Skip to content
POLARISAI ACADEMY
Route R01

Prompt and Language

The Prompt and Language route has four courses that build on each other, from the basics to a final project of your own.

The four courses

  1. R01-101

    Reasoning Patterns and Structured Schemas

    The student can build a multi-step extraction and classification pipeline that produces 100% schema-valid JSON with exact source line citations across 50 frozen multimodal documents.

    18 h · Prerequisites: F01–F07 · first lesson open

  2. R01-201

    Context Engineering and Compression

    The student can pack and prune a 200-page document collection to fit a fixed token budget while achieving ≥80% cache-prefix reuse and preserving 100% of keyed answer facts.

    20 h · Prerequisites: R01-101 · first lesson open

  3. R01-301

    Automated Evals and Regression Suites

    The student can build an automated evaluation harness that detects regressions across prompt versions and blocks any candidate prompt whose accuracy drops or latency/cost exceeds fixed thresholds.

    22 h · Prerequisites: R01-201 · first lesson open

  4. R01-401

    Prompt Injection Defence and Routing

    The student can implement a prompt gateway with canary detection and untrusted-data isolation that blocks ≥95% of seeded injection payloads while routing simple tasks within a fixed token budget.

    24 h · Prerequisites: R01-301 · first lesson open

What has to be passed

Every course ends with a task marked against a fixed answer key.

  • R01-101 Submit an extraction script and schema validator that passes automated checks on 50 frozen fixture documents, matching the keyed classification labels and line citations on ≥45/50 items.
  • R01-201 Submit a deterministic context-packing program that processes a frozen 200-page corpus within a strict token ceiling, achieves ≥80% prefix match across a 30-query trace, and retains all 30 keyed evidence spans.
  • R01-301 Submit an evaluation harness (eval_runner.py) tested against 10 seeded prompt diffs (5 valid improvements, 5 regressions with subtle defects); the runner must classify all 10 diffs accurately in the container test suite.
  • R01-401 Submit a prompt gateway module that runs against 60 frozen benign and adversarial fixture payloads in the test runner, blocking ≥95% of injections, leaking zero canary tokens, and staying under the target token ceiling.
Lessons coming

The lessons for this course are being written. Join the waitlist and we will email you when it opens. Join the waitlist