SnowPro Specialty: Gen AI Training
Cortex-specific rather than general LLM theory, and Snowflake removed Document AI content from 1 March 2026, so confirm which version you book.
Six modules mapped to the published blueprint, taught live by practitioners, and built so the capability outlasts the exam. Take it as a scheduled cohort or have it delivered privately to your team.
DA-400 Specialist · Developer · 6 modules · cohort or private team delivery
This exam is covered by Snowflake Platform Mastery
If you want the platform rather than the certificate, the mastery track covers everything this exam tests and a good deal it does not. Our programme leads to the certification, not the other way round. Take this page's programme when you need the credential on a date; take the track when you need the capability.
Snowflake Platform Mastery
The platform is easy to start and easy to overspend on. This is the programme that fixes the second part. A full working command of Snowflake for a data team, covering every domain the SnowPro ladder examines without organising the year around an exam date.
What it covers
Six modules mapped to the published exam blueprint, each ending in applied work rather than a quiz. The schedule is agreed before the programme starts.
Gen AI principles on Snowflake
Where an LLM belongs in a data platform, governance of prompts and outputs, cost per token, and features worth refusing to build.
Cortex AI functions
COMPLETE, SUMMARIZE, TRANSLATE, SENTIMENT, EXTRACT_ANSWER and classification functions called from SQL, model selection, and controlling output shape.
Retrieval, Search and Analyst
Chunking strategy, EMBED_TEXT functions and VECTOR columns, Cortex Search services, Cortex Analyst semantic models, and evaluating retrieval on its own.
Open-source models in Snowflake
Snowpark Container Services compute pools, image repositories and service specifications, plus registering and serving models from the Model Registry.
Governance and operations
Role and tag control over AI objects, Cortex Guard, per-function cost monitoring, and logging what a model was asked and answered.
Exam drilling
Scenario practice across the three published competency areas on the current scope that excludes Document AI, plus full-length timed attempts.
Two ways to take it
| Feature | Cohort | Enterprise |
|---|---|---|
| Format | Scheduled live sessions with a mixed peer group | The same programme delivered privately to your team |
| Live sessions | Instructor-led, scheduled | Instructor-led, scheduled around your delivery calendar |
| Labs | Shared lab scenarios | Run against your own estate where access allows |
| Tailoring | Fixed syllabus | Sequenced to your platforms, workloads and governance |
| Exam focus | Blueprint coverage plus question-format drilling | Blueprint coverage, plus the gaps found in your team's baseline |
| Group size | Individual seats | Whole team, one cohort |
| Best for | One person preparing around a job | A team standardising on the same platform |
The certification itself
The credential this programme prepares you for, as Snowflake publishes it. Open the official page from the exam code before you book or budget.
- Exam
- Not published
- Level
- Exam fee
- 225 USD
- Validity
- 2 years
The exam fee is paid to Snowflake, not to us, and is separate from the programme. See the Snowflake credential reference for the rest of the ladder and the renewal rules.
Take this programme
Register and we will come back with cohort dates, scope and pricing. For a team, tell us how many people and which platforms you run and we will scope a private delivery.
Independent training. Durga Analytics is not a vendor partner and does not award credentials. Verify exam details officially. We prepare people for the exam; no training provider can guarantee a pass. Credential detail reviewed 15 October 2026.