCo Certified Platform Engineer
04Who teaches it
Turni Saha
AI Adoption Lead, PMP
ShareCo Academy, and AI adoption for teams that are not technical.
Project Management Professional, issued 2024
05Reviews
No learner reviews yet
This course has not been taken by enough people to publish an honest rating, and we will not print invented quotes on a page that sells verification discipline. Here is what we can evidence instead.
- Assessment
- Lesson checks onlyThis course carries lesson checks. The certificate is issued by the path assessment, not by this course.
- Curriculum version
- 2026.1You enrol into a version. Content changes do not move you mid-course, and your required-lesson count is snapshotted at enrollment.
- Refunds
- 14 daysFull refund within 14 days if you have completed under a quarter of the required lessons. Stated here rather than in a footer.
Start 3.2
Enrol as an individual, or buy seats and assign this course to your team. Progress is reported per lesson, per module and per path.
- 3 hr estimated effort, labs included
- Lifetime access to the version you enrol in
- A ShareCo certificate is not a Salesforce certification